Generating optimized process variable values and control data for an additive construction process

Abstract

The invention relates to a method and a device (60) for generating optimized process variable values (PGO) for an additive construction process of a manufacturing product (2, 2', 2''). For this purpose, request data (AD) of the manufacturing product (2, 2', 2'') is provided, and an optimization method is then carried out in order to ascertain the optimized process variable values (PGO) while taking into consideration the request data (AD), wherein at least one optimized scan direction distribution (SSV) for at least one region of the manufacturing product (2, 2', 2'') is ascertained as an optimized process variable value (PGO) using an AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS). The optimized process variable values (PGO) are then provided. The invention additionally relates to a method and a control data generating device (54, 54') for generating control data (BSD, PSD), to a method for generating an AI-based optimization unit (KNSP, KNWS), to a control method, to a controller (50) for a production device (1) for an additive manufacturing process, and to a corresponding production device (1).

Description

[0001] Generation of optimized process variable values ​​and control data for an additive assembly process The invention relates to a method and a device for generating or determining optimized process variable values ​​for an additive assembly process of a manufactured product (hereinafter also referred to as a “component”), a method and a control data generation device for generating control data for a production device for the additive manufacturing of at least one manufactured product in an additive assembly process, as well as a method and a control device for controlling a production device for the additive manufacturing of a manufactured product. Furthermore, the invention relates to a method for creating an AI-based optimization unit, e.g. a neural network, which can be used in one of the aforementioned methods. Furthermore, the invention relates to a production device for the additive manufacturing of manufactured products in an additiveManufacturing process with at least one such control device. In the production of prototypes and now also in series production, “additive build-up processes” (also called “additive manufacturing processes”) are becoming increasingly relevant. In general, “additive build-up processes” are understood to mean build-up processes in which the finished product is built up, usually on the basis of digital 3D design data, by depositing material (the “build-up material”). The build-up is usually, but not necessarily, carried out layer by layer. The term “3D printing” is often used as a synonym for additive manufacturing; the production of models, samples, and prototypes using additive build-up processes is often referred to as “rapid prototyping,” and the production of tools as “rapid tooling.” One basic possibility for implementing an additive build-up process involves the selective solidification of the build-up material, whereby this solidification takes place atMany manufacturing processes can be carried out with the help of radiation energy, e.g. electromagnetic radiation, in particular light and / or heat radiation, but possibly also with particle radiation, such as electron beams. Such processes that work with radiation are also referred to as "beam melting processes". Examples of these are so-called "laser powderbed fusion processes" (also called "selective laser sintering" or "selective laser melting") or "electron powderbed fusion processes". In this process, thin layers of a mostly powdery build-up material are repeatedly applied on top of each other and in each layer, the build-up material is selectively solidified by spatially limited irradiation of the areas that are to belong to the finished product after production, in a type of "welding process" in which the powder grains of the build-up material are partially or completely melted with the help of the energy locally introduced by the radiation at this point.be melted. After cooling, these powder grains are then bonded together to form a solid. During the solidification of the build material, the energy beam is guided along predefined scan paths, usually taking into account a defined irradiation strategy, usually a so-called "hatch strategy", within the contours of the area to be solidified in the respective layer, over the layer on the build field in order to melt and solidify the material in a desired spatial and temporal sequence. In addition, other process parameter values, such as intensity, focus extension or energy beam extension (e.g., energy beam diameter), a form of intensity distribution (or intensity profile), as well as a feed rate (or scan speed) of the energy beam, layer thickness, etc., are specified and must be adhered to as closely as possible. The latest findings show that in theIn additive manufacturing, some of the process variables have a significant influence on the locally resulting microstructure in the component. This can be the case, not only, but especially, with metals as the build material. The microstructure, in turn, determines component properties at the macro level and thus the quality of the component, in particular whether it meets certain quality requirements. As will be explained later, the key process variables can include, in addition to the aforementioned process parameter values ​​of the energy beam, in particular the hatch strategy. Furthermore, all of these process variables also influence the build speed and thus productivity, energy consumption, and build costs. When optimally setting some of the process variables, i.e., selecting the appropriate process variable values, competing objectives (such as build speed on the one hand, and stiffness or strength of the component on the other) may need to be weighed against each other.Similarly, in other additive build-up processes, e.g., processes in which material is applied only at the desired locations using a material application head, which subsequently solidifies or is solidified, various process variables, in particular the selection of material solidification paths (hereinafter, such solidification paths are also generally referred to as "scan paths") and the feed rate, etc., can have a significant influence on the component properties and quality of the component on the one hand, and on the productivity on the other, which is why the process variable values ​​must be selected skillfully. This also applies in principle to additive manufacturing processes such as, for example, powder deposition welding (laser cladding) and wire deposition welding (Direct Energy Deposition (DED) or Wire-based Arc-light Additive Manufacturing (WAAM)). It is therefore an object of the present invention to provide suitable methods for generating optimizedProcess variable values ​​for an additive build-up process and for generating control data based thereon or for the additive manufacturing of a manufactured product, as well as suitable devices therefor. This object is achieved by a method for generating optimized process variable values ​​according to patent claim 1, a method for generating control data according to patent claim 11, a method for controlling a production device for the additive manufacturing of a manufactured product according to patent claim 12, a method for creating an AI-based optimization unit according to claim 13, a device for generating optimized process variable values ​​according to patent claim 14, a control data generation device according to patent claim 15, a control device for a production device for the additive manufacturing of a manufactured product according to patent claim 16, and a production device for the additive manufacturing of manufactured products according toPatent claim 17 is solved. The method according to the invention for generating or determining optimized process variable values ​​for an additive build-up process (or manufacturing process) of a manufactured product from multiple layers of a build-up material comprises at least the following method steps: First, requirement data of the manufactured product are provided. These include, for example, geometric data of the manufactured product. In the simplest case, the geometric data can only be maximum dimensions, which can be determined, for example, by the available installation space, and / or minimum dimensions. However, the geometric data can also include certain exact dimensions, e.g., of parts or sections of the component, such as dimensions of connecting pieces in order to be able to couple the component to other parts, exact lengths of the component to be maintained in certain extension directions, etc. In particular, they can also include the exact dimensions of the componentwith all details. The geometric data can be provided in any way, for example by input at a user interface, by importing from other program parts, networks and / or data storage devices. For example, the geometric data can also include CAD data of the component, which can be imported from a design program. The requirements data can, however, also include data on other requirements, such as mechanical stress requirements and heat treatment requirements, etc. If no special heat treatment is necessary after manufacture of the component, the heat treatment requirements are, for example, simply the thermal requirements resulting from the cooling of the component, in particular the cooling rates. The heat treatment requirements are usually defined by a function with a time-temperature profile (i.e. a temperature-time history function).In many cases, e.g., if the component cools down after production without special measures, these heat treatment requirements (or a corresponding function that defines these heat requirements) can also be neglected in the optimization process. Taking the requirement data into account, the method according to the invention then carries out an optimization process to determine the optimized process variable values. In this case, at least one optimized scan direction distribution for at least one area of ​​the manufactured product is determined as an optimized process variable value using an AI-based optimization unit. "AI-based" here means that the optimization unit is based on artificial intelligence (AI). For example, this can be a neural network, as will be explained in more detail later using examples. Such an "area of ​​the manufactured product" can be, for example, a (virtual) segmentof the component, which, as will be explained later, preferably extends over several layers. As will also be explained later, a component can be (virtually) divided into so-called "segments," whereby a segment preferably comprises a subsection / area of ​​the manufactured product. The sum of the segments of the manufactured product then results in the manufactured product. However, the entire manufactured product can also be formed from just one segment, especially in the case of small objects. More complex components, however, generally have several segments. In principle, the "area of ​​the manufactured product" can also itself comprise several segments or any sections, or the entire manufactured product. A scan direction distribution in a segment is also referred to below as a "segment scan direction distribution," since it is a distribution of the scan directions within the segment. A segment scan direction distribution givesThis indicates the frequency with which scanning directions (e.g., which scanning direction angles) occur in the respective segment. A "scan" is generally understood to mean the movement of the unit responsible for solidifying the material at the respective locations along the specified "scan path", for example, a material application head that releases material that then solidifies, and / or an energy beam for solidification, etc. For example, in the beam melting processes mentioned above, "scanning" is understood to mean the movement of the point of impact of the energy beam (i.e., in selective laser melting and similar processes, the movement of the laser focus) on the current working plane along the specified "scan path". The current "scan direction" is always the current direction along the currently traversed scan path. The scan direction can, for example, be determined by a scan direction angle in the current working plane in relation to an arbitrarily specifiedReference direction must be specified. The speed of movement of the impact surface of the energy beam or of the unit responsible for solidifying the material at the respective locations on the build field is the scanning speed, which can also be modified depending on the location, i.e., it does not have to be constant. The "working plane" is generally the plane that is perpendicular to the build direction of the component at the respective point. In the case of a "Laser Powderbed Fusion process" as explained above, this is the plane in which the powder layers are applied, i.e., the scanning paths of a layer are generally in a plane that does not tilt during the solidification of a layer. For other additive manufacturing processes, such as powder deposition welding (laser cladding) and wire deposition welding (Direct Energy Deposition (DED) or Wire-based Arc-light Additive Manufacturing (WAAM), a working plane could also be defined, without loss of generality, via theA so-called tangential plane can be defined. Such a tangential plane has its origin at the point of impact of the beam energy on the material. It should be mentioned at this point that a scan path does not have to be continuous, but can also comprise several spaced-apart scan path sections, particularly in one plane. Thus, the individual "hatches" explained below, along which an energy beam is moved across the material layer in the working plane according to a "hatch direction arrangement" (generally also called "hatch strategy" for short), in order to solidify the cross-section of the component in the plane, can each be viewed as individual "scan path sections". The selective irradiation or the movement of the impact surface of the energy beam on the build field in a beam melting process, as mentioned above, usually takes place according to a suitable irradiation strategy. As a rule, during aSolidification process, larger two-dimensional areas, i.e., larger surfaces on the construction site, are to be irradiated. Regardless of how the energy beam is generated and the precise location of the impact point on the construction site, it has proven advantageous to initially virtually "divide" at least such larger areas to be irradiated according to a selected pattern, for example, into virtual "stripes", a diamond pattern, a checkerboard pattern, or the like. The individual areas of this pattern, i.e., defined sub-areas, for example, geometrically standardized surface pieces such as stripes or fields, are then usually traversed with the energy beam in the form of a so-called "hatch" (generally also called a "hatch"). In a stripe pattern, the building material - viewed macroscopically - is gradually solidified along parallel stripes, and in detail - viewed microscopically - the movement of the impact surface of the energy beam onthe build area along closely spaced hatch lines, which run back and forth across the irradiation strip boundaries, perpendicular to the direction of extension of the respective irradiation strips. A hatch direction arrangement or hatch strategy can, for example, define whether to work with changing hatch directions (alternating irradiation) or with constant hatch directions (unidirectional irradiation, i.e. with a return from one hatch end to the beginning of the following neighboring hatch in the irradiation strip). A hatch direction can therefore also be regarded as a local set of scan directions. In the contour areas of the component, the scan paths usually run along the contour to ensure that the surface is as smooth as possible. The above-mentioned "scan direction distribution" (or the "segment scan direction distribution" of a segment) can - as will be explained in more detail later - be determined, among other things, by aThe "layer scan direction arrangement" generally defines the essential strategy of the scan paths in a layer-by-layer build-up, i.e. the irradiation strategy in beam melting, in a respective layer, i.e. in which way or direction the scan paths in a layer run relative to each other, and if necessary also in which order the scan paths are traversed in the layer in order to melt and solidify the material in the desired spatial and temporal sequence. The "layer scan direction arrangement" thus defines the relevant scan directions that are or were specified within a layer in the build-up process for the essential part of the surface of the layer. The layer scan direction arrangement can therefore also generally, as already mentioned above for the hatch strategy, have a significant influence as a process variable on the locally resulting microstructure in theComponent. It should be noted that a rotation of the orientation of the layer scan direction arrangement from layer to layer – as will be explained later – is not to be understood as a change in the layer scan direction arrangement. This means that layers can be considered to have been created with the same layer scan direction arrangement, even if the orientation has been changed (by rotation around the main construction direction in which the layers lie on top of one another). Changes to individual scan path sections, in particular along the component contours in the respective layers, which are caused, for example, by this change in orientation or by the change in the component contour from layer to layer, etc., are not considered to be significant changes in the layer scan direction arrangement in this sense. This means that the layer scan direction arrangements of the layers can be considered to be identical within the meaning of the invention, since such changes generally do not lead to asignificant change in the "intra-slice scan direction distribution" (which is essentially determined by the slice scan direction arrangement) and thus would not lead to a significant change in the property values ​​of the segment. A typical example of a "slice scan direction arrangement" therefore comprises the previously explained hatch direction arrangement or hatch strategy or can be defined by it. In the optimization method, the scan direction distribution is therefore advantageously an optimization variable. This is preferably a continuous, particularly preferably continuous, optimization variable in the optimization method. Equally preferably, a scan direction distribution can also be defined "quasi-continuously", e.g., by a sufficient number of discrete values. Thus, a "quasi-continuous" definition of a segment scan direction distribution in a plane can be achieved by a sufficient number of discrete, closely spaced values, such as 360Support points over an angular range of 360°. Preferably, as will be explained in more detail later, further optimized process variable values ​​can also be determined in the optimization process, such as optimal parameter sets for the component, in particular optimal parameter sets for the various segments of a component. Such a "parameter set" comprises, for example, a defined group of process parameter values, i.e. a tuple of individual process parameter values, with which the machine is later controlled or is to be optimally controlled for building at least one layer of the respective segment. The optimized or optimal process variable values ​​determined in the optimization process, e.g. the optimized scan direction distribution(s), in particular segment scan direction distributions, and if applicable the optimal parameter sets, are finally provided in order, for example, to generate optimized control data based thereon, with which aProduction facility can be controlled during the assembly process. The provision of the optimized process variable values ​​can, for example, include saving them for later use and / or transferring them to another calculation unit and / or transmitting them to the production facility. The method according to the invention for generating or determining the optimized process variable values ​​enables, depending on the specific design, a very general optimization of the property profile of additively manufactured components and is advantageously not limited to optimization with regard to a single component characteristic, such as mechanical strength. Rather, it represents a possibility for solving boundary value problems of any thermophysical and manufacturing-technological nature. In addition to taking into account a requirement profile (based on the requirement data), depending on the design within the framework of the proposed methodalso the most cost-effective way in terms of production technology to meet the requirements set can be determined. This can be achieved, for example, by maximizing the volume build-up rate, as will be explained in more detail later. Examples of suitable optimization methods, which also work, for example, with segment scan direction distributions as optimization variables as well as a selection of optimal parameter sets, are already described in detail in patent application DE 102022 117 935, to which reference can be made here or the content of which is hereby fully incorporated. The present invention can, among other things, build on the methods mentioned therein or further improve the methods mentioned therein. In addition to the optimization methods therein, an AI-based optimization unit is now used according to the invention to determine at least one optimized scan direction distribution, for example theSegment scanning direction distribution(s) for at least one area of ​​the manufactured product. This enables a considerable acceleration of the entire process, as will be described later using an exemplary process sequence. In particular, in this way, with the help of the AI-based optimization unit, a type of preselection of optimal process variable values, in particular scan direction distribution(s), can be made within one stage of the complete optimization process, which simplifies and accelerates the further procedure. On the basis of the optimized process variable values ​​thus obtained according to the invention, control data according to the invention can then be generated for a production device for the additive manufacturing of at least one manufactured product. A corresponding method according to the invention for generating control data for a production device for the additive manufacturing of at least one manufactured product from several layers of aBuild material comprises at least the following method steps: - In a first stage, optimized process variable values ​​are provided, which were generated for the additive build process according to the inventive method characterized above, e.g. by directly adopting these optimized process variable values ​​or retrieving them from a memory. - In a second stage, the control data for the production device are then generated in such a way that the optimized process variable values ​​are sufficiently achieved in the additive build process according to a predetermined evaluation criterion and can preferably also be maintained during the manufacturing process. Depending on the current technical possibilities, it may be that the optimized process variable values ​​cannot be maintained exactly or can only be maintained with extremely great effort. The predetermined evaluation criterion should therefore preferably be defined in such a way that the optimizedProcess variable values ​​in the production process are achieved or approximated as closely as possible (optimally exact) or at least lie within a predetermined tolerance range around the respective optimized process variable value and are maintained during the manufacturing process. The tolerance range can also depend on the respective optimized process variable value. Preferably, this is control data for a production device (i.e. the production device is then also designed to suit this purpose), with which, as described above, build-up material, preferably powder, is built up and selectively solidified in a preferably powder-bed-based beam melting process, wherein for solidification, the build-up material on a build field is irradiated with at least one energy beam, wherein an impact surface of the energy beam is moved along predetermined scan tracks on the build field in order to irradiate the build material in a target area in and around theTo melt the impact surface. "Moving" the energy beam or the impact surface of the energy beam can be understood as the usual deflection of the energy beam, e.g., by galvanometer mirrors, but also as a movement of the entire radiation output unit, e.g., in the form of a diode bank, in particular a laser diode bank, or by moving beam shaping. A "target area" here refers to the impact surface, i.e., the area on the surface where the energy beam impacts, but also the area beneath it, i.e., into the depth of the material or layer, and possibly also an area around this impact surface in which the energy beam still has an effect, e.g., through heat conduction in the build-up material. Merely for the sake of completeness, it should be mentioned again that the energy beam comprises both particle radiation and electromagnetic radiation, such as light or, preferably, laser radiation.The control data can therefore preferably be exposure control data, such as scan data that defines or specifies the movement of the energy beam on the surface, control data for adjusting the level of energy or laser intensity, control data about the "shape" of the beam or the beam profile and / or the focus or the extent of the beam perpendicular to the beam direction. Furthermore, this control data can also - as will be explained later - include other control information, such as coating control data that specifies the thickness of a current layer, information for controlling pre- or post-heating with other energy input means, for the injection of inert gas, etc. It should also be mentioned at this point that the control data can be used for "simple" control of the process, but also for regulating the process, for example by the control data containing target data for aspecify further control of the process. In other words, with the aid of the method according to the invention, the required variables for a controller can also be derived, which receives, for example, actual data for feedback, which is determined using melt pool monitoring or a temporally resolved temporal and / or spatially resolved imaging for monitoring the built-up layer, such as thermally using optical tomography. Such methods are known to those skilled in the art. Disturbances arising in the production process are compensated in order to remain as close as possible to the target process control specified by the control data. In a method according to the invention for controlling a production device for the additive manufacturing of a manufactured product, control data is first generated in the manner mentioned according to the invention and then used to control the device with the control data. The control data can begenerated and transmitted as a complete package or a type of "control protocol" to the device, which then carries out the production process. In principle, however, it would also be possible to determine control data for subsequent process steps during the ongoing process, for example, to determine the control data for the next layer or segment while a layer or segment is being solidified. According to the invention, at least one AI-based optimization unit is used in the optimization process. Such an AI-based optimization unit should generally be created in a manner tailored to the optimization process. Thus, at least one AI-based optimization unit preferably comprises at least one optimization unit based on reinforcement learning and / or a neural network (in particular a deep learning network). If it is a neural network, this must, for example, first be suitablybe trained. Only the trained neural network then forms the AI-based optimization unit suitable for the method. A method according to the invention for creating an AI-based optimization unit (i.e., for example, for setting up and training a neural network), which can be used in one of the optimization methods described above to determine optimized process variable values ​​for a plurality of different types of requirement data (in particular requirements or requirement parameters such as mechanical stress requirements and heat treatment requirements), comprises at least the following method steps: - Firstly, at least one first AI-based optimization unit is determined (e.g., a first neural network is trained), which, based on a first type of requirement data (e.g., mechanical stress requirements), determines optimized process variable values ​​of a first type of process variable (e.g., aoptimal parameter set). - On the other hand, at least one second AI-based optimization unit is determined (e.g., a second neural network is trained), which determines optimized process variable values ​​of a second type of process variables (e.g., scan direction distributions) based on the first type of requirement data (e.g., the aforementioned mechanical stress requirements) or which determines optimized process variable values ​​of the first type of process variables (e.g., an optimal parameter set) or the second type of process variables (e.g., the scan direction distributions) based on a second type of requirement data (e.g., heat treatment requirements). - Subsequently, an AI-based combination optimization unit (e.g., a combined neural network) is created using a training method in which at least the first and second AI-based optimization units are coupled to one another to monitor the trainingthe AI-based combination optimization unit can be used. In this way, with less computing and time expenditure (compared to training with the help of purely "classical" (i.e., non-AI-based) optimization methods, which are also possible in principle, as will be shown later using examples), AI-based (combination) optimization units can be created, which can quickly determine optimal values ​​for different types or combinations of types of different process variables based on any different types of requirement data. It is pointed out again that the above-mentioned requirement data or process variables are to be seen only as examples for the inventive method for creating an AI-based optimization unit, even if in the specific case these are data or variables that are preferably used within the scope of the desired optimization. An inventiveA device for generating or determining optimized process variable values ​​for an additive assembly process of a manufactured product comprises (for carrying out the above-described method according to the invention) at least the following components: - A requirement interface unit, designed to provide requirement data of the manufactured product, which, for example, includes geometric data of the manufactured product. This can be, for example, an interface for transferring the data and / or a memory in which this data is stored. - An optimization unit, designed to carry out the optimization method described above for determining the optimized process variable values ​​taking into account the requirement data, comprising at least one AI-based optimization unit to determine at least one optimized scanning direction distribution for at least one region of the manufactured product as an optimized process variable value, -A process variable value interface unit, designed to provide the optimized process variable values, including the scan direction distribution(s), e.g. the optimal segment scan direction distribution(s) and the optimal parameter sets. This can be, for example, an interface for transferring the data and / or a memory in which this data is stored. In principle, the request and process variable value interface unit can also be implemented as a common unit, or at least use common components, such as a common memory. A control data generation device according to the invention for generating control data for a production device for the additive manufacturing of a manufactured product in an additive build-up process, preferably in an above-mentioned beam melting process, comprises at least the following components: - An above-described device according to the invention for generating orDetermination of optimized process variable values ​​for the additive build-up process of a manufactured product and / or an interface to such a device for adopting the optimized process variable values. Such an interface also includes the possibility of accessing a memory, e.g., a database, in which the optimized process variable values ​​were previously stored by the device for generating the optimized process variable values. - A data generation unit for generating the control data for the production device such that the optimized process variable values ​​are sufficiently achieved in the additive build-up process according to a predetermined evaluation criterion, as already explained above in connection with the method for generating control data. The control data generation device can, for example, be part of a control device of such a production device for the additive manufacturing of a manufactured product.However, it can also be implemented independently on another computer in order to then transfer the data to the control device. Accordingly, a control device according to the invention for a production device for additive manufacturing of a manufacturing process has a control data generation device according to the invention and / or an interface to such a control data generation device for receiving the relevant control data from the control data generation device. Such an interface in turn comprises the possibility of accessing a memory, e.g. with a database, in which the control data, e.g. from the control data generation device, was previously stored. The control device is designed to control the production device using this control data, e.g. for irradiating the build-up material with the energy beam. A production device according to the invention for additive manufacturing of manufactured products inAn additive build-up process or manufacturing process comprises, in addition to the components customary depending on the type of manufacturing process, such as, for example, a feed device for introducing build-up material – for example, in the form of a layer of build-up material – into a process chamber and an irradiation device for selectively solidifying the build-up material by irradiation with an energy beam, at least one such control device. It should be noted at this point that the device may also comprise several irradiation devices, which are then controlled in a coordinated manner using the control data in order to sufficiently achieve the optimized process variable values ​​according to the given evaluation criteria or to maintain them during the manufacturing process. The device according to the invention for generating or determining optimized process variable values ​​and the inventiveControl data generation devices can each be implemented largely in the form of a computer unit, even in the form of a common computer unit, with suitable software. The computer unit can, for example, have one or more cooperating microprocessors or the like. In particular, it can be implemented in the form of suitable software program parts in the computer unit of a control device of a production device according to the invention. A largely software-based implementation has the advantage that even previously used computer units, in particular control devices of production devices for additive manufacturing, can be easily retrofitted by a software or firmware update in order to operate in the manner according to the invention. In this respect, the object is also achieved by a corresponding computer program product with a computer program that is directly integrated into a memory device of a computer unit,in particular a device for generating or determining optimized process variable values, a control data generation device or a control device, with program sections to carry out all steps of the method according to the invention when the program is executed in the computer unit or control device. In principle, the required software components or program sections can also be distributed across several interconnected computer units, which in this sense can also be regarded as a common, merely distributed computer unit. Such a computer program product can, in addition to the computer program, optionally comprise additional components such as documentation and / or additional components, including hardware components such as hardware keys (dongles, etc.) for using the software. For transport to the computer unit or control device and / or for storage on or in theA computer-readable medium, for example a memory stick, a hard disk, or another portable or permanently installed data storage device, on which the program sections of the computer program that can be read and executed by a computer unit, in particular the control device, are stored, can serve as the computer unit or control device. In particular, the inventive method for creating an AI-based optimization unit can also be implemented with the aid of a computer program product that can be installed on any computer. The AI-based optimization unit (for example, a neural network) can itself form a computer program product, which can then, for example, be transferred to one of the above-mentioned units in order to use it within the inventive optimization method. Further, particularly advantageous embodiments and developments of the invention emerge from thedependent claims and the following description, wherein the independent claims of a claim category can also be developed analogously to the dependent claims and embodiments of another claim category and, in particular, individual features of different embodiments or variants can be combined to form new embodiments or variants. As explained above, in the optimization process (taking into account the requirement data), at least one optimal parameter set can also be determined as at least one further optimized process variable value. Such an optimal parameter set can preferably be selected from a number of "candidate parameter sets", wherein this selection is preferably also carried out using an AI-based optimization unit. This can be a separate AI-based optimization unit which serves only the purpose of finding optimal parameter sets (i.e., forFor example, a neural network that has been trained precisely for this purpose). However, it can also be an AI-based combination optimization unit that has been constructed (for example, using the method described above) in such a way that it can simultaneously serve to find several optimized or optimal process variable values, e.g., to find an optimized pair of scan direction distribution and parameter set. A parameter set (which can also be synonymously referred to as a "process parameter set"), and thus also a candidate parameter set, comprises, as already mentioned, a defined tuple of individual process parameter values, with which the machine is later controlled or is to be optimally controlled to build at least one layer of the respective segment. The process parameter values ​​can, in particular, be predefined, preferably discrete (i.e., non-continuous) optimization variables. The parameter set preferably comprisesone or more of the following process parameters: - Power of the energy beam (e.g. the laser power in a laser melting process) - Scanning speed of the energy beam - Hatch distance - Energy beam diameter (e.g. focus extension and shape) - Intensity distribution or intensity profile of the energy beam - If laser as energy beam: continuous or pulsed operating mode - Power curves of the energy beam - Thickness of the layers For different types of build-up material, for example different powder types, preferably metal powder types, several candidate parameter sets can be available. Different powder types can differ in particular according to a) material, whereby there is also a difference between pure material or alloys, b) other powder parameters, such as particle size distribution, sphericity of the particles, chemical properties, etc. Since different powder batches of the same materialcan have different combinations of the aforementioned parameters, each powder batch could also be considered a separate powder type, if this is desired and appropriate. However, a parameter set or a candidate parameter set can also include the type of the associated build-up material itself as an additional "process parameter value", i.e., with the selection of a candidate parameter set, the material type is then determined by this process parameter value (discrete value). This is ultimately a question of the organizational or structural design of a database for the candidate parameter sets. In practice, incidentally, initially only a few candidate parameter sets, e.g., 4 to 20 candidate parameter sets, will be available for a specific material. In principle, the number of candidate parameter sets is only limited by the technical possibilities for the size of the database, i.e., how much storage space andhow much computing time is available (in advance) to create the database. When determining the number of candidate parameter sets, the required computing times can also be taken into account, since limiting the number can reduce the computing time in an optimization process. The use of candidate parameter sets is particularly advantageous for saving computing power. As already mentioned, preferably (e.g., at the start of the optimization process or beforehand), the manufactured product is virtually divided into several segments using requirement data, in particular geometric data, and the optimization process is then carried out in such a way that optimized process variable values, preferably an optimized segment scan direction distribution and an optimal parameter set for each segment, are determined. The determined optimal segment scan direction distributions can then together form an optimalScan direction distribution in the entire component. Preferably, this is done by first defining a so-called "region" (which could also be referred to as "computational region" or "design space") comprising the manufactured product, i.e., the manufactured product is completely captured in the region. This entire region is then (virtually) divided into so-called "segments," whereby the manufactured product comprises at least one such "segment." Generally speaking, a segment is then an area within the region, usually within the component. However, the region can also comprise so-called "powder segments," i.e., non-solidified segments or segments to be solidified. These can be areas within the "region" but outside the contours of the component (but within the build space or production volume of the AM machine, or in the design space), or cavities or hollows in the manufactured product. As will be explained later, the boundariesThe final contour of the component must first be defined between the segments to be solidified and the powder segments. For example, if the area were a cuboid enclosing the finished product, with the finished product being at a distance from all cuboid side surfaces, in the simplest case two segments in the area would be sufficient, namely a solidified or to-be-solidified segment (which encompasses the entire finished product) and a powder segment (which encompasses the entire area outside the finished product). In principle, however, the area boundaries could also completely coincide with the boundaries or contours of the finished product, in which case, for example, there need not be any powder segments at all, provided there are no cavities in the finished product within the area. The segmentation of the component or the entire area can be carried out automatically or according to user specifications with the aid of a user interface, whereby semi-automatic processes are also possible.are possible, i.e. partly automatically and partly according to user specifications. The segmentation is preferably carried out using the requirement data, in particular the geometric data. In this case, for example, the component can also be divided according to certain functionally essential construction phases (i.e. which function the construction phases primarily have), such as strut, pressure plate, flange part, etc. In a particularly preferred embodiment of the method according to the invention, a defined "target function" is used to carry out an optimization process. Suitable and preferred target functions are, for example, also described in detail in DE 102022117 935, which is why explicit reference is again made to this document. For example, using the target function and the requirement data for at least one segment of the manufactured product in the defined area, the selection of at least one optimal "parameter set" from a number of"Candidate parameter sets" and the determination of an optimized or optimal segment scan direction distribution (ultimately matching the optimal parameter set). In the optimization process, an objective function assigned to the respective segment can preferably be selected such that - if necessary while observing certain boundary conditions (e.g. maximum permissible Mises equivalent stress or minimum safety factor for a given external load) - specified target macro-properties (e.g. quality requirement data, in particular load data on loads that the component must withstand, such as high stiffness at the highest possible build rate while maintaining a certain defined safety factor of e.g. 1.65) are achieved as well as possible in the segment, if the optimal process variable values ​​obtained by minimizing the objective function (or at least a sub-function matching the objective macro-properties) are later in theadditive build-up process are adhered to or approximated as closely as possible. The quality requirement data can, in addition to the geometric data, also be part of the aforementioned requirement data. The requirement data can also be taken into account, at least in part, in the defined objective function (directly or indirectly). However, requirement data, in particular geometric data, can also be partially taken into account in the area definition. For example, certain conditions can be specified regarding the external shape of the area, e.g., by the manufactured product fitting into the area and, for example, extending to certain outer surfaces of the area. In this case, a boundary condition in the objective function could be that material must be hardened in certain areas of the area. Particularly preferred in the optimization process for a segment, i.e., for all layers in the segment, is precisely one optimal parameter set from theCandidate parameter sets are selected, as this is considerably less computationally intensive than searching for several optimal parameter sets that are assigned to different layers of the segment. Likewise, there can preferably also be only one optimized segment scan direction distribution per segment. This means that, very particularly preferably, a segment can also be defined in such a way that exactly one optimal parameter set and one optimized segment scan direction distribution apply within the boundaries of the segment. At the boundaries of the segment to another segment, the optimal parameter set and / or the optimized segment scan direction distribution then change. Particularly preferably, optimized process variable values ​​for several segments of the defined area can also be determined in parallel (i.e., coupled) using a common objective function within the optimization method. Very particularly preferably, an optimization is carried out for all segments of the component or evenall segments of the area are coupled in an optimization process. The solution of the optimization process, i.e. the optimal parameter sets obtained with the optimal segment scan direction distributions for the segments, can then also be a Pareto optimum for the entire manufactured product if there is a conflict of objectives between the requirements for the respective segments or for the entire component. In this respect, an optimized scan direction distribution (or component scan direction distribution) is then also sought and found at a higher level for the entire component. A parallel, i.e. simultaneous, determination of optimized process variable values ​​for several segments using a "common objective function" can also be understood as the use of a number of mathematically coupled segment objective functions, whereby the individual segment objective functions are each assigned to one of the segments. Through this coupling, one can ultimatelydefined area, i.e. all segments defined therein, each determine an optimal parameter set and an associated optimized segment scan direction distribution with a common objective function (which is defined by the segment objective functions). This means that the common objective function is then essentially the sum of the segment objective functions across all segments involved in the joint optimization. Most preferably, the objective function includes, as further requirement data, a minimization of a parameter set change within the entire manufactured product. Taking this additional objective into account is equivalent to a reduction of the segment boundaries, as far as possible, i.e. the manufactured product is divided into as few (virtual) segments as possible. This can also be realized by formulating the objective function in such a way that the segment boundary surfaces are minimized. In particular, for this purpose, the optimization process can preferablyThe segment boundaries are considered as a further optimization variable and can then – at the end of the optimization process, i.e. after optimization has been completed – be provided as further optimized process variable values. In other words, the boundaries of the segments can also be shifted during the optimization. In extreme cases, a change in the segment boundaries is possible up to the complete disappearance of a segment. Likewise, new segments could also be created by shifting the segment boundaries. In this respect, in this preferred variant, the number of segments in the area is not necessarily fixed, but can be optimized during the optimization process. In particular, the number of areas can also be minimized in order to achieve the goal of having to change the optimal parameter set in a component as rarely as possible. The shifting of the segment boundaries also affects the outer boundaries of the manufactured product, insofar asThese are defined as segment boundaries between a component segment and a powder segment in the area. In this way, the topology of the component can also be advantageously changed in the optimization process, i.e., for example, certain areas can be shaped differently than was originally specified in a starting specification, if, for example, the requirements for the component are better met with the changed topology or at least sufficiently well met with less effort. In this respect, geometric data of the manufactured product initially specified as requirement data, in particular if they define the shape of the manufactured product more precisely, can also be changed or optimized. As a result of this preferred development of the optimization process, the following optimized process variable values ​​are then preferably obtained for a segment: 1. an optimal parameter set (as the first optimized process variable value), which in turn comprises tuples ofindividual process parameter values, 2. an optimized segment scan direction distribution (as the second optimized process variable value), 3. optimized segment boundaries (as the third optimized process variable value). In order to realize a shift of the segment boundaries in the optimization process, a phase field method, in particular a multi-phase field method, can preferably be used, as described in DE 102022117935 and DE 102022117936. Reference is therefore also made to these documents, in particular with regard to the phase field method. A multi-phase field method is particularly well suited to dealing with variable segment boundaries. Particularly preferably, the parameter sets respectively assigned to the segments can be proportionally assigned at least at the locations that lie in an "interface region" between a number of adjacent segments (at least two different, but possibly also more than two, adjacent segments).Preferably, in the optimization process, the parameter sets present at a location can each be represented by their “shares.” The value of the share can preferably be between 0 and 1, whereby a value of 1 for a parameter set means that this parameter set is present at that location, and a value of 0 means that it is not present. Locations in an interface region between two segments can thus be characterized in the optimization simply by a share of a first parameter set applicable in a first segment and a share of a second parameter set applicable in a second segment. In an interface region where more than two segments meet, shares of more than two parameter sets can also be present at one location. Preferably, at each location, the sum of the shares of all parameter sets present there is equal to 1. Preferably, in the optimization process, the width of the “interface region” (which is then generallyis assumed in the method) can be defined or specified by a user. In the optimization method, one of the process parameter values ​​of the (optimal) parameter set for an individual layer of the segment comprises at least one layer scan direction arrangement, i.e. the scan directions that are or were specified within the respective layer in the build-up process. In particular, this layer scan direction arrangement can comprise the hatch direction arrangement (hatch strategy) in the layer. As mentioned, in each layer there is therefore an "intra-layer scan direction distribution" that is determined by the layer scan direction arrangement. Particularly preferably, a layer scan direction arrangement is selected in the optimization method that can apply to all layers of the segment, apart from a possible rotation of the overall orientation of the layer scan direction arrangement between different layers. The segment scan direction distribution then results as a combination ofthe rotations of the layer scan direction arrangement between the layers in the segment. To optimize the segment scan direction distribution, the relative orientations of the layer scan direction arrangements of different layers of the segment can then preferably be optimized, whereby the rotations of the layer scan direction arrangement between the layers in the segment can be defined by suitable control commands with which the production device can be controlled during the construction of the component. It is particularly suitable for this optimization (sub)problem to use an AI-based optimization unit. Preferably, at least one process parameter value of the parameter set also includes a track width between two solidification paths, e.g., which hatch distance is selected. This track width can be specified in the parameter set independently of the layer scan direction arrangement. Preferably, within theOptimization process, e.g., in the objective function, an orientation of the manufactured product relative to a main build direction (i.e., a relative orientation in the build space) is considered as a further optimization variable. In a layered build, the main build direction is generally considered to be the direction perpendicular to the layers in which the layers are gradually built up one above the other. In a beam melting process, particularly a laser melting process, a Cartesian coordinate system x, y, z is generally defined as the reference system, with the x-direction and the y-direction running parallel to the layer planes or spanning the plane of the build area, and the z-direction pointing vertically upwards from the build area, thus corresponding to the main build direction. At the end of the optimization process, i.e., after optimization has been completed, the optimized orientation found can be provided as a further optimized process variable value. This canbe advantageous in this respect, since the orientation in the build space influences the position of the segment boundaries in space. By taking the orientation into account, it is possible for the optimization to aim, for example, at reducing or even minimizing overhangs and / or support structures. Various requirement data can be taken into account in the optimization process, e.g. in the objective function or in another way. The requirement data can preferably comprise one or more "target production data" and / or "target property data" and / or "constraints". Particularly preferably, one or more of the following target production data can be taken into account: - Build rate in the additive build process, - Material type of the build material (This allows not only the material to be determined, but also the consistency, e.g. whether it is a powder and, if so, with which parameters), - Build technology (i.e. theType of assembly process such as laser melting, electron beam melting, etc.), - Machine type (i.e. the type of production device used). Likewise, one or more of the following target property data can preferably be taken into account: - Target load data (This can, for example, include information about external loads that the component must withstand. However, it can also already include the stress states determined from these external loads, for example in the context of a simulation, i.e. the "internal load", in the respective area of ​​the component and / or in the component as a whole.) - Stiffness (i.e. a resistance to elastic deformation of the finished product in the area of ​​the respective segment.) - Strength (i.e. a resistance to plastic deformation of the finished product in the area of ​​the respective segment.) - Mass and / or mass distribution of the finished product (In many cases, the aim here is to achieve the lowest possibleMass, i.e. to achieve a mass reduction so that the manufactured product is as light as possible and / or to save on material expenditure. However, depending on the component, the largest possible mass could also be deliberately required, at least locally, e.g. for flywheels or the like.) - Surface accessibility (For example, certain requirement data regarding surface accessibility can ensure that post-processing of the component is guaranteed or facilitated. For example, good removability of support structures usually requires good accessibility. Accessibility can also be determined in the optimisation process, preferably using a suitable method, e.g. a ray tracing method or, as described in M. Inui, S. Nagano and N. Umezu, Fast computation of accessibility cones for assisting 3 + 2 axis milling; COMPUTER-AIDED DESIGN & APPLICATIONS, 2018, VOL. 15, NO. 5, 667–676, in a separate process step orCheck process step.) - Support properties (Here, the properties that any support structures should have can be taken into account, e.g., whether they are intended to provide support and / or dissipate heat. It should be noted that a support structure for heat dissipation does not necessarily have to be solidly bonded to the component; there could then also be a powder layer between the support structure and the component, which corresponds to at least a (real) layer thickness. (Moreover, overhangs of a component can be designed in such a way that "supporting supports" are not required.) One or more of the following constraints can also preferably be taken into account: - chemical properties (e.g., that the material for the component should not be rust-resistant), - geometric data (e.g., certain dimensions to be precisely adhered to or maximum / minimum dimensions of the component, as already explained at the beginning). In addition, a multitude of otherRequirement data may be taken into account, depending on the type of manufactured product (component). Some requirement data may also be viewed or declared as "target production data" as well as "target property data" or as "constraints." Likewise, some of the data, in particular the target property data relating to the component's load-bearing capacity, or the chemical properties or chemical resistance, may also be viewed as quality requirement data, as already mentioned above. Particularly preferably, the requirement data may be considered in the optimization process with a predefined weighting, i.e., it may be determined which requirement data are, for example, more important and which are relatively less important. Preferably, as in DE 102022117935, the objective function may comprise a plurality of subfunctions, each of which is assigned specific requirement data, i.e., each of the subfunctions isthen for a specific requirement. Consideration of the requirement data in the optimization process with a predefined weighting can then also be particularly preferably realized simply by having the objective function comprise a sum of weighted sub-functions, wherein the sub-functions are assigned to specific requirement data. Preferably, within the scope of the invention, an optimization process is used which comprises several iteration steps. In an iterative optimization process, in particular, individual sub-functions can be optimized in separate iteration loops, separated from other sub-functions or optimization parameters. Depending on the specific design, the computational effort can thus be reduced. Particularly preferably, at least one AI-based optimization unit is used in at least one iteration step of the iterative optimization process. The entire optimization process can therefore preferably also be used as a type of“Hybrid methods” combine AI-based and “classical” (non-AI-based) optimization methods, whereby individual classical optimization steps, which may also contain iteration loops, can be replaced by an AI-based optimization unit. Preferably, in the optimization method, at least one starting process variable value (e.g., a starting parameter set and / or a starting scan direction distribution, in particular a starting segment scan direction distribution) is initially defined. Preferably, a “starting configuration” is determined, which comprises a combination of several starting process variable values. For example, to determine a starting configuration, at least starting segments can be defined or specified, and for each starting segment, a starting parameter set can be selected from the number of candidate parameter sets, and a starting segment scan direction distribution can be determined. The starting configuration can, for example, be determined in a first step of theoptimization procedure immediately after the definition of the area. In a preferred variant, the candidate parameter set that leads to the highest construction rate in the segment can be selected as the starting parameter set for a segment. However, the starting parameter sets can also be selected differently, e.g., simply stochastic. Particularly preferably, in the optimization procedure, at least one starting process variable value can initially be determined using an AI-based optimization unit. This means that the AI-based optimization unit(s) select(s), for example, suitable starting values ​​or "pre-optimized values" so that the subsequent, e.g., predominantly classical, optimization procedure "converges" more quickly, i.e., reaches the goal more quickly. In particular, at least one AI-based optimization unit can be used to determine a starting configuration (where, as mentioned, at least starting segments are defined and for eachStart segment: a start parameter set is selected from the number of candidate parameter sets and a start segment scan direction distribution is determined. It should be noted at this point that for the "powder segments" mentioned above (i.e., segments in the area that are not too solidified), the energy beam or laser power in the start parameter set can simply be set to 0, i.e., no energy is introduced into these segments. This value is then permanently retained for this powder segment, i.e., it is not changed during the optimization process or iteration. However, the boundaries of the powder segment can shift to neighboring segments if the component topology is also to be optimized in the optimization process. To determine an optimized scan direction distribution and / or select an optimized or optimal parameter set from the available candidate parameter setsIn principle, various criteria and / or methods come into consideration. In a preferred procedure, at least one parameter set suitability value is determined for at least one area of ​​the manufactured product (e.g., for a segment; i.e., segment-wise) for at least a number of possible (candidate) scan direction distributions (or candidate segment scan direction distributions) and / or at least a portion of the candidate parameter sets. A parameter set suitability value can be a scalar value, preferably between 0 and 1, which indicates a measure of the suitability of the respective candidate parameter set to meet certain requirement data. It is also referred to below as the "Parameter Set Score" (or, for short, as the "PS Score"). In this regard, particular reference is also made to DE 102022117935. The value of the PS Score of a candidate parameter set in comparison to the PS Scores of the other possible candidate parameter sets can then, for example, be used to determineIt can be determined whether this particular candidate parameter set (for a specific scan direction distribution) is the most suitable candidate parameter set to meet certain, defined requirement data, or the PS score can be viewed as a measure of the probability that the candidate parameter set (for a specific scan direction distribution) is the best. For example, a candidate parameter set with a PS score close to 1 could be almost 100% suitable to meet the requirement. An optimized scan direction distribution (or segment scan direction distribution for a segment) and / or an optimal parameter set is then selected from the candidate parameter sets using the parameter set suitability values. In this case, parameter set suitability values ​​are particularly preferably determined for different pairs of segment scan direction distributions and candidate parameter sets. This means that for eachFor each segment for which an optimal parameter set and an optimized segment scan direction distribution are sought, parameter set suitability values ​​are calculated, with respect to which the optimization is carried out. In this case, for example, the pair of parameter set and segment scan direction distribution for which the best parameter set suitability value can be determined can ultimately be selected for a segment. Preferably, for at least some of the (segment) scan direction distributions and / or candidate parameter sets (in particular each pair of parameter set and segment scan direction distribution), several requirement-specific parameter set suitability values ​​(i.e., requirement-specific PS scores) are determined for different requirement data. This means that the requirement-specific PS score can be used as a comparison measure to clarify which of the available candidate parameter sets (if necessary in combination with a specific scan direction distribution or segment-scan direction distribution) is the best to meet the precisely defined specific requirement, e.g., the required build rate and / or strength. Examples for determining possible (requirement-specific) PS scores will be given later. Particularly preferably, the requirement-specific parameter set suitability values ​​for a scan direction distribution and / or a candidate parameter set (in particular each pair) can each be combined to form an overall parameter set suitability value (for the respective segment). Since it is generally necessary in the optimization process to select an optimal parameter set and / or a (segment) scan direction distribution, even when there are several different, sometimes even conflicting, requirements, it is sensible to work with such overall parameter set suitability values. The selection of an optimal parameter set from the candidate parameter sets can then be carried out using theOverall parameter set suitability values ​​of the candidate parameter sets are determined. Examples of suitable combinations of possible (requirement-specific) PS scores will also be given later and also described in DE 10 2022 117 935. The type of combination can also depend on the requirements. Preferably, the combination method can comprise a multiplication of the requirement-specific parameter set suitability values. In particular, an overall parameter set suitability value can be obtained by simply multiplying all requirement-specific parameter set suitability values ​​of the relevant candidate parameter set. Most preferably, optimized process variable values ​​for the finished product can be determined within the optimization method in such a way that optimized process variable values ​​(preferably an optimal parameter set and an optimized segment scan direction distribution) are determined for each individual segment.which are optimized, on the one hand, with regard to an overall parameter set suitability value in the respective segment and, on the other hand, also overall with regard to a "sum parameter set suitability value" in the finished product. Such a sum parameter set suitability value can, for example, be formed by summing the total parameter set suitability values ​​of the individual segments across all segments of the finished product. Thus, in this preferred approach, the optimization is also carried out for all segments in parallel using a common objective function, with the sum parameter set suitability value preferably serving as at least a significant part of the objective function, which, for example, is to be maximized. The determination of the segment scan direction distributions and / or the selection of an optimal parameter set from the candidate parameter sets for a segment (in particular the selection of the pairs of scan direction distribution and candidate parameter set) can be carried out inWithin the scope of the invention, this can preferably be carried out using an AI-based optimization unit. Preferably, at least one AI-based optimization unit is used, the generation of which involved training the AI-based optimization unit (in particular the neural networks) using parameter set suitability values, in particular using overall parameter set suitability values. If AI-based optimization units (e.g., neural networks) are used at the segment level, which are trained to optimal overall parameter set suitability values, the selection of the pairs of scan direction distribution and candidate parameter set with the "best" (e.g., largest) overall parameter set suitability value can be significantly accelerated. This means that by training AI-based optimization units using parameter set suitability values ​​(in particular, requirement-specific parameter set suitability values) and / orOverall parameter set suitability values ​​and / or sum parameter set suitability values, as well as the subsequent use of at least one AI-based optimization unit trained in this way, the optimization itself ultimately takes place (albeit quasi "indirectly") also using the relevant suitability values, only generally faster. The process variable values ​​optimized overall with regard to a sum parameter set suitability value in the manufactured product are preferably determined using an (iterative) combinatorial optimization method, particularly preferably a heuristic approximation method, further particularly preferably a simulated annealing method and / or a quantum annealing method. Simulated annealing methods or quantum annealing methods can be used in particular to find an approximate solution to optimization problems which, due to their high complexity, require the complete testing of all possibilities andmathematical optimization methods. Such methods can therefore be particularly well applied within the scope of the present invention, even if a large number of possibilities have to be tried out, since the various variants can be determined relatively quickly and “computationally inexpensively” using AI-based optimization units, such as neural networks. The simulated annealing method, in combination with the AI-based optimization method, can therefore, for example, contribute particularly well to solving the combinatorial problem of swapping parameters. The optimization method can, as already mentioned, preferably comprise several iteration steps, i.e. at least one part of the method that can be run iteratively several times. For example, in one or more steps, a (pre-) determination of (if applicable, starting) scan direction distributions and the selection of optimal (if applicable, starting) parameter sets can be carried out, e.g. using the(Total) PS scores can be determined, and in one or more other steps, e.g., using the objective function or subfunctions, the optimized segment scan direction distribution and the optimized segment boundaries can be determined, and if necessary, in yet other steps, further optimized process variable values ​​(with or without the objective function) can be determined. Changes to the scan direction distributions and parameter sets are also possible, as will be explained later using examples. As mentioned, AI-based optimization units can also be useful in all of these steps, e.g., to perform substeps within "classic" optimization steps, or AI-based optimization units can be trained using the "classic" optimization steps (or by using the results of these optimization steps as training data) so that they can later replace these optimization steps. A multi-step optimizationThe constructed iteration loop can then be run through several times until a predetermined termination criterion is met. This termination criterion can preferably be met if the process variable values ​​found in the current iteration loop are optimal, i.e. no significantly better values ​​are found in a repeated run, and / or if all requirements according to predefined evaluation criteria are sufficiently met and / or if, for example, a certain number of runs has been reached. Other termination criteria are also conceivable. The optimization method preferably comprises at least one state determination step in which a “state description” is determined for a manufactured product that would be built from the desired construction material using the current process variable values. In an iterative method, the “current process variable values” are the process variable values ​​that apply in the current run of the iteration loop.In the first run, the current process variable values ​​are the process variable values ​​of the above-mentioned start configuration. To determine the state description in the state determination step, the state of the current system, i.e., the component with the current segments and the parameter sets currently assigned to the segments, can preferably be simulated (i.e., how the respective segment of the – still virtual – manufactured product, for which the optimal process variable values ​​are currently being sought, would behave, for example, under a certain load if it were produced with the current process variable values). Therefore, the state determination step could also be referred to as a “state simulation step.” Particularly preferred simulation methods include, for example, a finite element method or finite volume simulation. For example, a load simulation or a vibration simulation can be carried out with the (virtual) component, and the resultis then the possible load or the natural frequency of the system or component, assuming the current configuration of the process variable values. In particular, the aforementioned expected stress states in the component can be determined, which can be used, for example, in the AI-based optimization unit (in particular a neural network) as input data to obtain scan direction distributions or optimal parameter sets optimized for these load requirements. Preferably, the state description is compared with predefined quality requirements for the manufactured product. This allows it to be checked whether the manufactured product meets the predefined quality requirements. The state simulation step can be carried out as a (quality) requirement simulation, i.e., using quality requirement data that specifies how the component may behave under certain loads or the effects of certain forces.or should. The state simulation step can be carried out, in particular, using at least part of the requirement data, which can also include suitable quality requirement data. The requirement data can therefore be used in the selection of the optimal parameter set and in the objective function. If the state description does not meet the predefined quality requirements, a (further) change to the current process variable values ​​can preferably be made. Such a further change can be carried out both in further separate optimization process steps or method steps, as described later, and can also be integrated into various steps in the further method. Optionally, after a further change to the process variable values, another state determination step and a comparison of the state description with the predefined requirements can be carried out. This means that this control can also be carried out in an iteration loop.A termination criterion for this iteration loop can be, for example, a success (the state description meets the predefined requirements), but also the reaching of a maximum number of iterations. Then, if necessary, it is possible to start all over again with a modified starting configuration (e.g., with a different material). The optimization process can then include various further optimization process steps – e.g., also in individual iterative loops – as described, for example, in DE 10 2022117935. All steps mentioned there can, in principle, also be used advantageously here (whereby they can be supported or replaced by the use of AI-based optimization units, if this is advantageous). At the end of the sequence of steps of the iterative process, there are preferably improved segments with improved current parameter sets andimproved segment scan direction distributions are present, i.e., an improved configuration or improved current process variable values ​​are then available. In a particularly preferred development of the method according to the invention, a property database of a property database system is used within the framework of the optimization method (e.g., in one of the aforementioned steps) to determine or select a changed (updated) segment scan direction distribution for a segment. In such a property database system, properties of the manufactured product to be built, or more precisely of individual layers and / or of segments of the manufactured product formed therefrom, can be stored depending on the respective process parameter set of the respective layer or segment in question and, if applicable, depending on the segment scan direction distribution. For the implementation of such a property database system, variousPossibilities. In particular, the property database system can also comprise multiple property databases, e.g., with different properties and / or parameter assignments. Preferably, the property database system comprises a so-called "basic property database." In this database, "basic properties" of individual layers can be stored depending on the process parameter sets to be used or used to build the layers (including the layer scan direction arrangement or hatch direction arrangement or the type of build material, which are also a process parameter of the respective process parameter set). Thus, in such a database, each of the individual parameter sets is assigned at least one basic property value, preferably a group of basic property values, which a layer of the segment or component would have if the respective layer were manufactured using the assigned parameter set.Methods for constructing and using such a basic property database are described in detail in DE 102022117935 and in particular also in DE 102022117936, the content of which is also fully incorporated herein. As explained therein, in a suitable test method using previously manufactured test specimens, at least one basic property value and / or a microstructure can be determined for each of these test specimens. These microstructures can be stored or stored as an entry in the basic property database, linked to the parameter set used to manufacture the test specimen, which can preferably include, among other things, the type of build material and a layer scan direction arrangement or hatch direction arrangement / hatch strategy. In particular, macro properties or "macro property values" of a segment formed from the layers or even of an entire component can then be derived from these basic properties of the layers.Such a "macroproperty value" describes a property value at the macroscopic level or from a macroscopic perspective, i.e., which property the entire segment possesses, such as thermal conductivity, fracture strength, etc. Preferably, several macroproperty values ​​of the segment or several segments of the component are determined within the framework of the method. A macroproperty value can include a tensorial value, such as an elasticity tensor, but also a categorical value, such as corrosion resistance or not, the nature of a lattice structure, e.g., face-centered cubic (fcc), body-centered cubic (bcc), or hexagonal close-packed (hdp). Various macroproperty values ​​are explained below. If the properties of the individual segments of the component at the macroscopic level, i.e., the "macroproperty values," are known, this can also provide information about the component properties.and the quality of the component as a whole, in particular whether it meets certain quality requirements. The macro-property values ​​of the segments can therefore also be used in the above-mentioned condition determination step to determine a condition description of the manufactured product. Preferably, the basic property database can comprise, for a plurality of different parameter sets, as a basic property value, a "texture" of a layer which was manufactured using the respective parameter set (i.e. also using a specific build-up material) in an additive build-up process. The term "texture" refers to the totality of the orientations of the crystallites within a structure, i.e., it is a crystallographic texture which should not be confused with a surface texture, such as the roughness of a surface. Particularly preferably, the texture is in the form of the so-called"Orientation density distribution function" (ODF). The texture or ODF can be determined, for example, in a measurement under the scanning electron microscope using an EBSD method (EBSD = Electron Backscatter Diffraction) or other methods. Alternatively, or particularly preferably additionally, the basic property database can also include further basic property values, which can be determined, for example, on the basis of the texture, in particular the orientation density distribution function, of the layer for the parameter set. The further basic properties can be calculated from the texture or ODF using the known properties of the single crystals of the building material (e.g., by averaging or a homogenization method, as also explained in detail in DE 102022117936). For example, such basic properties can be the yield point, a tensile strength inarbitrary directions, etc., to name just a few. Conversely, the texture could also be derived from other basic property values ​​or macroproperty values, such as the elasticity tensor. Preferably, the basic property database can each comprise basic property values ​​for a reference orientation of the respective slice scan direction arrangement, in particular the hatch direction arrangement. The reference orientation or reference alignment can be arbitrarily selected. For a slice whose slice scan direction arrangement, and thus also its "intra-slice scan direction distribution," is rotated relative to the reference orientation by at least one rotation angle (in any direction around the main construction direction, i.e., the direction perpendicular to the slice planes), a basic property value can then be determined or calculated using the rotation angle from the corresponding basic property value stored for the reference orientation.This is possible through simple angle conversions. A rotation of the layer scan direction arrangement, in particular the hatch direction arrangement, from layer to layer is common, for example, in beam melting processes. A typical example would be a 67° rotation angle from layer to layer. There are various possibilities for determining a macroproperty value of a segment. In a preferred procedure, as mentioned, a macroproperty value of a segment with several superimposed layers is determined or combined from the basic property values ​​of the individual layers. This is preferably done using a mathematical "homogenization method." A corresponding method is, as mentioned, explained in detail in DE 102022117936, so that reference can be made thereto. To further save computing time, e.g., with recurring configurations within segments, preferably at least one macropropertyproperty value of at least one segment can be determined using a provided basic property database. Alternatively or additionally, the property database system preferably comprises a so-called "macro property database." In this, at least one macro property value, preferably a group of macro property values, of segments (consisting of several layers) can be stored for various combinations of segment scan direction distributions and parameter sets (also depending on the construction material), which would or were created with the segment scan direction distribution assigned in the database and the assigned parameter set. For the determination or selection of a modified segment scan direction distribution for a segment, it can then preferably be taken into account whether for a specific combination (i.e., a "candidate combination") of possible segment scan direction distributionsand (e.g., within the optimization process) current parameter set (including the build material) a macro property value is already entered in the macro property database. If this is the case, it can be considered whether this already stored segment scan direction distribution (and thus in particular also the hatch direction arrangement in the individual layers or "standard" hatch strategy) should be used for the segment to be manufactured, which may be much more advantageous in terms of computational technology and time but may, for example, be slower to build, or whether a strategy not yet stored with an individual hatch direction arrangement should be used, which may be faster and / or have other advantages, but requires a more complex calculation from individual base property values. If, on the other hand, no "standard" build strategy, especially a "standard" hatch strategy, can be used, a more complex calculation must be carried out anyway.from basic property values. On the one hand, determining macro property values ​​for entire segments by querying a macro property database is much simpler and faster than determining the macro property values ​​for the segment from the basic properties of the individual layers. On the other hand, creating and storing a large number of macro property values ​​requires considerable computing time and storage space. The macro property database therefore preferably contains at least macro property values, preferably groups of macro property values, for the most frequently used build-up strategies, especially in the beam melting process, "standard exposure strategies" or so-called "standard hatch strategies" that are regularly used. Typical standard hatch strategies in the beam melting process are the so-called 67° hatching or the xy hatching (= 90° hatching). In these processes, theOrientation of the hatch strategy rotated by 67° or 90°, whereby the hatch strategy remains essentially unchanged. If certain queries occur repeatedly, they are usefully included in the entries of the "standard" hatch strategies of the macro property database. A database system could therefore preferably be structured in such a way that it is recorded which combinations of segment scan direction distributions and parameter sets are used most frequently, and then new entries are created in the macro property database accordingly, i.e. the database system "learns" as it were. As mentioned, in addition to the texture or ODF, there are a multitude of other property values ​​(in particular base or macro property values) that may be of interest. These can usually be calculated from the texture or ODF using the known properties of the single crystals of the construction material (e.g., by averaging). Particularly preferably, at least one of theProperty values, in particular the basic or macro property values, at least one value of one of the following material parameters: - elasticity tensor - "tensile strength tensor" (this indicates the mechanical stress at a location in the workpiece at which a certain yield criterion exists; a definition of the entries for the tensor variables for the respective yield criterion can be found, for example, in J. Betten, Kontinuumsmechanik, 1993, Springer-Verlag) - yield point distribution (for example in the form of the Hill tensor, as can also be found in the book by J. Betten) - hardening coefficient - thermal conductivity - fracture strength. Such a property value can preferably comprise several direction-dependent partial values ​​for at least one material parameter, i.e. the property values ​​can also be anisotropic. In general, a property value can therefore be defined as a tensor, e.g. as a vector (1st order tensor) or a matrix (2nd order tensor), in order to have three dimensions ordirections, or as a 4th-order tensor to take properties in the crystal system into account. An example of this would be the 4th-order elasticity tensor, where the elasticity tensor entries of the various crystal space directions contain values ​​for a general three-dimensional stress state, from which the E-moduli, for example, in a layer in the x-direction and in the y-direction can be calculated by conversion. A similar anisotropic behavior can also be present, for example, in the yield point distribution or the tensile strength tensor. Without loss of generality, other common forms of representation can also be used, such as the Voigt notation. The optimization method preferably includes at least one "cavity testing step". In this step, it can be checked whether cavities present in the finished product after construction, which may be filled with unconsolidated powder, correspond to a surface of themanufactured product. This serves to check whether the powder can be removed from the cavities of the component later, and if so, how well. Therefore, this cavity testing step can also be referred to as a "depowdering testing step." For the exact procedure, reference can again be made to DE 102022117935. If it turns out during the cavity testing step that not all cavities can be depowdered as desired, the geometry of the component may be changed again if necessary. For example, the optimization process can then start again from the beginning, in particular with a different start parameter set. Furthermore, the optimization process can preferably include at least one heat conduction testing step, in which it is checked whether a planned heat treatment with regard to specified quality criteria would be possible with the manufactured product, i.e., heat treatment requirements for the component are checked. In this case, it can be checked, in particular, whetherthe heat treatment can be carried out within a reasonable time with sufficient final quality. If this is not the case, the optimization process could also start again from the beginning, in particular with a different starting parameter set. In a particularly preferred variant of the invention, the heat treatment requirements can also be taken into account when determining optimized scan direction distributions or optimal parameter sets in an AI-based optimization unit (in particular a neural network) by transferring a time-temperature profile corresponding to the load requirements along with the input data for the AI-based optimization unit, as will be explained later using an example. As mentioned above, the control data for the production device for the additive manufacturing of a or the finished product can then be generated based on the optimized process variable values, so that theoptimized process variable values ​​in the layer-by-layer additive build-up process are sufficiently achieved according to a predefined evaluation criterion. In this case, an optimal orientation of the layer scan direction arrangement, i.e., in particular, the direction of the hatch direction arrangement or hatch strategy of the individual layers, can preferably be selected in a segment for each individual layer in such a way that the optimal segment scan direction distribution is achieved or approximated as well as possible across all layers in the segment. This means that the initially continuous optimization variable "scan direction distribution" (in particular, "segment scan direction distribution") is discretized with respect to the control parameters in order to take into account in the layer-by-layer build-up that only one predefined layer scan direction arrangement or hatch strategy is present in each layer, preferably the same layer scan direction arrangement in each layer, only rotated relative to each other.The method described above allows, as mentioned, a general optimization of the property profile of additively manufactured components. It takes into account the correlation between the selected manufacturing strategy, in particular the selected manufacturing variables (e.g., the process parameters in the parameter set), and the resulting component properties. The process variables that have a significant influence on the microstructure, which in turn essentially determine the component properties at the macro level or the quality of the component, such as the machine configuration, the exposure strategy, and / or post-processing, can be considered with different weightings. As mentioned, the method is not limited to optimization with regard to a single criterion, but represents a possibility for solving boundary value problems of any thermophysical and manufacturing-technological nature. This can not only ensure compliance with theNot only can the necessary requirement profile (especially the quality requirements) be ensured, but the most cost-effective method for meeting the requirements can also be found. Furthermore, the method presented here differs from a conventional optimization method, such as those offered by topology optimization programs already in use, in that it has several options for meeting the requirement of a local property. For example, the need for locally increased material stiffness can be met by adding material, but also by adapting the scanning strategy to create a desired texture or by changing the material. From these possibilities, the optimization method presented here always finds a solution on the Pareto front defined by the boundary value problem. Many of the statements made aboverefers to observations and phenomena that apply to metallic materials – such as the derivation of properties from the crystallographic texture. Therefore, the method is particularly well suited to metallic materials and is preferably used for these materials. In principle, however, a correlation between selected production parameters and resulting component properties can also be determined in the same or similar way for ceramic or polymeric materials, e.g., semi-crystalline polymers, and thus the method can be extended to these material classes through appropriate adaptations. The invention is explained in more detail below with reference to the attached figures using exemplary embodiments. In the various figures, identical components are provided with identical reference numerals. They show: Figure 1 is a schematic, partially sectioned view of an exemplary embodiment of a device.for additive manufacturing to implement the invention with a control data generation device and a device for generating optimized process variable values ​​as well as with a checking device and a device for determining property values, Figure 2 shows a schematic representation of a rod-shaped sample component with two segments and a schematic representation of possible layer scan direction arrangements and their orientations in different layers, Figures 3 to 6 are schematic representations to explain how the layer scan direction arrangements and their orientations of the different layers of the sample component from Figure 2 can lead to different segment scan direction distributions of the two segments, Figure 7 shows a schematic representation of a further example of a segment scan direction distribution, which describes almost a uniform distribution, Figure 8 shows a schematic representation of a further example of aSegment scan direction distribution, which describes an approximate uniform distribution, Figure 9 is a schematic diagram of an embodiment of a device for generating optimized process variable values, Figure 10 is a block diagram for the setup of a possible target function for an optimization method, e.g. according to Figure 12, Figure 11 is a diagram for the course of a subfunction ^ ^in order to take a safety factor into account in a possible objective function for an optimization method, e.g., according to Figure 12. Figure 12 shows a flowchart of a possible process sequence of an optimization method of an embodiment of a method for generating optimized process variable values. Figure 13 shows a perspective view of an example of a component to be manufactured with a schematic representation of possible forces acting on the component. Figure 14 shows the component according to Figure 13 with a grayscale representation of the loads acting on the component in the individual sections due to the external forces. Figure 15 shows the component according to Figures 15 and 14 with a representation of a possible (virtual) segmentation of the component and a possible definition of an area surrounding the component for the optimization method according to Figure 12.Figure 16 is a flowchart of a possible method sequence within method step 3 of the optimization method according to Figure 12, Figure 17 is a schematic representation of a first embodiment of a neural network, Figure 18 is a simplified flowchart of a possible method for training a neural network as in Figure 17, Figure 19 is a schematic representation of a second embodiment of a neural network, Figure 20 is a schematic representation of a third embodiment of a neural network, Figure 21 is a schematic representation of a fourth embodiment of a neural network, Figure 22 is a simplified flowchart of a possible method for training a neural network as in Figure 21, Figure 23 is a simplified flowchart of an alternative method for training a neural network as in Figure 21,Figure 24 is a schematic representation of a fifth exemplary embodiment of a neural network. Figure 25 is a simplified flowchart of a possible method for training a neural network as in Figure 25. Figure 26 is a block diagram of an exemplary embodiment of a device for determining property values ​​of a segment. The following exemplary embodiments are described with reference to a production device 1 for the additive manufacturing of manufactured products in the form of a laser sintering or laser melting device 1, with explicit reference once again to the following:that the invention is not limited to laser sintering or laser melting devices. The production device 1 is therefore also referred to below as a "laser melting device" 1 - without any loss of generality. Such a laser melting device 1 is shown schematically in Figure 1. The device has a process chamber 3 or a process space 3 with a chamber wall 4, in which the production process essentially takes place. In the process chamber 3 there is an upwardly open container 5 with a container wall 6. The upper opening of the container 5 forms the current working plane 7. The area of ​​this working plane 7 lying within the opening of the container 5 can be used to build the object 2 and is therefore referred to as the construction field 8. The container 5 has a base plate 11 movable in a vertical direction V,which is arranged on a support 10. This base plate 11 closes off the container 5 at the bottom and thus forms its base. The base plate 11 can be formed integrally with the support 10, but it can also be a plate formed separately from the support 10 and attached to the support 10 or simply mounted on it. Depending on the type of specific build material, for example the powder used, and the manufacturing process, a build platform 12 can be attached to the base plate 11 as a build base, on which the object 2 is built. In principle, however, the object 2 can also be built on the base plate 11 itself, which then forms the build base. The basic construction of the object 2 takes place by first applying a layer of build material 13 to the build platform 12, then – as explained later – with an energy beam E at the points that are to form parts of the object 2 to be manufactured.The build material 13 is selectively solidified, then, with the aid of the support 10, the base plate 11, thus the build platform 12, is lowered, and a new layer of the build material 13 is applied and selectively solidified, etc. In Figure 1, the object 2 built in the container on the build platform 12 is shown below the work plane 7 in an intermediate state. It already has several solidified layers, surrounded by unsolidified build material 13. Various materials can be used as the build material 13, preferably powder, in particular metal powder, plastic powder, ceramic powder, sand, filled or mixed powders, or even pasty materials. The work plane 7 here defines the x / y plane of a Cartesian reference coordinate system. The z-direction points vertically upwards from this x / y plane and forms the main build direction.Since in this direction, the layers L of the component 2 are gradually built up one upon the other as the base plate 11 is successively lowered. Fresh build material 15 is located in a reservoir 14 of the laser melting device 1. With the aid of a coater 16 movable in a horizontal direction H, the build material can be applied in the form of a thin layer in the working plane 7 or within the build area 8. Optionally, an additional radiant heater 17 is located in the process chamber 3. This can be used to heat the applied build material 13, so that the irradiation device used for selective solidification does not have to introduce too much energy. This means, for example, with the aid of the radiant heater 17, a quantity of basic energy can be introduced into the build material 13, which is of course still below the necessary energy.in which the build material 13 melts or sinters. An infrared radiator, for example, can be used as the radiant heater 17. For selective solidification, the laser melting device 1 has an irradiation device 20, or more specifically, an exposure device 20 with a laser 21. This laser 21 generates a laser beam E (as an energy beam E for melting the build material in the build field 8). The energy beam E is then deflected by a downstream deflection device 23 (scanner 23) in order to follow the exposure paths or tracks provided according to the exposure strategy in the respective layer to be selectively solidified and to selectively introduce the energy. This means that the impact surface 22 of the energy beam E is moved on the build field 8 by means of the scanner 23.wherein the current movement vector or the movement direction S (or scanning direction S) of the impact surface 22 on the construction field 8 can change frequently and quickly. This laser beam E is focused onto the working plane 7 in a suitable manner by a focusing device 24. The irradiation device 20 is preferably located outside the process chamber 3, and the laser beam E is guided into the process chamber 3 via a coupling window 25 mounted on the top side of the process chamber 3 in the chamber wall 4. The irradiation device 20 can, for example, comprise not just one, but several lasers. These can preferably be gas or solid-state lasers or any other type of laser, such as laser diodes, in particular VCSELs (Vertical Cavity Surface Emitting Lasers) or VECSELs (Vertical External Cavity Surface Emitting Lasers) or a row of these lasers. The laser melting device 1 can furthermore (not shown,known to those skilled in the art) devices, etc., in order to apply methods such as melt pool monitoring or the like, in order to compensate for any disturbances that may arise in the production process in order to remain as close as possible to the desired process control specified by the control data created according to the invention. The control device 50 here has a control unit 51, which controls the components of the irradiation device 20 via an irradiation control interface 53, namely, in this case, it transmits laser control data LS to the laser 21, scan control data SD to the deflection device 23, and focus control data FS to the focusing device 24. The control unit 51 also controls the radiant heater 17 using suitable heating control data HS, the coater 16 using coating control data ST, and the movement of the carrier 10 using carrier control data TSD, thus controlling the layer thickness. The control device 50 is, here, for example, via a bus 55 or another data connection,coupled to a terminal 56 with a display or the like. Via this terminal 56, an operator can control the control device 50 and thus the entire laser melting device 1, e.g., by transmitting process control data PSD. In order to optimize the production process, the process control data PSD, in particular the exposure control data BSD of the process control data PSD (both synonymously abbreviated simply as "control data") are generated or modified in the manner according to the invention by means of a control data generation device 54, 54' such that the control of the production device 1 is effected such that, during the additive build-up process, certain optimized process variable values ​​PGO are sufficiently achieved and maintained according to a predetermined evaluation criterion.as already mentioned above. For this purpose, the control data generation device 54 can also have a suitable device 60 for generating the optimized process variable values ​​PGO - in particular in the form of suitable software or the like. This can in turn have, as subunits (e.g., software modules, routines, objects, etc.), a checking device 80 for checking the (expected) compliance with property requirements by a component that was built using specific process variable values, and a device 70 for determining property values ​​of segments of such a component. Preferred procedures for determining optimized process variable values ​​PGO,and preferred embodiments of suitable devices will be explained later with reference to Figures 2 ff. The control data generation device 54 can, for example, be part of the control device 50 and be implemented there, for example, in the form of software components. Such a control data generation device 54 integrated into the control device 50 can, for example, accept requirement data AD (including geometric data GD) for the component to be manufactured and, on this basis, generate the optimized process variable values ​​PGO and, based thereon, the appropriate control data PSD and transmit them to the control unit 51. The control data PSD comprise, in particular, exposure control data BSD, but possibly also other control data, such as, for example, coating control data ST or carrier control data TSD, in order to select a suitable layer thickness. However, it would also be possiblethat the control data generation device 54' is implemented on an external computer unit, for example, here the terminal 56, and already creates optimized process variable values ​​PGO and the corresponding process control data PSD (in particular exposure control data BSD) for the component to be manufactured based on the request data AD (including the geometric data GD), which are then transferred to the control device 50. In this case, the internal control data generation device 54 present in the control device 50 could also be dispensed with. A variant is also possible in which, based on the request data AD (including the geometric data GD), the optimized process variable values ​​PGO are determined for the component to be manufactured in a separate device 60 (e.g., on a dedicated computer unit connected to the bus 55), which are then transferred, for example, to the respective control data generation device 54.54', so that it only determines the appropriate control data PSD, BSD for this purpose. The control data generation device 54, 54' then no longer requires a device 60 for generating the optimized process variable values ​​PGO (or a checking device 80 or a device 70 for determining property values ​​of segments of a component). Several of the above-mentioned possibilities for arranging the various devices 54, 54', 60, 70, 80 in a suitable topology of computing units and the control device 50 are shown as alternatives in Figure 1. Furthermore, further variants are also feasible, for example, to distribute the tasks for implementing the invention among different computing units or the like. The process control data PSD generated by the control data generation device 54, 54', in particular exposure control data BSD, can also be regarded as target values.which are then used in the control unit 51 for a control process. It is also pointed out again at this point that the present invention is not limited to such a laser melting device 1. It can be applied to any other method for the generative or additive production of a three-dimensional object by, in particular, layer-by-layer application and selective solidification of a building material. Accordingly, the irradiation device can not only comprise a laser, as described here, but any device could be used with which energy can be selectively applied to or into the building material as wave or particle radiation. For example, instead of a laser, another light source, an electron beam, etc., could be used. Even if only a single object 2 is shown in Figure 1, it is possible and generally also commonto produce several objects in parallel in the process chamber 3 or container 5. As mentioned above, additive manufacturing techniques involve a relationship between certain process variables, such as the scanning speed, laser power, and scanning strategies, in particular in a laser melting process, and the resulting microstructure within the component. In crystalline or semi-crystalline solids, such as metallic components, that have been additively manufactured using a laser melting process,For example, the crystallographic texture has a significant influence on component properties. Texture is defined as the totality of crystal orientations. It can be described, for example, by the "orientation density function" (ODF for short). DE 102022 117935 and DE 102022 117936 describe such microstructures such as texture and the influence of process variables during component production (manufacturing variables) in more detail, so reference is also made to these in this regard. However, even with polymeric or ceramic materials, a correlation can be observed between selected manufacturing variables and the resulting properties of the component.so that the invention can in principle also be used with other materials or any construction materials. An important factor for the development of a texture within a component are the cooling conditions during solidification. Critical influencing factors are the temperature gradient occurring and the feed rate of the solidification front. In laser-based additive manufacturing, in which a three-dimensional melt pool is always present locally, which gradually moves further in the scanning direction, both the scanning speed and the laser power density influence the texture, as they are also the main factors influencing the shape and size of the developing melt pool. For example, at very low scanning speeds, an approximately spherical melt pool forms,This results in heat dissipation inclined at approximately 45° to the build direction. If the scanning speed is increased while maintaining the same power, the length of the melt pool increases, while the width and depth (in the z-direction) decrease, which is why the heat dissipation is aligned, to a good approximation, along the build direction (i.e., in the z-direction) (see, for example, Figure 3 in DE 10 2022 117 935 with the associated description). The texture in a component depends not only on the exposure strategy within the respective layers, i.e., on the layer scan direction arrangement mentioned above. Initially, the layer scan direction arrangement only significantly (co-)determines the "intra-layer scan direction distribution" in a single layer. However, since a segment of the component, or the entire component, is composed of multiple layers,The relative position of the intra-layer scan direction distributions of the individual layers to one another also plays a significant role in the overall texture of the segment or in a component, since a different orientation of the layer scan direction arrangements or intra-layer scan direction distribution would also lead to a different segment scan direction distribution, which defines the frequency of occurrence of the respective scan directions in the segment or component as a whole. Figures 2 to 6 illustrate, by way of example, how different segment scan direction distributions SSV2, SSV3 result for two different segments SG2, SG3 of a very simple component 2'' created from multiple layers L, whereby a different layer scan direction arrangement HS2, HS3 (hatch strategy) was used in each of the segments SG2, SG3. The layer scan direction arrangements HS2, HS3 remain the same across all layers of the respective segment SG2,SG3 and are only rotated by a defined angle (which is different in the segments SG2, SG3) from layer to layer. The component 2'' is a simple square bar 2'' and the construction direction z runs in the longitudinal direction of the square bar 2'', i.e. the individual layers L are each oriented in the x / y plane. In the central area inside this square bar 2'' there is an elongated round bar-shaped segment SG2. The entire outer area of ​​the square bar 2'' except for this round bar-shaped segment SG2 in the interior (which forms a kind of core of the square bar 2'') is a second segment SG3. This is shown on the left side of Figure 2. On the right side of Figure 2, the hatch directions in four arbitrarily selected slices L1, L2, L3, L4 (also called layers) of this component 2'' are shown to demonstrate that in the respective segments SG1, SG2 different slice scanning direction arrangements HS2,HS3 can be used. In this case, the slice scanning direction arrangements HS2, HS3 each correspond to very simple hatch strategies HS2, HS3, which are used to scan or fill the entire surface of the respective segment SG2, SG3. Components are usually divided into different areas, with the core area, for example, being scanned along wide tracks, each of which has a specific hatch pattern perpendicular to the track direction, i.e., the hatch strategies are considerably more complex. Furthermore, in areas at the edges of the component, whether outer edges or cavities in the component, a contour mode is usually used, in which an energy beam is continuously moved along the contour, so that no hatch pattern is visible on the surface of the finished component. The simplified hatch strategies HS2,HS3 in Figure 2 are, however, better for clarifying the overall principle. As shown here using the lowest layer L1 (the layer drawn separately on the side), the inner segment SG2 has a hatch strategy HS2 in which two tracks are always moved parallel in one direction, followed by two adjacent tracks parallel in the opposite direction, etc. In contrast, the hatch strategy HS3 in the outer segment SG3 is selected such that one track always alternates in the forward direction and a second track in the reverse direction, etc. This means that the tracks here run in a meandering manner. In addition, as mentioned, for the two segments SG2, SG3, different strategies for reorientation or rotation around the z-axis (main assembly direction) of the hatch strategy HS2, HS3 are pursued from layer to layer. Thus, in the inner segment SG2, the orientation of the slice scanning direction arrangement HS2,HS3 is always rotated by 45°. In the outer segment SG3, however, a rotation of 90° always occurs. If a segment SG2, SG3 is then constructed from several such superimposed layers, a different segment scan direction distribution SSV2, SSV3 results for the segment SG2, SG3 as a whole, as shown in Figures 3 to 6. In these figures, a diagram of the segment scan direction distribution SSV3 for the outer segment SG3 is shown at the top, and the segment scan direction distribution SSV2 for the inner segment SG2 is shown at the bottom. In these and all other diagrams for the segment scan direction distributions SSV1, SSV2, SSV3, SSV4, the frequency of occurrence of the scan direction at the respective angle is plotted over an angle from 0 to 360°. The reference angle (i.e., where, for example, the angle 0° lies in the layer plane) can be chosen arbitrarily,since this is only a distribution. For example, the orientation of the hatch directions running in the x-direction could always be selected as the reference orientation RO for the segment. If the component – ​​as is usually the case – comprises several segments, the same reference orientation should be selected for all segments of the component, i.e., a reference orientation is defined for the component. Furthermore, the frequency of occurrence of the scan direction can be plotted in arbitrary units. Since the individual scan paths are relatively precisely maintained according to the defined slice scan direction arrangements HS2, HS3, relatively narrow Gaussian lines result in the segment scan direction distributions SSV2, SSV3 for the corresponding degrees of the orientation of the slice scan direction arrangement HS2,HS3. Between the upper segment scan direction distribution SSV3 for the outer segment SG3 and the lower segment scan direction distribution SSV2 for the inner segment SG2, the respective layer (in Figure 3 the lowest layer L1) is shown again in Figures 3 to 6. Arrows mark how the individual scan directions of the hatch strategy HS3 in the outer segment SG3 of the lowest layer L1 contribute to the peaks in the upper segment scan direction distribution SSV3 and how the individual scan directions of the hatch strategy HS2 in the inner segment SG2 of the lowest layer L1 contribute to the peaks in the lower segment scan direction distribution SSV2. For example, the first layer L1 for the outer segment SG2 leads to a peak at 90° and another peak at 270°. The hatch strategy HS2 for the inner segment SG2 in the first layer L1, on the other hand, leads to a peak at 0° and another at 180°. The further figures 4, 5 and 6 then show,how the overlying layers L2, L3, and L4 contribute to additional peaks in the segment scan direction distributions SSV2 and SSV3 for the outer segment (see the upper curve in each case) and the inner segment (see the lower curve in each case). It is clearly evident here that not only the hatch strategies HS2 and HS3 are responsible for the segment scan direction distribution SSV, but also, in particular, the strategy for orienting the respective hatch strategies from layer to layer. Thus, the segment scan direction distribution SSV3 for the outer segment SG3 only exhibits peaks at 0°, 90°, 180°, 270°, and 360°, whereas the segment scan direction distribution SSV2 for the inner segment SG2 encompasses considerably more angles. In principle, however, it would also be possible, and in reality, even preferable, to use considerably more complicated or smoother segment scan direction distributions in which the scan directions do not extend within such narrowly defined angles.as is the case in the simple embodiment presented previously. Figure 7 shows an example of a nearly uniformly distributed segment scan direction distribution SSV3, where the distribution function is approximated by the probabilities achieved in each individual degree direction. Since most machines can typically resolve to within 1°, the distribution function could be approximated by 360 individual steps. Such a uniform distribution can be achieved in the product structure if a segment consists of many layers and the same layer scan direction arrangement (hatch strategy) is used in each of the segment's layers, but the orientation of the layer scan direction arrangement is always rotated by an angle (e.g., the frequently used angle of 67°) from layer to layer.which is not a divisor of 360°. Then, virtually all angles occur in the segment scan direction distribution. Figure 8 also shows a segment scan direction distribution SSV4 with a nearly uniformly distributed angle. Such a segment scan direction distribution SSV4 can also be approximated from basis functions, e.g., radial basis functions, as shown. This has the advantage that the entire segment scan direction distribution is parameterizable, i.e., it can be described by a relatively limited number of free angle distribution parameters, which can reduce the computational effort required to find the optimal segment scan direction distribution. Changing the segment scan direction distribution is therefore always possible, for example, by selecting different slice scan direction arrangements (i.e., a correspondingly modified parameter set, since the slice scan direction arrangement—unlike the segment scan direction distribution—is specified as part of the parameter set).in particular, other hatch strategies, and / or by modifying the orientation or rotation of the layer scan direction arrangements in successive superimposed layers, for example, by rotating each by 45° instead of 90°, etc. This, as well as the choice of other process parameters during production, influences the texture and thus also other properties of a component. The invention can utilize all of these aforementioned relationships in that, based on a known parameter set that was or is to be used to construct a layer of a segment of a component, as well as a segment scan direction distribution that results across the entire segment composed of several layers,at least one macroproperty value of the relevant segment can be determined or approximated. Furthermore, based on the relationships between the process parameter values ​​and the segment scan direction distribution on the one hand, and the desired properties of the resulting manufactured product on the other, optimized process variable values, in particular an optimized segment scan direction distribution and an optimal parameter set in the respective segment (and thus also an optimal scan direction distribution for the component as a whole), can be determined for the individual segments of the manufactured product in such a way that the component ultimately fulfills certain (quality) requirements particularly well. A simplified diagram of a device suitable for generating optimized process variables is shown in Figure 9. The core of this device 60 is an optimization unit 65 (short "optimizer").for example, in the form of software. Among other things, the optimizer 65 contains, as a subunit, e.g., in the form of a software module, at least one AI-based optimization unit NN, specifically a neural network NN. However, multiple AI-based optimization units NN can also be used in the optimizer 65. Examples of AI-based optimization units in the form of (trained) neural networks and training methods will be explained in more detail later. This optimizer 65 can be transmitted, for example, by a user, via a requirement interface unit 61, requirement data AD of the desired manufacturing product. The requirement data AD includes at least geometric data GD of the manufacturing product. These geometric data GD can, for example, in the most general case, also include only permitted maximum dimensions for the component, or only maximum or minimum dimensions in certain directions.but on the other hand also very specific dimensions over certain exact lengths or even the CAD data that define the complete contours of the component. Furthermore, data about the hardware properties of the machine used (i.e., the production device 1) are fed to the optimizer 65 via an interface 62, in particular about the possible process parameters with which the production device 1 can be controlled. Via an interface 63, the optimizer 65 can access a properties database system DBS (hereinafter also referred to as "database system"), which will be explained in more detail later: In the database system DBS, certain parameter sets with which the production device 1 can be controlled during the build-up process of a layer (in particular the scanning speeds, the laser power density, etc.) are stored depending on various information about the scanning directions,For example, the layer scan direction arrangements within a layer and / or the segment scan direction distribution within a segment consisting of several layers, each of which is assigned property values ​​of the respective layer or segment. This can include, among other things, the above-mentioned basic property values ​​BEW of the individual layers, such as the texture as a mathematical description using ODF in the respective layer or its elasticity tensor, but also macro property values ​​MWA, which, for example, describe the texture or ODF from a macroscopic perspective in the entire segment, and / or macro property values ​​MWA derived therefrom, such as stiffness or strength, to name just a few examples. From all of this data, the optimizer 65 can then, for example, in the procedure explained below with reference to Figure 12,Determine optimized process variable values ​​PGO and make them available for further purposes via an interface 64. The entire device 60, i.e. not only the optimizer 65, but also all interfaces 61, 62, 63, 64, can be implemented in the form of software on a suitable computer unit. The database system DBS can also be part of the device 60 and likewise be implemented on the respective computer device. In principle, the interfaces (i.e., the request interface 61, the further interfaces 62, 63, and the process variable value interface unit 64) can also be designed as a common interface unit to accept data, process it in the optimizer 65, and output it again. The provision of the optimized process variable values ​​PGO can, for example, be carried out by storing it in a suitable memory or by sending it to another unit,which then generates the optimized control data for the production device based thereon, for example in one of the control data generation devices 54, 54', as shown schematically in Figure 1. For the optimization process, the optimizer 65 also receives information about a desired target function ZF, whereby this target function ZF can also result at least in part from the requirement data and / or can be adopted from another program and / or can be specified or configured by means of a user interface. Such a target function ZF can have a plurality of subfunctions TF1, ..., TFi, ..., TFn (also called "subfunctions" or "subfunctional"), each of which servesdifferent requirements must be taken into account. This is illustrated graphically in Figure 10. Furthermore, with regard to the establishment and use of the objective function ZF and its possible sub-functions, reference is made in particular to DE 102022117935. The functionalities therein can also be used within the scope of the present invention and are only supplemented by the invention. Preferably, a sub-function TF1 can, for example, generally comprise the maximization of the build rate, and preferably there is also a sub-function TFn which aims at minimizing the changes in the parameter set within the overall structure of the component. This means that the component should contain as few different segments as possible, since the individual segments are defined in such a way thatthat the same set of parameters is used within the segment to build the layers of the respective segment. This can be achieved, for example, by a subfunction to minimize the number of segment boundaries. In addition, there are a number of other optional subfunctions TFi that can take into account a wide variety of criteria, such as minimizing material usage, optimizing a safety indicator factor (see equation (8)), minimizing the entropy of the segment scan direction distribution, i.e., reducing the dead load of the component or mass as much as possible, depowderability, etc. of the component, and / or other arbitrary criteria. In Figure 10, the objective function ZF is shown as a chain with a (preferably mandatory) first link, which represents the subfunction TF1 for maximizing the build rate.and with a final chain link (preferably mandatory in the preferred optimization method with movable segment boundaries explained later), which represents the subfunction TFn for minimizing the number of segments and thus the change of the parameter set (provided – as preferred – exactly one optimal parameter set is selected for each segment). In between, some optional subfunctions TFi are shown. However, this only serves to illustrate the various possibilities. In fact, the subfunctions TF1, ..., TFi, ..., TFn can be concatenated in any suitable order and manner in an objective function. In order to prioritize the individual criteria, the various subfunctions TF1, ..., TFi, ...,TFn can also be considered with a weighting factor in the objective function ZF. The choice of optional subfunctions depends on the user and their optimization problem and can be expanded as required. Through sequential coupling with the boundary value problems or mechanical loads or property requirements, the shape of the component is optimized in a user-selected area for specified applications. An objective function ^ (which can also be referred to as a "quality functional" or "functional" for short) that can be used within the optimization process and with which the optimal parameter sets and optimized slice scan direction arrangements of the segments of a previously defined area ^ can be determined simultaneously, can be mathematically defined, for example, as follows: ^ =, ∫ ^ ^^^ ^^ (1) ^ ^^^are the segment objective functions of the individual segments in the area ^. The integration corresponds to a summation of the segment objective functions in the area ^. These segment objective functions can be defined as follows: ^ = ∑ ^ ^ ^^ ^ ^ ^ ^ ^ (2) The segment objective functions ^ ^^^ can be described without loss of generality as a weighted sum of partial functions ^^ ^ (the partial functions), each of which is weighted by a weighting factor ^ ^ multiplied. i is a running index for numbering the subfunctions and the U in ^ ^ is only a placeholder for a concrete name of the subfunction, for example U = ^^^^^ for the subfunction (the subfunctional) ^ ^^^^^ to minimize construction time or maximize construction rate. Basically, all sub-functionalities ^ ^ (and thus also the segment objective functions ^ ^^^and ultimately the objective function ^) in some way from a chosen set of parameters ^ ^ (^) dependent ^ represents the spatial coordinates in the area ^ in which optimization is taking place (i.e. in the component and in the powder segments). This means that each location in the area ^ is assigned a specific set of parameters ^ ^ (^), which corresponds to the currently applicable parameter set for the segment in which the point is located for constructing the layers of the respective segment. During optimization, a more suitable parameter set is selected from a plurality of candidate parameter sets for each point or segment (in addition to the search for the optimal segment scan direction distribution), as already mentioned above. ^ is here – and in the following – an index variable that represents the various parameter sets ^ ^ (^) of the candidate parameter sets. For example, the subfunction ^ ^^^^^To minimize construction time, for example, it can be defined as follows: This subfunction ^ ^^^^^ the objective function can be used to estimate the contribution of each parameter set ^ ^ (^) on the construction speed. The subfunctional ^ ^^^^^ should ensure that under all possible configurations of parameter sets ^ ^ (^) depending on the location ^ precisely those with the highest volume build-up rate are taken into account. ^ ^ denotes the volume build-up rate, which at the respective location ^ is determined by the process parameter set ^ ^ (^) can be reached. Other definitions of the subfunction ^ ^^^^^ to minimize construction time are also possible, as will be shown later. In addition, many sub-functionalities ^ ^ still depends on the segment scan direction distribution ^ (^): ^ ^ (^ ^ ( ^ ), ^(^)) (5) The segment scan direction distribution ^ (^) is dependent on the location ^ insofar as it depends on the segment in which the current location is located. A concrete example of a subfunction dependent on the segment scan direction distribution ^ (^) is a subfunction that serves to adapt the location-dependent stiffness to the stiffness requirements as well as possible. An example of this can be found in DE 10 2022117935. As shown in equation (2), a user can use a higher weighting factor ^ ^emphasize certain requirements within its multi-physics requirement profile and thus ensure that this aspect is given greater consideration when finding a Pareto optimum. The weighting factors can, in principle, be any number greater than 0. A sensible option would be to always choose numbers between 0 and 1, whereby the sum of the weighting factors can also be normalized to 1. If, for example, three subfunctions are to be considered in the objective function—namely, one for the safety factor, one for the construction rate, and one for the number of segment boundaries—with the safety factor being of greater importance, the subfunction for the safety factor could be weighted with 0.5 and the other two subfunctions with 0.25 each. The objective function to be ultimately minimized within the framework of the optimization procedure can therefore be defined by combining equations (1) and (2) as follows: The functional ^ here has integral form and always assumes a scalar value for the entire domain ^. A higher value of the quality functional ^ therefore describes a less desirable state with respect to the specified requirement profile, and a lower value a more desirable one. By minimizing this function (6), the optimum can be found, ie, the optimal parameter set ^ ^^^ ^ (^) is determined from the available (candidate) parameter sets ^ ^(^) for the respective optimal segment scan direction distribution ^ (^). Various optimization methods can be used for this, whereby two basic cases can be distinguished: a) Optimization with fixed segment boundaries. b) Optimization with movable segment boundaries, i.e. the shape of the segments (and thus also of the component) can be varied. In both cases, the optimization can preferably be carried out in an iterative, sequential process, whereby all process steps can be run through multiple times in iteration loops (particularly nested ones) in order to take into account the influence of the optimizations in the respective steps on the other steps.In principle, it is also possible to perform an optimization with fixed segment boundaries in individual steps and then run these steps iteratively multiple times. Between runs, segment boundaries can also be changed in other steps of the loop. This means that with each run through this optimization step with fixed segment boundaries, an optimization with possibly changed segment boundaries is performed. A more detailed example of this specific preferred approach will be explained later using Figure 12.First, however, an overview of generally usable optimization methods with fixed segment boundaries or with movable segment boundaries is given below: a) Optimization with fixed segment boundaries: For this purpose, a variety of classical, in particular numerical, methods for linear and non-linear local or global optimization with and without constraints can be used. Depending on the form of the objective function ^, methods that are derivative-free (e.g. interval bisection methods, downhill simplex methods, etc.), that require the first derivative (such as secant methods, gradient methods and conjugate gradient methods, quasi-Newton methods, etc.) or that require the second derivative (such as Newton methods or Newton-Raphson methods) are particularly suitable. Depending on the method chosen, the subfunctional must then be formulated in such a way that it is approximate with respect to the variables to be optimized (i.e. the process parameter sets ^. ^(^) and / or the segment scan direction distributions ^ (^)) are continuous, once continuously differentiable, or even twice differentiable. Preferably, methods with high convergence are used, i.e., those that require the highest possible derivative, as such methods are faster. Examples of the technical implementation of suitable optimization methods can be found in fundamental works such as C. Richter, Optimization in C++: Fundamentals and Algorithms, 2016, Wiley-VCH, Berlin, where in the proposed work the quality functional is denoted by ^(^) instead of ^ and the quantities to be optimized are denoted by ^. Particularly for optimization steps with fixed segment boundaries, the use of at least one AI-based optimization unit (as will be shown later) is also recommended, although AI-based optimization units can in principle also be used for optimization with movable segment boundaries.The previously mentioned conventional methods can then be used, for example, to train the AI-based optimization units or neural networks. b) Optimization with variable segment boundaries: There are also various methods for implementing optimization with movable segment boundaries. As mentioned, it is possible to simultaneously optimize the shape, i.e., the geometry, of the segments (and thus of the component) and the segment scan direction distributions. The parameter sets applicable at the individual locations can inevitably be varied by shifting the segment boundaries, since the location in question may be assigned to a different segment, in which a different parameter set applies, due to the boundary shift. Without loss of generality, in principle, all methods used for topology optimization can be used to minimize the objective function ^.Zu diesen Verfahren zählen u.a.: - diskrete Topologie Optimierung, Michell A. G. M. The limits of economy of material in frame structures. Philosophical Magazine 8(47):589–597, 1904 - Shape derivatives Topologie Optimierung, P. Gangl, Sensitivity-based topology and shape optimization with application to electrical machines, Universität Linz, Dissertation 2016 - Level set, S. Kambampati, C. Jauregui, K. Museth & H. A. Kim, Large-scale level set topology optimization for elasticity and heat conduction, Structural and Multidisciplinary Optimization volume 61:9–38, 2020 - Evolutionary structural optimization, P. Tanskane, The evolutionary structural optimization method: theoretical aspects, Computer Methods in Applied Mechanics and Engineering, 191(47–48): 5485-5498, 2002 - Phase field, J. Kato, S. Ogawa, T. Ichibangase & T.Takaki, Multi-phase field topology optimization of polycrystalline microstructure for maximizing heat conductivity, Structural and Multidisciplinary Optimization volume 57: 1937–1954, 2018 For this purpose, a so-called “interface dynamics” must be derived from the objective function ^, whereby a numerically solvable differential equation is set up in which the objective function ^ is derived according to the parameters to be optimized. These procedures are generally known to the person skilled in the art. In connection with the invention, a so-called “multi-phase field method” can be used with particular preference, as explained in DE 102022117935 (with the proofs therein for the basic procedure). However, the invention is not intended to be necessarily limited to this preferred method.The multi-phase-field method (as a phase-field method) is actually a method for the numerical simulation of processes in which two or more phases and the interfaces between them, the phase boundaries, are to be described. The phase-field method can be used to determine how structures and the shape of the interfaces change over time. Within the scope of the invention (as explained in DE 10 2022 117 935), this principle can be advantageously used to describe the displacement of the interfaces between adjacent segments, each of which has different sets of process parameters. ^ (^) and / or segment scan direction distributions ^ (^) should apply. The different process parameter sets ^ ^(^) and / or segment scan direction distributions ^ (^) correspond to the different "phases" in the present case. Otherwise, the procedure can be largely adopted. In order to perform an optimization with moving segment boundaries using such a multi-phase field method, non-linear, partial differential equations are usually derived from the objective function ^ (as described in more detail in DE 102022117935), which each describe the movement of the segment boundary surface positions (i.e., the positions of the individual points or locations ^ of the segment boundaries). Since at a boundary between two adjacent segments, on the one hand, a parameter set ^ ^ ( ^ ) to another parameter set ^ ^ ( ^ )is changed ( ^ is simply another index variable not equal to ^), but on the other hand no sharp transitions (sharp interfaces) or jumps are allowed when using the required differential equations, the parameter sets ^ ^ (^) at the location ^ each through their “shares” ^ ^ ^ (^). The value of the proportion can be between 0 and 1, where ^^ ^ (^) = 1 means that the parameter set ^ ^ (^) to a location ^ and a portion of ^ ^ ( ^ ) = 0, that it is not present. Thus, locations ^ in a boundary area (hereinafter also referred to as "boundary area", the width of which is user-definable) between two segments can simply be given a proportion ^ ^ ^ (^) of a first parameter set ^ ^ (^), which applies in the first segment, and a share ^^^ (^) of a second parameter set ^ ^ (^), which applies in the neighboring second segment. If more than two segments meet in an interface region, contributions from more than two parameter sets can be present at one location ^. In any case, the sum of the contributions of all parameter sets present at each location must equal 1. In order to have contributions ^ ^ ^ (^) of parameter sets ^ ^ (^), for all locations ^ in a middle area of ​​a segment, i.e. outside a border area to another segment, the proportion ^ ^ ^ (^) of the parameter set applicable in the segment ^ ^ (^) is set to 1. The objective function ^ or the individual sub-functions ^ ^ must then be adjusted accordingly for the phase field method so that it contains the proportions ^ ^ ^ (^) of the parameter sets ^^ (^) must be taken into account mathematically. This is done individually for the various sub-functionalities and is described for various sub-functionalities in DE 102022 117935, so that reference can be made to this document. This document is also referred to for the definitions and explanations of the above-mentioned differential equations. Within the framework of the multi-phase field method, as explained in more detail in DE 102022117935, the segment scan direction distributions ^(^) can also be optimized by performing an optimization according to the free angle distribution parameters ^ ^ ^ (^), with which the segment scan direction distributions ^(^) can be defined. For example, the free angle distribution parameters ^ ^ ^(^) in a non-parametric description of the segment scan direction distribution ^(^) are the contributions of the individual discrete scan direction angles to the respective segment scan direction distribution ^(^). For example, the segment scan direction distribution ^(^) can be broken down into 360 discrete scan direction angles, each with a degree. A free angle distribution parameter ^ ^ ^ (^) is then the proportion of exactly the ^-th scan direction angle in the segment scan direction distribution ^(^). The value of the segment scan direction angle proportions ^ ^ ^ (^) lies between 0 and 1, whereby a value between 0 and 1 does not indicate a segment boundary, but only describes a part of the scan direction angle in the segment scan direction distributions ^(^). It is true that at each location ^ the sum of all segment scan direction angle components ^ ^ ^ (^) must be equal to 1. If the segment scan direction distribution ^ ( ^ )can be defined parametrically, e.g. as a Gaussian distribution, the free angular distribution parameters ^ ^ ^(^) can alternatively be the individual parameters of the segment scan direction distribution ^(^) according to which the optimization is to be carried out, where ^ and ^ stand for the individual parameters (e.g. ^ for the mean value and ^ for the standard deviation). In practice, an existing program or parts of a program for the numerical solution of such tasks can simply be used for optimization using this phase field method. For example, such programs are available in the software packages OpenPhase, OpenFoam or deal.II etc. Since in an optimization with variable segment boundaries the segment boundaries are defined by diffuse interface regions, after the optimization has been completed it is determined in which voxels in the interface region which process parameter set and which segment scan direction distribution is to be applied. This can also depend, among other things, on the specific purpose for which the data obtained in the optimization process is to be used.If they are to be used directly to control the production device, it can also be used in the interface areas that the parameter set components ^ for the voxels there. ^ ^ (^) different parameter sets ^ ^(^) are known, which are each assigned to the various neighboring segments. In this case, for example, the data for the process parameter sets including their components can be transferred voxel by voxel to the control device of the production device, and during the production process the process parameter sets are applied multiple times in an overlap area between two segments according to their components. In a laser powder bed fusion process, for example, the laser can expose this area multiple times in the overlap area, each time with different process parameter sets. In order to reconstruct sharp segment boundaries again in order to represent the component as a CAD model, this can be done using a suitable method, for example in the form of isosurfaces.Isosurfaces are surfaces that connect adjacent voxels in space with the same features or values ​​of a certain size, such as parameter set components or free angular distribution parameters. As already mentioned, a segment is preferably also defined by the fact that the segment contains the same process parameter set (in addition to the same segment scan direction distribution). ^ applies (and in this sense it could also be called a "process parameter area"), the isosurfaces determined in this way are equivalent to the segment boundaries. In the voxels in which different parameter sets ^ ^ (^) with their respective parameter set parts ^^ ^(^) are present, a decision must be made as to which parameter set should apply there. Preferably, this can be the parameter set with the largest proportion, for example. One method for generating isosurfaces is, for example, the marching cubes method, as described in CD Hansen, CR Johnson Visualization Handbook, Elsevier Science, 2005, among others. Other methods from this textbook could also be used. A corresponding assignment of the voxels in the interface region to a segment scan direction distribution is not absolutely necessary, since by simply assigning them to a segment, you can not only define the process parameter set, but also assign the associated slice scan direction arrangement to the respective segment in which the process parameter set is to be applied. This then automatically results in the segment scan direction distribution of the segment, which should be uniform for the entire segment.In the following, some further sub-functions (= sub-functionals) are given as examples in order to set up the objective function according to equations (1) and (2): a) Sub-functional for minimizing segment boundaries. b) Sub-functional for ensuring the depowderability of the component (only with movable segment boundaries). c) Sub-functional for ensuring correct heat treatment. e) Sub-functional for reducing material usage. f) Sub-functional for optimally ensuring a safety factor. g) Sub-functional for maximizing the variation of the scan direction angles. h) Sub-functional for avoiding a divergence of segment scan direction distributions ^(^) within a segment. Since the above-mentioned sub-functionals are explained in more detail in DE 102022117935, for the sake of simplicity, reference can be made here again to the explanations of these sub-functions there.In principle, the subfunctions can also be used in this way within the scope of the present invention. However, the following also refers to the preferred example of optimally ensuring a safety factor for improvements to the optimization strategies within the scope of the present invention. Therefore, further explanations are given for the subfunctional for optimally ensuring the safety factor (which, however, largely correspond to the explanations in DE 102022 117935). In practice, structures are designed taking into account a "safety factor" with regard to their loading. A safety factor is expressed as a numerical value and indicates the factor by which the failure limit of a material condition or of an entire component is designed to be higher than it would have to be based on theoretical determination.The safety factor is generally determined from the condition of the component's material and the resulting theoretical state variables, e.g. strength, on the one hand, and the states of the field variables acting in the component, e.g. mechanical stresses, on the other. In order to represent this situation in a further development of the method according to the invention, a safety indicator factor is preferably introduced which describes the difference between the specified safety factor and the current state of the component or its segments from the simulation. The difference is preferably represented by a number. This representation can be arbitrary, but should preferably represent at least three states: i) the desired safety factor is not met, ii) the desired safety factor is exactly met, iii) the desired safety factor is exceeded.For this purpose, a definition can preferably be made such that the value 0 of the safety indicator factor expresses that the desired safety factor ^ is exactly met, that a value less than 0 expresses that this safety factor is not met, and that a value greater than 0 expresses that this safety factor is exceeded. The value of the safety factor ^ is generally always greater than or equal to 1, otherwise the component would most likely fail under the planned load. It generally depends on the area of ​​application and, where applicable, its standards. Typical values ​​for the safety factor ^ are, for example, 1.5 or 2 in the automotive industry and 1.5 to 6 in the aviation industry, depending on the safety relevance of the component. One safety indicator factor ^^. ^ ^^ ^ ( ^ ) ^ for a parameter set ^ ^ (^) at location ^ can be defined as follows: This is a material-specific flow function that can be scaled = 1 applies if the mechanical stress the yield point of the material is reached, ie the component begins to deform plastically. If the value of ^ ^^ ^^ , ^ ^ (^)^ less than 1, the component is deformed purely elastically. The safety indicator factor ^^ ^ ^^ ^ (^)^ is therefore only greater than or equal to 0 in the “allowed” range if a parameter set ^ ^ (^) is selected so that the resulting value of the material-specific flow function ^ ^ ( ^ )) is below the inverse of the safety factor ^. There are various ways to define suitable material-specific flow functions that are familiar to the person skilled in the art. Some variants are presented, for example, in J. Betten, Kontinuumsmechanik, 1993, Springer-Verlag. In principle, a suitable material-specific flow function or its parameters can also be defined, particularly in the isotropic case, with the help of experiments on suitable samples, e.g., via tensile tests or the like. A suitable partial functional ^ ^ using this “safety indicator factor” ^^ ^ ^^ ^ (^)^ according to equation (7) can be designed so that for an optimal parameter set ^ ^ (^) at the location ^ particularly preferred the value for the safety indicator factor ^^ ^ ^^ ^ ( ^ )^ equal to 0 is the goal. It is particularly preferred that an exceedance of the safety factor is penalized more severely than a fall below it, ie that the safety factor ^ is certainly met, but the effort required to achieve this is nevertheless minimized. An execution of such a subfunction ^ ^ can look like this for an optimization with fixed segment boundaries: The partial function described here was chosen in the form of the Leonard-Jones (exp, 6) potential. This function is intended to exhibit a minimum when the safety indicator factor is equal to or close to 0. For a value less than zero, the subfunction should quickly assume a large value. Using the value of the variable ^ in equation (8), the value for the safety indicator factor can be determined. ^^^ ^ ^^ ( ^ )^ on the abscissa, where the partial function ^ ^ has its minimum value. The subfunction ^ ^in equation (8) is constructed in such a way that for the value ^ = ^ this minimum value of the subfunction ^ ^ within the limits of calculation accuracy at ^^ ^ ^^ ^ ( ^ ) ^ = 0.025. A realization of the subfunction ^^ using equation (8) and ^ = ^ is often the preferred variant, since in practice a value for the safety indicator factor ^^ ^ ^^ ^ ( ^ )^ of 0 can almost never be achieved anyway, but in this way it can be ensured that the value is very close to the value 0 from the safe side, i.e. greater than 0. In a similar way, this can also be achieved with other potential functions instead of equation (8). For a requirement which, for example, allows for a fall below the safety factor in a certain range, but demands, for example, the smallest possible component volume, it can still be sensible to achieve a safety indicator factor of 0 as closely as possible, even if this is slightly undershot. If, for example, the partial function ^ ^According to equation (8), if a safety factor of 2 were desired for a value of ^ = ^, this could not be achieved, but the value for the safety factor would be at least 2.1. However, this fact can be taken into account by a value of ^ < ^, which, on the other hand, leads to the safety factor being slightly undercut in the optimization. Likewise, for such cases, a correction of the safety factor could also be made beforehand, e.g., according to ^ ^ ^^^^ = ^^^.^^^ ^ (9), where simply the modified safety factor ^ ^^^^ instead of the safety factor ^ in equation (7). In the context of a numerical implementation of the optimization, it may happen that a negative value for the subfunction ^ ^ occurs because the term ^^ ^ ^^ ^ (^)^ + ^ in equation (8) becomes negative. In this case, for example, when implementing the optimization with equation (8), the value of the subfunction ^^ easy to 10 9 so that the optimization procedure is forced to choose the values ​​differently and thus "correct" the invalid state. An example of a suitable subfunction ^ ^ , specifically the function according to equation (8), is shown graphically in Figure 11. Here the value of the subfunction ^ ^ (in arbitrary units; au = arbitrary units) above the safety indicator factor ^^ ^ (in arbitrary units). It is clearly seen that the value of the subfunction starting at the minimum of the subfunction ^ ^ with increasing safety indicator factor ^^ ^ (to the right), ie, when over-dimensioning, increases slowly. However, at the minimum of the subfunction ^ ^ with falling safety indicator factor ^^ ^ (to the left) the values ​​of the subfunction ^ ^strong. As already mentioned, to construct the objective function, at least a minimal configuration is preferably required, which (as explained in DE 102022117935) is particularly preferably composed of a sub-functional for minimizing the construction time or maximizing the construction speed and - if an optimization is carried out with movable segment boundaries - a sub-functional for minimizing segment boundaries (process parameter boundaries), i.e. for minimizing the segments in the component. In addition, as already mentioned, the objective function can contain a number of further optional sub-functionals, such as the other sub-functionals mentioned above. The above examples each show the simplest form of the sub-functional, which can be modified to include further constraints, provided that the condition in question is not to be added to the optimization problem in the form of a separate sub-functional.Whether an optimization criterion is linked to another sub-functional, in particular one of the mandatory sub-functionals, or whether separate sub-functionals are defined depends on the complexity of the optimization problem. An example of the coupling of an optimization criterion to a mandatory sub-functional is illustrated below by the coupling of the safety factor to the sub-functional for minimizing the construction time or maximizing the volume build-up rate. This sub-functional for minimizing the construction time was already presented above using equation (4) (without shifting the segment boundaries). In both cases, the sub-functional can now be extended by a safety factor to create a sub-functional ^. ^^^^^^^ to be defined with baurate-safety factor coupling: ^ ^^^^^^^ = −^ ^ (^ ^ ( ^ ) )^^^^ ( ^^ ^ ) (4') ^^ ^denotes the safety factor indicator, as it can be defined above using equation (7). ^^^^ is the signum function, which only considers the sign and assigns a positive sign to the value 0. Therefore, if a parameter set ( ^ ) ^ would result in the safety factor being undercut (i.e. the safety factor indicator ^^ ^ would be negative), the volume build-up rate would no longer be subtracted from the objective function, but added, because the sign in the sub-functional ^ ^^^^^^^changes. Thus, falling below the safety factor is inevitably penalized. If a sub-functional is used in which the safety factor is already integrated, it is not necessary to use a separate sub-functional to maintain the safety factor. An objective function ZF defined in the manner described above can now be used in an optimization process (for example, by the optimizer 65 according to Figure 9). An example of a possible optimization process is explained below using Figure 12. This is an iterative process. In some of the process steps, the objective function can be used repeatedly, whereby, if necessary, (only) certain sub-functions of the objective function are also used in different steps in order to initially handle or optimize the optimization goals underlying the sub-functions separately from one another. E.g.Certain subfunctions could be reduced in their effect or even deactivated in a step by setting certain parameters in this subfunction accordingly, or certain optimization parameters are initially considered constant in certain steps. In the example in Figure 12, an objective function is used as an example which contains the subfunctions for minimizing the construction time, minimizing the segment interfaces, considering a safety factor, for possible depowdering of the component, enabling heat treatment, maximizing the variation of the scan angles and avoiding divergence of the segment scan direction distributions. However, it is expressly pointed out again at this point that the objective function can also be structured in a different way, as explained above.The optimal objective function depends on the range of requirements, the available computing power and the available time. In step S0, an area G (the computing area or the design space) is first defined which contains the component to be produced. If the external dimensions of the component to be manufactured are not to change, i.e. the shape is to remain unchanged, the external contour of the component itself could, for example, form the area. Otherwise, it would also be possible to draw any box around the component in any way, i.e. the unconsolidated areas around the component or on certain sides of the component are also included in the area. This area is then subsequently (in the further steps, see below) divided into several segments, whereby some of the segments may belong to the component, but there may also be segments (e.g.Powder segments) can exist that lie outside the component, provided that the area, as mentioned, is larger than the component. In step S1, starting values ​​are then set for the subsequent optimization, which runs iteratively here, namely start segments SG', as well as start parameter sets PS' and start segment scan direction distributions SSV' associated with the start segments SG'. Figures 13, 14 and 15 illustrate how an area G can be defined for a specific component 2', here a buffer stop 2', and how segments SG0, SG1, e.g. as start segments, can be specified in the area G. In Figure 13, the component is shown as a triangular mesh to visualize that the data is virtually available to carry out a finite element simulation for the buffer stop 2' for a load case in which external forces, which are shown as arrows in Figure 13, act on the buffer stop 2'.Based on the simulation, a 3D load map can be created, which is visually represented in grayscale (or normally in color) for the buffer stop 2' in Figure 14. This representation shows that, for example, only a small part of the volume, namely less than 3% by volume of the entire buffer stop 2', is exposed to a load level above 200 MPa, with these more highly loaded areas being located primarily in the area of ​​the cross struts of the buffer stop 2'. With knowledge of the precise load information (which can also be requirement data, in particular quality requirement data), such as information about the more and less heavily loaded areas, the component can then be advantageously divided virtually into individual segments.Here, the buffer stop 2' can be divided into individual segments based on the load information such that the particularly loaded areas in the cross struts are viewed as separate segments SG1, and the remaining area of ​​the buffer stop 2' can form another segment. This is illustrated in Figure 15. These segments can then, for example, initially be used as starting segments SG' in the optimization process. Figure 15 also shows how the entire component 2' can, for example, be enclosed by a larger area G, and the entire outer area around the component 2' forms another segment SG0, which is a "powder segment" or "empty segment" in which the powder is not solidified during the build-up process. For such powder segments SG0, the starting parameter set in the optimization process can simply be set so that the laser power here is 0.This start parameter set then no longer needs to be changed for the powder segment SG0. For all other start segments SG', a suitable start parameter set PS' (for building up the layers of the relevant start segment SG') and a start segment scan direction distribution SSV' can then be selected in step S1, for example from a data storage DS in which, among other things, various candidate parameter sets KPS can be stored, which are available for construction with the production device 1 to be used. As a rule, this involves a relatively limited number of candidate parameter sets KPS, although the number is of course only limited by the available storage space and the computing time available for testing various candidate parameter sets KPS with regard to their influence on the property values ​​of the manufactured component.Since in many cases high efficiency in component production is also an important criterion, it is advisable to select the start parameter set PS' and the start segment scan direction distribution SSV' with which the highest build rate can be achieved. In principle, however, a different selection criterion can also be used. In particular, a start parameter set could already be selected using a suitable AI-based optimization unit NN. For example, a suitably trained neural network NN (if necessary after appropriate selection from a database) can be loaded from the data storage DS, as will be described later using step S3 or, in more detail, sub-steps S33 and S34. It should be noted at this point that it would also be possible to virtually divide the area G orof the component 2' into the start segments SG' according to how the highest build rate can be achieved, and not to use a load simulation at this point, as shown in Figures 13 to 15. This applies in particular if the component is not to be exposed to any high loads at all or if the load is more of a background factor. In the subsequent step S2, a requirements simulation is then carried out for the (still virtual) component to be manufactured, assuming that the start configuration defined in step S1, i.e. the start segments SG', the start parameter sets PS' and start segment scan direction distribution SSV', were used during production. As mentioned, for a known configuration orCombinations of segments SG and associated parameter sets PS and segment scan direction distributions SSV allow macroproperty values ​​of the individual segments, such as the texture (particularly in the form of the orientation density function ODF) and / or other macroproperty values, such as an elasticity sensor, a yield point distribution, a hardening coefficient, a thermal conductivity, a fracture strength, etc. to be determined. Within the scope of such a requirements simulation, a load simulation can then be carried out, for example, using the macroproperty values ​​(of the segments or the component formed from them), similar to that previously visualized in Figure 14 for the buffer stop 2', or a vibration simulation or the like. Such simulations are possible using conventional numerical simulation methods such as finite element methods or finite volume methods.The result of this requirements simulation is then a state description with various state values ​​of the current system or component with the individual segments, in particular the load these segments can withstand and the frequency of the entire system (component), in each case for the current configuration in which the calculation is carried out in step S2. As will be explained later, this step S2 is called several times as part of the iterative process to check the current configuration. The first time it is called, i.e. at the beginning of the optimization process, these state values ​​or the state description apply to the start configuration from step S1. In the subsequent step S3, a comparison of the state description or the state values ​​etc. can then be made with external specifications, in particular the requirements data for the component.These external specifications could, for example, also include load recordings that were made available in advance for the component as (quality) requirement data, such as the load recordings from Figure 14 for the example with the buffer stop 2'. If, in exceptional cases, all required variables are optimally fulfilled, it would in principle be possible to build the component using the start configuration, particularly if this start configuration was already selected so that the highest possible build rate can be achieved. The start configuration would then be the optimal configuration and the optimized process variable values ​​would already have been found. This is, however, very unlikely. Normally, if not all requirements are met, the process variable values, namely the segments orTheir precise segment boundaries, as well as the parameter sets and the segment scan direction distributions for the individual segments, were further optimized. The goal is to assign each segment the process parameters, ie, the complete process parameter set. ^and to assign the segment scan direction distribution that offers the greatest optimization potential if, for example, the geometry is to be further optimized, i.e., for example, the mass is to be further reduced, and / or the build rate is to be maximized. For this purpose, in step S3, new current parameter sets can be selected from the candidate parameter sets KPS for the current segments SG', if necessary, and new current segment scan direction distributions can also be determined. As mentioned, this selection can particularly preferably be made taking into account so-called "parameter set suitability values" PSS (shortly referred to as PS score PSS). The candidate parameter sets KPS and / or segment scan direction distributions (or pairs of candidate parameter sets KPS and / or segment scan direction distributions) can be assigned with regard to specific requirements, i.e., for each optimization criterion, for example, with regard to strength, stiffness, build rate, etc., different “requirement-specific PS scores” can be assigned and these parameter set suitability values ​​PSS always depend on the process parameter set ^. ^ The parameter set suitability values ​​for the construction rate and for compliance with the safety factor are shown here as examples. The parameter set suitability value PSS for the construction rate can be defined as follows. It is only important that for the design proposed here, the value of the parameter set suitability value is a maximum of 1 (= maximum construction rate) and that for all suitable variants of the parameter set suitability values, the value is greater than 0. Here, the construction rate of a process parameter set ^ ^ (^ ^ ) normalized by the maximum build rate of all process parameters available for optimization Other parameter set suitability values ​​PSS can be derived not only from the process parameter set ^ ^, but also on the segment scan direction distribution ^ and also on a current state of the system in the respective segment, such as the homogenized mechanical stress explained above in the segment. An example of this is the parameter set suitability value for ensuring a safety factor. The parameter set suitability value for ensuring a safety factor can be as follows: ^^^^^^^^^^^^^(^ , ^, ^^ , … ) = ^ − ^^^(−^ ^ ^ ^ ^^ ^ ^ (^ ^ , ^, ^ ^^ , … ) ) + ^ (12) … ) refers to the safety indicator factor already described above, except that here the dependence on the segment scan direction distribution ^ and the homogenized mechanical stress is displayed in the segment with. ^ denotes the smallest number that can be displayed by the computer. The safety indicator factor is, as already mentioned, 0 if the parameter exactly fulfills the current safety condition, a negative number if the target safety factor is not reached, and a positive number if the target safety factor is exceeded. The exponential function in equation (12) limits the maximum value according to the requirement to 1. The requirement-specific PS scores PSS can be stored in the data memory DS or can be recalculated for the current configuration. This depends on which concrete requirement the requirement-specific PS score refers to. For requirements that only depend on the selected parameter set, such as the build rate, these requirement-specific PS scores can be stored together with the parameter set.For requirements that also depend on external field variables, in particular mechanical forces, the PS scores are preferably recalculated each time the loop is run through in step S3. An easily understandable example of this would be the mechanical stress in a component under a specified load. These stresses depend, for example, on the geometry of the component and thus also on the current configuration of the segments. If the boundaries of the segments are changed during the optimization process, the stresses in the component inevitably change as well. Consequently, it is better to adapt the PS scores with regard to such loads to the current configuration. To do this, first, a new parameter set and a new segment scan direction distribution are searched for for the various segments in step S3.A preferred possible procedure for the method sequence carried out for this purpose in step S3 is explained in more detail below using the flow chart in Figure 16. In the requirement simulations (which can also be referred to as "state simulations") in step 2, the states for the individual (volume) elements (e.g., voxels) were determined using the numerical method, for example if a finite volume or finite element method is used. A segment usually comprises a certain number of such elements. In the first sub-step S31 of the optimization process in step S3, a homogenized state of the field variables of the individual elements of the segment occurring in the segment can therefore particularly preferably be calculated for each segment. In the discrete case, the "homogenized state" is calculated by averaging the field variables of all elements in each segment.In general, this operation can be expressed as an integral and implemented in the specific numerical method through appropriate discretization. A preferred homogenized field quantity for a segment is, for example, the homogenized mechanical stress discussed above (under the specific requirements to be met by the component or "target conditions," for example, a pressure of 5 MPa from the side on the buffer stop). The following integral, for example, can be used to determine a homogenized mechanical stress: This means, for example, for the homogenized mechanical stress ^^ ^ ^that a mechanical stress distribution in a segment is compressed to a single value (scalar, vector, matrix, or tensor). Thanks to homogenization, the optimization does not have to be performed for n finite volumes or finite elements, but only over k segments, where k <= n is reasonable and, in the best case, k << n. This can significantly reduce the computational effort. The homogenized mechanical stress can be represented by a stress tensor as shown, whereby for representation (e.g. as input variable for a neural network) it is sufficient to use a six-dimensional stress state vector (which contains in vectorial form the matrix elements characterizing the stress tensor, namely the diagonal elements ^ ^^ , ^ ^^ , ^ ^^ for the compression in the three spatial directions x, y, z as well as the elements ^ ^^ , ^ ^^ , ^ ^^, for the thrust in these directions). Another preferred input variable (or input parameter) is, for example, a function ^̇ for the temperature-time behavior or temperature profile function (i.e., for example, an expected later cooling rate of the manufactured component and / or a special heat treatment), whereby the function can be a simple scalar, such as a cooling rate of 300K / s, or could again be represented by a vector that contains the temperature values ​​for different points in time. In a subsequent step S32, a database query is then carried out for particularly suitable parameter sets for "fixed" criteria or requirement parameters, i.e. for those requirement parameters whose fulfillment does not depend on the segment scan direction distribution. One such requirement parameter is, for example, the build rate. For example,A requirement-specific PS score is calculated for this requirement parameter, and based on this PS score, a pre-selection or ranking of the best candidate parameter sets is then carried out for the subsequent selection during further optimization. This can accelerate the process of finding the overall optimal parameter set. It is also possible to use these steps, for example, during the training of the AI-based optimization unit or neural network used. Then, if necessary, this can be omitted during later optimization, i.e., here in step S32, since the AI-based optimization unit indirectly takes this point into account. Subsequently, in step S33, suitable operational, i.e., already trained, neural networks NN (as AI-based optimization units) are searched for the corresponding field sizes in a database (e.g., in the data store DS), i.e.The search is for neural networks (NNs) designed to accept the aforementioned field variables as input variables for the neural network (NN). The search is preferably for neural networks capable of using a combination of different types of requirement data as input variables and / or generating a combination of different types of process variables as output data. An example of such a combined neural network is a neural network that, based on an input voltage state, provides a pair of optimal segment scan direction distributions and a corresponding optimal parameter set for the respective segment.On the input side, a combination could be such that a vector can be input into the neural network as an input variable, which vector includes, on the one hand, the stress state and, on the other hand, the temperature-time curve (possibly as a scalar in a single vector element). The basic structure of neural networks and training methods are sufficiently known to those skilled in the art, so that the following only provides a very rough, schematic, exemplary brief overview of a possible basic principle of neural networks that can be used within the scope of the invention and possible training methods for this. The neural networks NN can, in principle, be constructed in the form of all previously known variants of artificial neural networks. A simple, typical schematic representation of a first neural network NPS is shown in Figure 17.This neural network NPS is particularly simple in that it only has one input value, namely the above-mentioned six-dimensional vector with the homogenized stress state. to only one output value, here an optimal parameter set PS (which is represented by a scalar ^ ^represented, but which stands for a fixed tuple of individual parameter values). The input vector is usually input into the neural network NPS (this network NPS also stands in for other neural networks in the following explanations) at a so-called "input layer" LI, which is linked via any number of so-called "hidden layers" LH to an "output layer" LH, at which the output value is ultimately issued. Each of these layers contains a number of nodes or neurons, and usually each neuron in a previous layer is linked to all neurons in a subsequent layer, with the links having different weightings. In order to introduce non-linearity into a neural network (since not all tasks of neural networks can be represented with linear functions), the individual neurons orNodes pass on their results depending on a usually sigmodal “activation function” assigned to the respective neuron. In a trained network, the aforementioned weights and the parameters for the activation function (“activation function parameters”) are fixed. The number of nodes in the input layer LI depends on the input variable, for example, how many digits an input vector has. Likewise, the number of nodes in the output layer LO depends on the output variable. The number of nodes in the intermediate hidden layers LH, as well as the number of hidden layers, is at the discretion of the expert, who defines the network for the respective purpose before training. When training the network, the best values ​​in the neural network, such as the weights for the connections between the nodes and the activation function parameters, e.g.Training data is used for which the correct or optimal output variables are already known. These “correct” output variables for the input variables can be determined in advance and assigned to them, i.e. so-called “labeled” training data is used. Alternatively or additionally, the “correct” output variables for the input variables can also be determined using a parallel determination process, e.g. in a “classical” optimization process. Examples of this are given using Figures 18, 22, 23 and 24. During training, an error can then be determined for each of the output variables and with the help of error feedback and an optimization process, the weights can be adjusted layer by layer and the activation function parameters can be adjusted in each case in order to optimize the network.A very simplified flowchart for a typical example of such training of the neural network in Figure 17 is shown in Figure 18. Accordingly, for an input value, here again the six-dimensional vector for the homogenized stress state ^^ ^. ^, on the one hand, in a classic optimization process NO, an optimal parameter set PSOR is sought as a comparison value or reference output variable (hereinafter also referred to as “reference value”). In the classic optimization process NO, for example, a suitable objective function ZF (as explained above, for example) and / or PS scores PSS can be used for this purpose. So that the optimization is not only carried out with regard to one requirement, but all requirements can be taken into account, it is preferable to take several or all requirement-specific PS scores PSS into account in the process. In particular for this purpose, the individual PS scores PSS can also be combined to form an overall parameter set suitability value PSSG (overall PS score). The adoption of the requirement-specific PS scores PSS and determination of an overall PS score PSSG by the optimizer NO is shown schematically in Figure 18.A possible combination of the individual PS scores PSS to form an overall PS score PSSG in the individual segments and, if applicable, the formation of a sum parameter set suitability value across all segments of the component (which can also be usefully used here) will be explained in more detail later in connection with Figure 22. Secondly, an optimal parameter set is searched for as the "prediction value" PSON using the neural network NPS to be trained. These two optimal parameter sets PSOR, PSON, found in different ways, are compared in a step VG to determine a suitable error value ERR. For example, a mean square error could be determined as the error value ERR (for example, formed based on a distance between the two vectors representing the parameter sets PSOR, PSON in a space dimensioned by the number of elements of the vectors).In a subsequent step ES, a decision is then made as to whether this error value ERR is small enough. If this is not the case, a so-called “backpropagation” is used to correct the weights and activation function parameters in the neural network NPS to be trained, which is symbolized in Figure 18 by step KB. If the error value ERR is sufficiently small, the process is terminated in step TE, and the neural network NPS is considered to be sufficiently trained. In principle, however, any other suitable training method can be used. In the same way, a neural network NSV could be constructed and trained based on an input value, such as the six-dimensional vector. with the stress state, an optimal segment scan direction distribution SSV is found. A schematic representation of this is shown in Figure 19. In the example shown there, a 360-dimensional vector with the values ^ ^ ,…, ^ ^^^ which represents the segment scan direction distribution SSV by specifying the probabilities of occurrence of the respective angles in 360° steps in a plane, as already explained above with reference to Figure 7. As an additional input variable, a preselected parameter set PS could also be used here, whereby the input vector is simply extended by another vector element in the form of a scalar ^ ^can be supplemented. A network NSV trained in this way could in turn be used in training a combined neural network KNSP, KNWS (see, for example, the later explanations of Figures 23 and 25). Likewise, a neural network NNW could be constructed and trained in this way, which searches for an optimal parameter set PS (or an optimal segment scan direction distribution SSV) based on another input value, such as the function ^̇ for the temperature-time behavior. A schematic representation of a neural network for searching for an optimal parameter set PS (represented by the scalar ^ ^ ) is shown in Figure 20. Figure 21 shows a first example of a combined neural network KNSP. Starting from an input variable, an optimal combination of different output parameters is sought. In the example in Figure 21, the input variable is again the six-dimensional vector with the voltage state. The neural network KNSP is constructed and trained in such a way that it can, based on this, determine an optimal combination PSV (ie an optimal pair) of segment scan direction distribution SSV (again represented by the 360-dimensional vector with the values ​​^ ^ ,…, ^ ^^^ ,where other step sizes and a different number of angles are possible, ie the vector can have any length) and an associated parameter set PS (again represented by a scalar ^ ^). Such a combined neural network KNSP can also be constructed and trained using a process similar to that outlined in Figure 18. A corresponding flow chart is shown in Figure 22. For this purpose, it is only necessary to select or construct the classical optimization process NO' (or the "optimizer") in such a way that, starting from the input variable, an optimal pair of segment scan direction distribution SSV and parameter set PS is output as a reference output variable or reference value PSVOR, in order to compare this with a corresponding output variable or a prediction value PSVON of the neural network KNSP to be trained in the manner described above in the comparator VG, to determine an error ERR in the process and then to further modify the network accordingly if necessary. For this purpose, the classical optimization process NO' can in particular also include a suitable objective function ZF (as used, for example,explained above) and / or the above-described, preferably requirement-specific, parameter set suitability values ​​or PS scores PSS are used to ensure that segment scan direction distributions and parameter sets are selected that best meet the desired requirements. As already shown schematically in Figure 18, several or all requirement-specific PS scores PSS can preferably be taken into account in the process here too, in particular by combining the individual requirement-specific PS scores PSS into an overall parameter set suitability value PSSG (overall PS score) (the adoption of the PS score PSS and determination of the overall PS score PSSG by the optimizer NO' is again shown schematically in Figure 22).For example, if the individual requirement-specific PS score values ​​lie between 0 and 1, thus indicating a kind of probability of how well the specific requirement is met with the respective candidate parameter set, these requirement-specific PS scores could simply be multiplied to determine an overall PS score. For example, if a first candidate parameter set had a PS score of 0.8 for a first requirement and a PS score of 0.2 for a second requirement, whereas another candidate parameter set had a PS score of 0.6 for both the first and second requirements, the second candidate parameter set would be preferred because it has an overall PS score of 0.36, whereas the first candidate parameter set only has a PS score of 0.16. However, this assumes that the two requirements should be weighted equally.In principle, it could also happen that a particular requirement requires special emphasis. This could be taken into account by a weighting factor when determining the overall PS score. In one case, only the aforementioned PS score ^^^ is taken into account. ^ ^ ^^^^^^^^^ (^ ^ , … ) to ensure a safety factor and the PS score ^^^ ^ ^ ^^^^ (^ ^ ) are to be taken into account for the construction rate, the following product results: By maximizing the overall PS score ^^^^ ^ ^ (^ ^ , ^, ^ ^^ , … ) an attempt can be made to determine for each possible parameter set a segment scan direction distribution in the respective segment, which as a pair lead to the maximum overfulfillment of all criteria: This means that with a fixed (candidate) parameter set, the overall PS score is maximized ^^^^ ^ … ) by varying the segment scan direction distribution, and this for all possible (candidate) parameter sets for the segment. Then, from all (candidate) parameter sets with the respective optimal segment scan direction distribution, the optimal parameter set for the respective segment can be determined. ^^^ be elected: This results in the following formula for nested optimization: ^^^^^^ ^ ∈^^ The approach described so far is limited to one segment. To find an optimal output value for the entire component (i.e., suitable pairs of parameter sets and segment scan direction distributions for the individual segments that lead to an optimal component overall), for example, the sum of all total PS scores ^^^^ ^ ^ (^ ^ , ^, ^ ^^, … ) across all segments (i.e., a “sum parameter set suitability value”). For this purpose, a weighted sum is suitable, which must be maximized: ^^^ = ∑ ^ ^^ ^^^^^ ^ ^^ ∈ ^ ^ ^denotes the volume of the respective segment. A heuristic approximation method, particularly preferably a simulated annealing method (SA method) or a quantum annealing method (QA method), can preferably be selected as the method for this optimization. For the sake of simplicity, the optimization using the heuristic approximation method, in particular the SA method or QA method, can also be carried out individually in each segment, since the commutative law applies to the sum and the sum of the partial maxima must result in the maximum. These methods are also suitable within the classical optimization methods NO, NO' (e.g., according to Figures 18 and 22) for training neural networks. The SA or QA method solves a combinatorial problem.It is used to find an approximate solution to optimization problems whose high complexity precludes exhaustive testing of all possibilities and mathematical optimization methods. The goal is to find an optimum from which the greatest optimization potential for a coupled geometry, scan-strategy optimization, can be carried out. The name of this method comes from a mathematical simulation of a cooling process, such as annealing in metallurgy. After heating a metal, the atoms have sufficient time to arrange themselves and form stable crystals during slow cooling. This achieves a state with the lowest possible energy (close to the optimum). Applied to the SA or QA method, the temperature corresponds to a probability with which an intermediate optimization result may deteriorate.In contrast to a local search algorithm, the method can leave a local optimum again. Less favorable intermediate solutions are accepted because this offers the chance of finding a better local optimum - in this case a result with an even better overall PS score. Both methods are known in principle (see, for example, typical solutions for the so-called "traveling salesman" problem) and therefore need not be described in detail here. Suitable methods are described, for example, in "An Effective Simulated Annealing Algorithm for Solving the Traveling Salesman Problem" by Wang, Zicheng et al. in Journal of Computational and Theoretical Nanoscience, Volume 6, Number 7, July 2009, pp. 1680-1686(7), for the classical variant and in "Quantum annealing of the traveling-salesman problem" by Roman Martoňák et al. in Phys. Rev. E 70, 057701 – 10 November 2004, for the QA method.To further accelerate the process, an AI-based method can be used for a kind of pre-selection of suitable candidate parameter sets. This reduces the space of selectable parameter sets for which an optimized segment scan direction distribution must be determined. In practice, the field sizes will be limited anyway. For example, a component will never exist if the permissible mechanical stress is exceeded. This permissible value range can be described by the flow body under purely elastic loading. In a preliminary training, this permissible space can then be evaluated at discrete points, and the optimization can be performed for these points.If this approach is used within the otherwise classic optimization procedure N0, NO', a hybrid method is actually used to create reference values ​​in order to train a more complex neural network. At the end, a pair consisting of the optimal parameter set and the optimal segment scan direction distribution is available for each segment of the component as a reference value PSVOR for comparison with the prediction value PSVON, which is or was found by the neural network KNPS to be trained. Alternatively, this optimization procedure can also be carried out in advance, and the optimal distribution of the scan angles (optimal segment scan direction distributions) is calculated for each segment for all possible (candidate) parameter sets and stored in a look-up table. The values ​​in this table can then be used as labeled training data to train the neural network.In the case of the training methods described above (particularly in connection with Figures 18 and 22), in which a more classical and therefore more complex method is used to generate the training or reference values, it must be taken into account that the training can also be carried out in such a way that the respective neural networks to be trained are first "pre-trained" using classical methods with less effort (e.g. methods that initially only work segment by segment, i.e. do not use a sum parameter set suitability value, for example) and then, for further training (a type of "fine-tuning" or so-called "transfer learning"), the reference values ​​are created using a more complex method, for example with a sum parameter set suitability value, in order to take the optimization into account in the entire component.If (different) components with similar (standard) segments are repeatedly created, it would also be conceivable to store pre-trained neural networks for these segments in a database, which could then be individually "retrained" for the respective component using a more complex optimization process. AI-based optimization units or neural networks can also be pre-trained for specific groups of requirements and / or process parameters, which can then be individually retrained for the respective current requirements or process parameters using transfer learning. For example, a neural network that was trained using a specific type of steel as a construction material could be quickly retrained for other similar types of material.If the combined neural network KNSP trained with a previously described optimization method or the guided data generated therefrom is later used in the optimization process (for example, in step S3 of the method according to Figure 12), the optimized process variable values ​​for the component are ultimately determined in such a way that optimized process variable values ​​are determined for each individual segment, which are optimized with regard to an overall parameter set suitability value in the respective segment and with regard to a sum parameter set suitability value in the component as a whole. Figure 23 shows a flowchart for a possible method for training such a combined neural network KNSP as quickly as possible, which is based on the stress state. as input variable for the respective segment as output variable again provides an optimal combination of segment scan direction distribution SSV and parameter set PS, Analogous to the procedure shown in Figure 22, the input variable ^^ ^ ^ The neural network NPS is then trained, which determines the optimal combination of the segment scan direction distribution SSV and the parameter set PS. This pair is referred to as the predictive value PSV'. ON for further comparison with the reference value. However, instead of determining the reference value PSV' OR To use a more complex, special, classical optimization method as in Figure 22, two previously trained simpler neural networks are used here, namely a network NPS, which is based on the input value an optimal parameter set PS ONand on the other hand an already trained neural network NSV, which is based on the input value and the optimal parameter set PSON found by the first network NPS, a corresponding optimal segment scan direction distribution SSV is searched for, so that finally an optimal combination of parameter set PS and segment scan direction distribution SSV is determined as the reference value PSV'OR. Here, too, the two optimal parameter sets PSV' found in different ways OR 'PSV' ONIn a step VG, the values ​​are compared to determine a suitable error value ERR, such as the aforementioned Least Mean Square. In a subsequent step, a decision is then made as to whether this error value ERR is small enough. If this is not the case, the weights and activation function parameters in the neural network are corrected using a process known as "backpropagation," which is again symbolized by step KB in Figure 23. If the error value ERR is sufficiently small, the process is terminated in step TE, and the neural network is considered sufficiently trained. The prerequisite for this is, of course, the existence of already trained neural networks NPS, NSV for the individual values.It should be noted that the NSV network must be designed and optimized to determine the optimal segment scan direction distribution based on the voltage state and a predefined, optimized parameter set as input variables. This means that this is ultimately also a combined neural network, except that two different types of input variables are used to find an output value (the segment scan direction distribution). It should also be noted that an optimal parameter set PSON preselected in the first neural network NPS is used to create the reference variable or reference value PSV'OR, and the second neural network NSV operates with this fixed value and searches for the appropriate segment scan direction distribution SSV solely for this purpose.In other words, unlike the method shown in Figure 22, the method according to Figure 23 no longer tries out a multitude of possible combinations on the training side, in which the segment scan direction distribution SSV is first optimized for all possible parameter sets and then it is checked which pair produces the best overall PS score. In return, however, this method is considerably faster when training a neural network KNSP, and the results of this combined neural network KNSP are entirely sufficient for the entire process, since the found output variable (i.e., the pair of parameter set and segment scan direction distribution) is only a first approximate solution, which is usually further modified in later process stages (see Figure 12). However, the entire process is improved by finding a better starting point for the subsequent process steps.In particular, the method converges faster, meaning that the subsequent optimal solution is found more quickly. Figure 24 shows a schematic representation of an example of an even more complex combined neural network KNWS, and Figure 25 shows a flow chart for a possible training procedure. Like the neural network KNSP according to Figure 21, this neural network KNWS is also constructed and trained in such a way that, based on an input variable for the respective segment at the output layer LO, it generates an optimal combination of the segment scan direction distribution SSV (represented by the 360-dimensional vector with the values) as the output variable PSV''. ^ ^ ,…, ^ ^^^ ) and an associated parameter set PS (again represented by a scalar ^ ^). In contrast to the neural network KNSP shown in Figure 21, the input variable is now also a combination of two different types of request data. Here, a seven-dimensional vector is used as the input variable at the input layer LI, which combines the six-dimensional vector with the voltage state and additionally contains a scalar value as a further vector element, which represents the function ^̇ for the temperature-time behavior (for example, here a simple cooling rate in K / s). The simplified flow chart shown in Figure 25 shows that a possible method for training such a combined neural network KNWS as quickly as possible can be constructed very similarly to the method according to Figure 23. The key point here is again that previously trained simpler neural networks NNW, NPS, NSV are used to determine an optimal combination of parameter set PS and segment scan direction distribution SSV as a reference value PSV''OR. Here, too, a trained neural network NPS is used, which is based on the input value a voltage-optimized parameter set PS σand on the other hand a trained neural network NSV, which is based on the input value and a pre-optimized parameter set PSOR, which was found using the neural network NPS, an associated optimal segment scan direction distribution SSV is determined. These neural networks NPS, NSV can therefore, in principle, be the same networks as those used in the method shown in Figure 23. In addition, a temperature-optimized parameter set PS is determined using another trained neural network NNW based on the temperature profile function ^̇ as input variable. ^̇ The stress-optimized parameter set PSσ and the temperature-optimized parameter set PS ^̇are then initially fed to a parameter set selector PAS as input variables. This selector decides which parameter set will be passed on as parameter set input variable PSON to the neural network NSV to determine an optimal segment scan direction distribution SSV. For this selection, the parameter set selector PAS can preferably use a so-called "policy reinforcement learning method". The neural network NSV can then select the pair of optimal parameter set PS ON and optimal segment scan direction distribution SSV as reference value PSV'' ORSuitable “policy reinforcement learning methods” are known to the expert and can be found, for example, in “Learning to Optimize” by Ke Li, Jitendra Malik in arXiv:1606.01885, 2016 and International Conference on Learning Representations (ICLR), 2017, or in “Learning to Optimize Neural Nets” by Ke Li, Jitendra Malik in arXiv:1703.00441, 2017. In parallel, the input variables , ^̇ fed to the neural network KNWS to be trained, which finds an optimal combination of segment scan direction distribution SSV and parameter set PS as prediction value PSV'' ON for further comparison in step VG with the reference value PSV'' ORdelivers. Based on the error value ERR determined here (such as a Least Mean Square as mentioned above), a decision can then be made (in block ES) as to whether this error value ERR is small enough and the neural network KNWS is considered sufficiently trained (block TE), or whether further correction of the weights and activation function parameters in the neural network KNWS in block KB is appropriate. In this method according to Figure 25, a fixed, preselected optimal parameter set PSON is used to create the reference output variable or the reference value PSV''OR, and the second neural network NSV works with this fixed value and searches for the appropriate segment scan direction distribution SSV only for this purpose. As already mentioned, an output variable PSV'' found later by the combined neural network trained in this way is only a first approximate solution, which is usually further modified in later process stages.Once a suitable neural network NN has been found, the data of this neural network NN can be loaded into the database in step S34 (in the method according to Figure 16), or more specifically, the weights for the connections between the nodes of the various layers LI, LH, LO and the activation function parameters of the various nodes of the trained neural network are loaded. It should be noted at this point that the reference number NN in the figures can stand for any AI-based optimization unit NN suitable for the respective goal, in particular also for the neural networks NPS, NSV, NNW, KNSP, KNWS described above. Using this data from the selected neural network NN or the selected neural networks NN, the respective optimal segment scan direction distribution and the associated best parameter set can then be quickly calculated in step S35 based on the input data.In the next step S36, the current segment scan direction distributions and the parameter sets in the relevant segments are updated for further optimization, and the method according to Figure 12 works with these new segment scan direction distributions and parameter sets. At the end of step S3, the same segments SG' can still be present, but better current parameter sets that better meet the requirements should preferably be assigned to some of the segments SG'. Following step S3, the objective function ZF can then be used in step S4 (see also Figure 12) to optimize the boundaries of the segments, i.e. an attempt is made to achieve an even better result by shifting individual segment boundaries in certain areas. If necessary, AI-based optimization units or neural networks NN can also be used to support this.This explicitly includes not only shifting segment boundaries of segments within the component, but also possibly shifting segment boundaries between segments at the edge of the component and outer powder segments in the area. This means that under certain circumstances the outer contours of the component can also change, for example, certain struts can be thickened or thinned, depending on what is required for the specific case. In this way, the component geometry can be optimized at the same time. The optimization options in step S4 are also explained in DE 102022117935, although not all of the options described there have to be used. At the end of step S4, improved segments (and optionally further improved segment scan direction distributions and parameter sets) could then be available that match the parameter sets selected in step S3 with regard to their geometry or segment boundaries.In step S5, the procedure from step S2 is repeated once again, i.e. a new state description (synonymously also referred to as system description) is determined with the current process variable values, i.e. the current segments, the current parameter sets and the current segment scan direction distributions, and a check is carried out to determine whether all requirements, in particular the quality requirements, are sufficiently met. If the requirements are not sufficiently met, the program returns to step S4. This loop between steps S4 and S5 is executed until a termination criterion is reached, i.e., until, for example, the changes between two iteration steps become very small with regard to the specified quality criteria. It can then be assumed that almost the best combination for the current load case is present.In the subsequent step S6, which comprises three sub-steps S6a, S6b, and S6c, a check is carried out to determine whether all areas containing powder also have a way out of the component. This ensures that no powder remains in the component after unpacking, at least in cases where a powder-filled cavity is not intentionally desired within the component, for example, in cavities that are not connected to the outside. For this purpose, in step S6a, the powder can be assumed to be a viscous fluid flowing out of the cavities. By returning to step S4, in which the objective function ZF is also used to modify the segment boundaries, the segment boundaries can then be changed so that the areas with powder inclusions can be minimized or removed entirely.This can be done in a loop which, for a certain number of iterations, attempts to either shift the inclusions by changing the geometry of the segments so that they ultimately lie on the component surface, or to fill the inclusions with molten material, i.e. to eliminate the powder-filled cavities. Here, for example, the termination criterion can again be that no further relevant changes are made in the loop or that a maximum number of iteration steps have been carried out. Subsequently, in the optional step S6b, a so-called Minkowski subtraction can be carried out in areas where powder inclusions may still be present in order to remove these areas from the computational grid by erosion, analogous to image processing methods. In a final step S6c, a check is then carried out to determine whether any powder inclusions may still be present.If this is the case, these areas are removed by returning to step S3. There, a new parameter set is selected for the area in question, which results in the area being solidified, and then the complete optimization is carried out again, starting from step S3, using the new parameter set. However, steps S6a to S6c are explained in more detail in DE 102022117935, so reference is made to this in this regard. It should be noted that the depowdering step S6 is deliberately carried out separately after the optimization of the other points within the objective function in step S4. This is possible by setting the pressure to 0 everywhere in the first run, and thus in the previous run through steps S4 and S5 an optimization with regard to all other criteria is carried out first and depowdering does not already take place. With regard to the depowdering criterion, the objective function ZF orthe corresponding subfunction is initially set to 0 as inactive throughout the domain due to a clever choice of parameters. This approach can save computing time if, at the beginning of the optimization, a solution is initially available in a starting configuration whose shape is even further away from the optimal shape, and therefore a large number of passes through the iteration loop between steps S4 and S5 are to be expected. Steps S7 and S8 are purely optional and can be used to compensate for any errors introduced in the previous steps due to the homogenization of the states of the segments (e.g., the determination of an average state for each segment, even if this varies spatially across the respective segment), since such homogenization can involve a certain amount of error.However, through homogenization in conjunction with AI-based optimization, at least a very good approximation of the optimum can be achieved in any case, which is close to the real optimum, so that generally only minor "post-optimizations" (a kind of "fine-tuning") would be necessary here. With this approach, step S8 corresponds to step S5 or S2, i.e. a status description and check is carried out here to determine the extent to which the system or component would meet the requirements with the current segments and the parameter sets currently assigned to the segments. If the requirements are not sufficiently met, a return to step S7 occurs. This loop between steps S7 and S8 is repeated until a termination criterion is reached, i.e. until, for example, the changes between two iteration steps become very small with regard to the specified quality criteria.For the exact procedure in steps S7 and S8, reference is again made to DE 10 2022 117 935. In steps S7 and S8, any possible spatial variation of the state (e.g., mechanical stress) within the segments is also taken into account, so these steps are naturally more complex than, for example, steps S2 and S5. However, since it is already certain that the current state at the start of these steps S7 and S8 is very close to the optimum, only a few more iterations are required. Finally, step S9, which is also optional, deals with a possible heat treatment of the subsequently manufactured component (if the heat treatment has not already been sufficiently taken into account in step S3 with the help of the neural networks). It comprises two sub-steps S9a and S9b.In step S9a, a virtual heat treatment is performed on the (still) virtual component to be manufactured, and the characteristic temperature profiles from this simulated heat treatment are stored for each point. In the subsequent step S9b, a check is then made to determine whether the simulated temperature profiles are within the permissible limits of the necessary heat treatment, for example, whether some points in the component have become too hot or not hot enough. If the limits are exceeded, a return to step S2 can be made, so that the entire optimization is ultimately performed again with a new starting configuration. The starting configuration is then selected such that the heat treatment problem is likely eliminated.If, however, the requirements in the context of heat treatment are met, the end of the optimization process is finally reached and the desired optimized process variable values ​​PGO are available, namely in the form of optimal segment boundaries SGG, optimal parameter sets PS and optimized segment scan direction distributions SSV. The optimization of the segment boundaries SGG can also include an optimized alignment of the object relative to the main build direction, i.e. the z-direction in which the layers are stacked. A modification of the segment boundaries can also be carried out with the aim of reorienting or optimizing the orientation of the component relative to the main build direction. By appropriate orientation in the build space, for example, overhangs and / or support can be reduced or minimized. Further explanations can also be found in DE 102022117935.Finally, it should be noted that within the scope of the optimization process, optimization preferably takes place simultaneously for all segments of the component, i.e., for example, not only are the start segment boundaries determined for all start segments SG' at the beginning in step S1, but the other start parameter sets PS' and start segment scan direction distributions SSV' are also set and always optimized together in the respective steps. This is particularly suitable for the inventive use of AI-based optimization units, since this allows the optimization to be carried out considerably faster than with a classic optimization. In the optimization process according to Figure 12, as previously explained, the current configuration is evaluated in several steps, for example in steps S2, S5 and S8. In this process, it is checked whether a construction process in which the segments currently present in the optimization process (i.e.The current segment boundaries (the current segment boundaries) and the current parameter sets associated with the segments, as well as the current segment scan direction distributions (SSV), would result in a component that meets certain requirements. This means that a state description of the virtual component can be determined using a state simulation, and the state description can, if necessary, be compared with specified (quality) requirements in a further step. Macroproperty values ​​of the individual segments can be used to determine the state or to determine the state description. Such macroproperty values ​​can, as mentioned above, be, in particular, the texture in the segment, which, as mentioned above, can be described by the orientation density function (ODF), but also other macroproperty values ​​derived from it, such as the elasticity sensor, the yield point distribution, hardening coefficients, thermal conductivity, fracture strength, etc.With reference to Figure 26, it will now be explained how, given a known parameter set PS for constructing the layers of a segment and a known segment scan direction distribution SSV of the segment, a macroproperty value MWA of the respective segment can be determined in a suitable device 70 or unit for determining macroproperties. It is explicitly pointed out that this device 70 can advantageously also be implemented in the form of software on a suitable computer unit. In particular, it can therefore be integrated into the optimization process, for example, as a software object or subroutine. Likewise, all other components of the device 70 now described, such as the interfaces and the database system, can be implemented in software. Furthermore, it is also possible, for example, to implement interfaces partly from hardware and partly from software and, for example,The entire device 70 is to be implemented distributed across various computer units that are suitably linked to one another. This applies in particular to the database system DBS used by the device 70, which here comprises, for example, a macro property database EDA and a basic property database EDB, which can also be easily outsourced to other computer and storage units. The functionalities and data contents of the macro property database EDA and the basic property database EDB, and options for constructing such databases EDA and EDB, will be explained later. For example, the current parameter set PS can be adopted via a parameter set interface unit 72, and a current segment scan direction distribution SSV can be adopted for the segment construction process via a scan direction interface unit 73.Furthermore, the device 70 can have an interface 74 via which segment information SGI can be transferred, i.e., information about the segment, such as the number of slices, the current segment boundaries, etc. All of this information can then be used in a macroproperty determination unit 71 to determine the macroproperty value MWA, or better still, an entire group of macroproperty values ​​for the respective segment, to which the current parameter set PS and the current segment scan direction distribution SSV, as well as the segment information SGI, are to be assigned. The operation of this macroproperty determination unit 71 is shown in Figure 26 in a very simplified flowchart format within the macroproperty determination unit 71.In a first step MS1, the macro property database EDA can first be queried to determine whether a finished macro property value MWA is already stored for a specific combination of parameter set PS and segment scan direction distribution SSV. If this is the case, this macro property value MWA is simply adopted, and this macro property value MWA can be returned by the macro property determination unit 71 via an interface 75 of the device 70, for example to a higher-level software component, which then continues to process this macro property value MWA. Macro property values ​​MWA are preferably stored in the macro property database EDA for those combinations of parameter sets PS and segment scan direction distributions SSV that occur particularly frequently, i.e., which are standard combinations that are used again and again.Of course, this macro property database EDA can be expanded gradually. If the query in the macro property database EDA was unsuccessful, a macro property value MWA must be recalculated for the current individual case based on the current parameter set PS and the current segment scan direction distribution SSV. To do this, in a further step MS2, a current basic property value BEW for the individual layers is queried in a basic property database EDB for the current parameter set PS. Such a basic property value BEW can, for example, be the texture and / or a microstructure MS of the layer, but also values ​​derived from it that apply to the respective layer. Preferably, however, work continues with the texture TX, which is described by an ODF, and the microstructure MS is also used.In a third step MS3, a mathematical homogenization of the basic property values ​​BEW for the individual layers then takes place. This means that the basic property values ​​BEW of the individual layers of the segment are combined in a suitable manner to approximate the macroproperty value MWA of the entire segment. This uses information about the number of layers, the layer scan direction arrangements within the layers, and the rotations of the layers relative to one another, which lead to the current segment scan direction distribution. Within the scope of this homogenization process in step MS3, for example, an average of the basic property values ​​of the individual layers can be calculated, with this average then forming the desired macroproperty value MWA.Alternatively, the inverse of the mean values ​​of the basic property values ​​BEW of the individual layers can be determined first, and then the inverse of this mean of the inverse values ​​is calculated. This inverse of the mean then forms the macroproperty value. Which of the two methods is used can depend on the microstructure MS of the individual layers and the current loading requirements. It should be noted at this point that, as already mentioned above, the basic property values ​​BEW of the individual layers do not differ significantly provided they were manufactured with the same parameter set PS (i.e. the same hatch strategy), except for the fact that with a change in orientation relative to the (in principle arbitrarily definable) reference orientation RO between the layers, the orientation of the basic property values ​​also changes.This naturally leads to a change in the orientation of the texture TX. Ultimately, this also influences all property values ​​in the form of direction-dependent material parameters, such as the elasticity tensor or the yield strength distribution, for example in the form of the Hill tensor, which can be quite different in different directions. However, it is sufficient to know the basic property values ​​for one orientation, preferably the reference orientation. The basic property values ​​for the other orientations can be calculated from this using simple operators, e.g., a simple rotation. The macro property value MWA determined in step MS3 can then also be output via interface 75, e.g., to a higher-level unit, which then processes it further.In addition, this macro property value MWA could also be stored in the macro property database EDA together with the parameter set PS on which the calculation was based and the associated segment scan direction distribution SSV. Provided the macro property database EDA has sufficient space, in principle, any new macro property value MWA could also be stored in the macro property database EDA. However, this is not necessarily done for, for example, very rare parameter sets PS or segment scan direction distributions SSV. In principle, the system can also be designed to learn, i.e.,a list is kept of the parameter combinations PS and SSV that occur most frequently, and the macro property database EDA is then gradually expanded for these parameter combinations, or vice versa. Each macro property value MWA is first stored in the macro property database EDA and then deleted again if it is no longer queried for a certain period of time, in order to create storage space for other combinations. The structure of a basic property database EDB, for example by producing and measuring different test specimens in different test manufacturing processes in order to determine the basic property values ​​BEW achieved for one or more layers of the test specimen using the different parameter sets, is explained in more detail with reference to several figures in DE 102022117935 and in particular also in DE 102022117936, so that reference can be made to them.The content of these documents is therefore also incorporated here to this extent. As explained above, the method and device for determining property values ​​of a segment or for checking the current state of a segment to determine whether it fulfills certain conditions can be used, in particular, within an optimization process to determine suitable process variable values ​​for the production of a product. In principle, however, it is also possible to carry out such a check entirely separately from such an optimization process, for example, to check control parameters before use that are intended for the manufacture of a component but were created in a different way than in the aforementioned optimization process. Likewise, a subsequent check can also be carried out on components that have already been manufactured and which are not to be destroyed and on which certain stress tests cannot therefore be carried out.For this purpose, knowledge of the process variables used in production and required for the method described above is sufficient. A possible structure of a testing device 80 that can be used for this purpose and a testing method are described in detail, for example, in patent application DE 102022117 935 (see, for example, Figures 24 and 25 with the associated description), to which reference can be made here or whose content should be considered incorporated herein. The testing device and the testing method described therein are equally applicable in connection with the devices and methods explained in the present application. Finally, it is pointed out once again that the devices and methods described in detail above are merely exemplary embodiments that can be modified in a variety of ways by a person skilled in the art without departing from the scope of the invention.In particular, the optimization method can be adapted almost arbitrarily to current requirements, for example, by adding additional steps, combining steps, or exchanging or expanding optimization criteria. Optimization criteria can also be taken into account in different ways. It should also be noted at this point that while the method described above for forming an objective function using a weighted sum of sub-functionals may be preferred, the method is not necessarily limited to this. For example, sub-functionals can also be defined in the form of constraints, e.g., using the Lagrange multiplier method. These constraints can be equality or inequality constraints, for example. Further information on this can be found in fundamental works such as C. Richter, Optimization in C++: Fundamentals and Algorithms, 2016, Wiley-VCH, Berlin.With regard to AI-based optimization units, it should be emphasized again that other AI methods or concepts can be used besides the neural networks presented above. In particular, the training methods can be modified and adapted to the respective requirements. Furthermore, the use of the indefinite articles "ein" or "eine" does not exclude the possibility that the relevant features may be present multiple times. Likewise, the term "unit" does not exclude the possibility that it consists of several interacting subcomponents, which may also be spatially distributed.

[0002] List of reference symbols 1 Production device / laser melting device 2 Manufactured product / component / object 2' Manufactured product / component / buffer stop 2'' Manufactured product / component / square bar 3 Process space / process chamber 4 Chamber wall 5 Container 6 Container wall 7 Working level 8 Construction field 10 Carrier 11 Base plate 12 Construction platform 13 Build material (in container 5) 14 Storage container 15 Build material (in storage container 14) 16 Coater 17 Radiation heater 20 Irradiation device / exposure device 21 Laser 22 Impact surface of the energy beam 23 Deflection device / scanner 24 Focusing device 25 Coupling window 50 Control device 51 Control unit 53 Irradiation control interface 54,54' Control data generation device 55 Bus 56 Terminal 57 Data generation unit 58 Decision unit 60 Device for generating optimized process variable values ​​61 Request interface unit 62 Interface 63 Interface 64 Process variable interface unit 65 Optimization unit / Optimizer 70 Device for determining property values ​​71 Macro property determination unit 72 Parameter set interface unit 73 Scan direction interface unit 74 Interface 75 Interface 80 Verification device AD ​​Request data BEW Basic property values ​​BSD Control data / Exposure control data DBS Property database system / Database system DS Data storage E Energy beam / Laser beam EDA Macro property database EDB Basic property database ERR Error value ES Process step decision FS Focus control data G Area GD Geometric data H Horizontal direction HS Heater control data HS2,HS3 Layer scan direction arrangement / hatch direction arrangement / hatch strategy HWR Main heat flow direction KB Backpropagation step KNSP, KNWS Combined neural network KPS Candidate parameter sets L, L1, L2, L3, L4 Layers LH Hidden layer LI Input layer LO Output layer LS Laser control data MS Microstructure MS1, MS2, MS3 Process steps MWA Macro property values ​​NN AI-based optimization unit / neural network NNW, NPS, NSV AI-based optimization unit / neural network NO, NO' Classical optimization process / optimizer PAS Parameter set selector PGO Optimized process variable values ​​PS Parameter set PS' Start parameter set PSON, PSVON, PSV'ON, PSV''ON Prediction values ​​PSOR, PSVOR, PSV'OR, PSV''OR Reference value PSV'' Output variable PSσ Input variable / stress-optimized parameter set PS, ^̇Input variable / temperature-optimized parameter set PSD Control data / process control data PSS Parameter set suitability value / PS score PSSG Total PS score QA Quality requirements / quality requirement data RO Reference orientation S Scanning direction / direction of movement of the impact surface SD Scanning control data SG Segments SG' Start segments SGG Segment boundaries SGI Segment information SG0 Powder segment SG1, SG2, SG3 Segments SSV Segment scanning direction distribution SSV' Start segment scanning direction distribution SSV1, SSV2, SSV3, SSV4 Segment scanning direction distribution ST Coating control data S0 to S10 Process steps S31 to S36 Sub-steps S6a, S6b, S6c, S9a, S9b Sub-steps TE Process step end TF1, …, TFi, …, TFn Sub-functions / sub-functions / sub-functional TSD Carrier control data TX Texture V Vertical direction VG Process step comparison x, y Spatial directions in layer plane z Main construction direction ZF objective function ^ ^ Process parameter set ^^ ^ ^homogenized field size / homogenized stress state / input size ^ ^^ , ^ ^^ , ^ ^^ Matrix elements of the homogenized stress state ^̇ Temperature curve function / Cooling rate / Input variable ^ ^ , ^ ^ ,…, Values ​​of the segment scan direction distribution SSV

Claims

Patent claims 1. Method for generating optimized process variable values ​​(PGO) for an additive build-up process of a manufacturing product (2, 2', 2'') from several layers (L, L1, L2, L3, L4) of a build-up material (13) with the following method steps: - Providing requirement data (AD, ^^ ^ ^ , ^̇) of the manufactured product (2, 2', 2''), - carrying out an optimization procedure to determine the optimized process variable values ​​(PGO) taking into account the requirement data (AD, ^^ ^ ^, ^̇), wherein at least one optimized scan direction distribution (SSV) for at least one region of the manufactured product (2, 2', 2'') is determined as an optimized process variable value (PGO) using an AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS), - providing the optimized process variable values ​​(PGO).

2. The method according to claim 1, wherein in the optimization method, at least one optimal parameter set (PS), which comprises a defined group of process parameter values, is selected from a number of candidate parameter sets (KPS) as at least one further optimized process variable value (PGO), preferably also using an AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS). 3.Method according to claim 1 or 2, wherein the manufactured product (2, 2', 2'') is divided into a plurality of segments (SG, SG1, SG2, SG3) using the requirement data (AD), in particular geometric data (GD) of the requirement data (AD), and the optimization method is carried out in such a way that optimized process variable values ​​(PGO), preferably an optimal parameter set (PS) and an optimized segment scan direction distribution (SSV) per segment (SG, SG1, SG2, SG3), are determined for each of the individual segments (SG, SG1, SG2, SG3).

4. Method according to one of the preceding claims, wherein the optimization method comprises a plurality of iteration steps and at least one AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS) is used in at least one iteration step and / or. wherein, in the optimization method, at least one starting process variable value (PS', SSV') is initially determined using an AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS).

5. The method according to one of the preceding claims, wherein at least one AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS) comprises at least one neural network (NN, NPS, NSV, NNW, KNSP, KNWS). 6.Method according to one of the preceding claims, wherein for at least one region of the manufactured product (2, 2', 2''), for at least a number of possible scan direction distributions and / or at least a portion of the candidate parameter sets (KPS), at least one parameter set suitability value (PSS) is determined, and an optimized scan direction distribution (SSV) is determined and / or an optimal parameter set (PS) is selected from the candidate parameter sets (KPS) using the parameter set suitability values ​​(PSS), wherein parameter set suitability values ​​(PSS) are preferably determined for different pairs of segment scan direction distributions (SSV) and candidate parameter sets (KPS).

7. Method according to claim 6, wherein for at least a portion of the scan direction distributions (SSV) and / or candidate parameter sets (KPS), a plurality of requirement-specific parameter set suitability values ​​(PSS) for different requirement data (AD, ^^ ^) are determined.^ , ^̇) are determined, wherein particularly preferably the requirement-specific parameter set suitability values ​​(PSS) for a scan direction distribution (SSV) and / or a candidate parameter set (KPS) are each combined to form an overall parameter set suitability value (PSSG).

8. The method according to claim 7, wherein within the optimization method, optimized process variable values ​​(PGO) for the manufactured product (2, 2', 2'') are determined such that optimized process variable values ​​(PGO) are determined for each of the individual segments (SG, SG1, SG2, SG3), which are optimized with regard to an overall parameter set suitability value (PSSG) in the respective segment and with regard to a sum parameter set suitability value in the manufactured product (2, 2', 2'').

9. The method according to one of claims 6 to 8, wherein the determination of a scan direction distribution (SSV) and / or the selection of an optimal parameter set (PS) from the candidate parameter sets (KPS) for a segment (SG, SG1, SG2, SG3) using the AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS), whereby preferably an AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS) is used, during the generation of which a training of the AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS) was carried out using parameter set suitability values ​​(PSS).

10. The method according to claim 8 or 9, wherein the process variable values ​​(PGO) optimized with respect to a sum parameter set suitability value in the manufactured product (2, 2', 2'') are determined using a combinatorial optimization method, preferably a heuristic approximation method, particularly preferably a simulated annealing method and / or a quantum annealing method.

11. Method for generating control data (BSD,PSD) for a production device (1) for the additive manufacturing of at least one manufactured product (2, 2', 2'') from several layers (L, L1, L2, L3, L4) of a build material (13) in an additive build process, comprising the following method steps: - providing optimized process variable values ​​(PGO) generated for the additive build process in a method according to one of the preceding claims, - generating the control data (BSD, PSD) for the production device (1) such that the optimized process variable values ​​(PGO) are sufficiently achieved in the additive build process according to a predetermined evaluation criterion, wherein build material (13) is preferably built up and selectively solidified within the additive build process, wherein, for solidification, the build material (13) is irradiated with at least one energy beam (E) on a build field (8), wherein an impact surface (22) of the energy beam (E) is moved on the build field (8),to melt the build-up material (13) in a target area in and around the impact surface (22).

12. A method for controlling a production device (1) for the additive manufacturing of a manufactured product (2), wherein control data (BSD, PSD) for the device (1) are generated according to a method according to claim 11, and the control of the production device (1) is carried out using this control data (BSD, PSD).

13. Method for creating an AI-based optimization unit (KNSP, KNWS), in particular for a method according to one of claims 1 to 10, in order to create a plurality of different types of request data (AD, ^^ ^ ^ , ^̇) to determine optimized process variable values ​​(PGO), whereby initially - at least one first AI-based optimization unit (NPS, NSV, NNW) is trained, which is based on a first type of requirement data (^^ ^ ^) optimized process variable values ​​(PGO) of a first type of process variables (PS) are determined and - at least one second AI-based optimization unit (NPS, NSV, NNW) is trained, which is based on the first type of requirement data (^^ ^ ^) optimized process variable values ​​(PGO) of a second type of process variable (SSV) are determined or which, based on a second type of requirement data ( ^̇), optimized process variable values ​​(PGO) of the first type of process variable (PS) and / or optimized process variable values ​​(PGO) of the second type of process variable (SSV) are determined and then an AI-based combination optimization unit (KNSP, KNWS) is created using a training method in which at least the first and the second AI-based optimization unit (NPS, NSV, NNW) are coupled to one another to monitor the training of the AI-based combination optimization unit (KNSP, KNWS).

14. Device (60) for generating optimized process variable values ​​(PGO) for an additive build-up process of a manufacturing product (2, 2', 2''), comprising the following components: - a request interface unit (61) designed to provide request data (AD, ^^ ^ ^, ^̇) of the manufactured product (2, 2', 2''), - an optimization unit (65) designed to carry out an optimization method for determining the optimized process variable values ​​(PGO) taking into account the requirement data (AD, ^^ ^ ^ , ^̇), comprising at least one AI-based optimization unit (NN, NPS, NSV, NNW, KNSP, KNWS) to determine at least one optimized scan direction distribution (SSV) for at least one region of the manufactured product (2, 2', 2'') as an optimized process variable value (PGO), - a process variable value interface unit (64) designed to provide the optimized process variable values ​​(PGO).

15. Control data generation device (54, 54') for generating control data (BSD, PSD) for a production device (1) for the additive manufacturing of a manufactured product (2) in an additive build-up process, in which manufacturing process, preferably build-up material (13) is built up and selectively solidified, wherein, for solidification, the build-up material (13) is irradiated with at least one energy beam (E) on a build field (8), wherein an impact surface (22) of the energy beam (E) is moved on the build field (8) in order to melt the build material (13) in a target area in and around the impact surface (22), wherein the control data generation device (54,54') comprises at least the following components: - a device (60) according to claim 14 and / or an interface to a device (60) according to claim 14 for accepting optimized process variable values ​​(PGO), - a data generation unit for generating the control data (BSD, PSD) for the production device (1) such that the optimized process variable values ​​(PGO) are sufficiently achieved in the additive build-up process according to a predetermined evaluation criterion.

16. Control device (50) for a production device (1) for the additive manufacturing of a manufactured product (2) in an additive build-up process, wherein the control device (20) has a control data generation device (54) according to claim 15 and / or an interface to a control data generation device (54') according to claim 15 for accepting control data (BSD, PSD) and is designed to control the production device (1) using this control data (BSD,PSD).

17. Production device (1) for the additive manufacturing of manufactured products (2) in an additive construction process with at least one control device (50) according to claim 16.

18. Computer program product with a computer program which is directly stored in a memory device of a computer unit, in particular a device (60) for, Generation of optimized process variable values ​​(PGO), a control data generation device (54, 54') or a control device (50) for a production device (1) for the additive manufacturing of manufactured products (2), is loadable with program sections in order to carry out all steps of the method according to one of claims 1 to 13 when the computer program is executed in the computer unit.

19. Optimized process variable values ​​(PGO) for an additive construction process of a manufactured product (2, 2', 2''), which optimized process variable values ​​(PGO) were generated according to a method according to one of claims 1 to 10.

20. Control data (BSD, PSD) for a production device (1) for the additive manufacturing of at least one manufactured product (2, 2', 2'') in an additive construction process, which control data (BSD, PSD) were generated according to a method according to claim 11.

Images