METHOD FOR DETERMINING MECHANICAL CHARACTERISTICS OF ADDITIVELY MANUFACTURED COMPONENTS

Abstract

The invention relates to a method for determining mechanical properties of additively manufactured components, comprising the process steps of performing several additive manufacturing steps to produce a component, acquiring measurement data from the manufacturing process steps and / or acquiring the component parameters and determining the component properties, wherein an AI / ML function is applied to the acquired measurement data from the manufacturing process steps and / or the acquired component parameters to determine the component properties.

Description

[0001] The invention relates to a method for determining mechanical characteristics of additively manufactured components with the method steps of carrying out several additive manufacturing steps to produce a component, recording measurement data from process data of the manufacturing steps and / or recording the component parameters and determining component properties of the component, wherein an AI / ML function is applied to the recorded measurement data from process data of the manufacturing steps and / or the recorded component parameters to determine the component properties. State of the art

[0002] 3D printing or additive manufacturing is a comprehensive term for all manufacturing processes in which material is applied layer by layer to create three-dimensional components. The layer-by-layer build-up is computer-controlled from one or more liquid or solid materials according to specifications from a CAD / CAM system. The layers can then be broken down into strips, particularly in direct energy deposition processes. In addition, in a process known as hatching, a layer is divided into strips (hatches) or squares and parallel vectors are distributed within them. With powder bed-based technologies, such as selective laser melting, the component is manufactured without further subdivision of the layers. When the workpiece is built up layer by layer, a print head or a laser is usually moved horizontally, i.e. in the XY plane, and at the same time, strips of material are applied using the print head or laser.Once a layer is completed, the build plate on which the workpiece is being manufactured is usually moved vertically downwards, i.e. in the Z direction, and another layer is started. During the application or melting of the layers, the workpiece may experience problems such as cracking, deformation and an uneven crystal structure, depending on the type of material applied and the set process parameters (e.g. temperature, feed rate). In other cases, this can even lead to the entire manufacturing process having to be stopped. In the prior art, a process plan is usually created based only on the geometric design of a workpiece. If such a process plan is executed, it can lead to a phenomenon that a specific section of the workpiece becomes overheated during a manufacturing process, for example, and it becomes difficult to control the temperature of the workpiece effectively.In addition, the current state of the art in additive manufacturing makes it impossible to change and adapt the process plan, especially during the manufacturing process, once a process plan has been fully developed. Statements about the actual strengths and mechanical properties achieved are impossible.

[0003] It is therefore an object of the invention to provide an improved method for determining mechanical characteristics of additively manufactured components, with which manufacturing errors can be compensated during the implementation of the additive manufacturing process and statements can be made about the strengths and mechanical characteristics actually achieved.

[0004] This object is achieved by means of the method according to the invention for determining mechanical parameters of additively manufactured components. Advantageous embodiments of the invention are set forth in the subclaims.

[0005] The method according to the invention for determining mechanical parameters of additively manufactured components comprises three method steps: In the first method step, several additive manufacturing steps are carried out to produce a component. The techniques used by an additive manufacturer to produce a component include, for example, extrusion deposition or selective deposition modeling (SDM), techniques such as fused deposition modeling (FDM) and fused filament fabrication (FFF), granulate printing processes, stereolithography (SLA), polyjet printing (PJP), multijet printing (MJP), selective laser sintering (SLS), selective laser melting (SLM), three-dimensional printing (3DP), techniques such as inkjet printing (CJP), directed energy deposition (DED), and the like. A manufacturing step involves the additive manufacturing of a layer or a portion of a layer of a component.In this document, the terms "manufacturing step" and "process step" are used synonymously. During an additive manufacturing step, a part of the component is deposited and / or the previously manufactured part is added, and / or preparatory and / or post-processing steps, such as tempering or plasticizing the melt, are performed.

[0006] In the second process step, measurement data from the production steps of the sub-area and / or component data of the sub-area are collected. Process data includes, for example, data on the number of process steps, process temperature, the volume of material to be applied, the print weight, and / or the print volume. Component data for the component includes, for example, wall thicknesses, layer heights, component structure, deposition speed, print speed, and / or material-specific parameters.

[0007] The third step in the process involves determining the component's properties. These properties are determined from the recorded component data. Component properties include, for example, the component's strength and mechanical, thermal, and chemical properties. The mechanical properties of a component and their parameters play a crucial role in many applications. Mechanical properties include the strength of a material, its deformability, stiffness, and toughness. Mechanical properties determine how a component reacts when forces are applied to it; the mechanical parameters express the mechanical properties in comprehensible numerical values.

[0008] According to the invention, an AI / ML function is applied to the acquired measurement data from the process data of the manufacturing steps and / or the acquired component parameters to determine the component properties. The AI / ML function comprises AI / ML data that was determined using process data from the manufacturing steps and / or acquired component parameters of previously manufactured components. Typically, a neural network and / or an AI / ML function is trained using the determined process data from the manufacturing steps and / or acquired component parameters.

[0009] The method according to the invention is computer-aided, whereby the term "computer-aided" is used in this document, for example, to mean that one or more computers execute or execute at least one method step of the method. Computers can be, for example, personal computers, servers, handheld computer systems, pocket PC devices, mobile radio devices, and other communication devices that can process data in a computer-aided manner, as well as processors and other electronic devices for data processing, which can also be networked.

[0010] In a further development of the invention, the process data and / or the component parameters comprise physical and / or geometric parameters. The physical parameters include, for example, mechanical parameters such as strength and deformability, but also temperatures, pressure and humidity, vibrations, and / or material-specific characteristics. The geometric parameters include, for example, the spatial coordinates of the component. This ensures that the physical parameters are known for each spatial coordinate of the component.

[0011] In a further embodiment of the invention, spatial coordinates are partially assigned to the process data and / or component parameters. This means that the physical parameters for each assigned spatial coordinate of the component are known.

[0012] In a further embodiment of the invention, the component parameters include the general geometric shape and dimensions of the component and / or the printing materials. A geometric shape within the meaning of the invention is a spatial arrangement and includes properties such as angle, thickness, and structure of the component's structural design. Different printing materials require different layer structures to achieve specified physical parameters of the component.

[0013] In a further embodiment of the invention, the component parameters include the change in mass during the execution of the manufacturing steps. Detecting the change in the component's mass during manufacturing allows for an assessment of whether the layer currently being produced is being manufactured correctly. For example, an insufficient or excessive material volume during the layer application is detected.

[0014] In a further development of the invention, the mass of the component is determined by continuously measuring the mass of the component. In particular, this data acquisition takes place during the additive manufacturing process. The measured data includes, for example, melt temperatures during the discharge and processing processes, melt pressure during the discharge and processing processes, print speed and acceleration values ​​of the print head, general geometric shape and dimensions of the component, and vibration measurements.

[0015] In a further aspect of the invention, the mass and / or mass distribution is determined using a scale in the print bed and / or by 3D volume determination and / or mass flow determination. These methods enable in-situ measurement of the component's mass during the additive manufacturing process.

[0016] In a further embodiment of the invention, the process data includes the determined positioning accuracy in X, Y, and Z coordinates. The positioning accuracy includes, in particular, the current position of the print head during the additive manufacturing process. In a further development of the invention, the positioning accuracy is determined using linear displacement measurement systems.

[0017] In a further embodiment of the invention, the spacing of the melt strands and / or the compression of the melt strands and / or the layers is determined in all spatial directions during the manufacturing process. The spacing and compression of the melt strands and / or the layers determine the mechanical characteristics or physical parameters of the component.

[0018] In a further embodiment of the invention, the spacing of the melt strands and / or the compression of the melt strands are determined by measuring the 2D / 3D height difference before and after the deposition of a new layer. During the additive manufacturing process, the print head moves in two dimensions to deposit a horizontally arranged plane or layer at a time; the workpiece or the print head is then moved vertically by a small amount to begin a new layer. The amount of vertical movement is recorded to determine the spacing of the melt strands and / or the compression of the melt strands.

[0019] In a further embodiment of the invention, the height difference is determined taking into account the nozzle distance from the previous layer during the deposition process of the current layer and / or the measured mass flow and / or the viscosity and flow behavior. During the deposition process, the molten material is deposited at the target position on a build platform and / or component layer by an extrusion process in the build space.

[0020] In a further embodiment of the invention, the process data includes the positioning speeds, the acceleration of the print head, the printing speed, the mass flow of the extrusion process, the vibrations, and / or the pressure of the melt during the deposition of the melt strand. This process data is also optionally recorded continuously throughout the entire additive manufacturing process of the component.

[0021] In a further embodiment of the invention, the process data includes temperature. By recording the temperature and optionally by controlling the component temperature during the manufacturing process, optimal fusion of the layers is achieved.

[0022] In a further development of the invention, the temperatures include the temperatures of the printing material in its initial or stored state, the printing material in the zones of the plasticizing unit, the melt, the build space, the print bed and / or the component and / or the current layer during the process. The measurement is carried out continuously and / or at specified, discrete times. By continuously measuring the temperatures of the printing material and / or the melt in the plasticizing unit and evaluating the mass flow, the residence time of the melt in the plasticized state can be determined. By recording and controlling the temperatures (melt, build space and print bed temperatures) and optionally by component cooling, optimal layer fusion and strength in general are sought during the manufacturing process.

[0023] In an advantageous embodiment of the invention, the process data are determined during the application and / or preparation of printing material and / or melt. This ensures dimensional accuracy or a definable maximum deviation between the target and actual geometry. Preparation can include the plasticization and / or homogenization of the melt.

[0024] In a further embodiment of the invention, component properties are derived from the determined process and / or component parameters. The component parameters include physical and / or geometric parameters. The physical parameters include, for example, mechanical parameters such as strength and deformability, but also temperatures and / or material-specific characteristics. The geometric parameters include, for example, the spatial coordinates of the component. This ensures that the physical parameters are known for each spatial coordinate of the component.

[0025] In a further embodiment of the invention, the component properties include the adhesion between the individual printing layers and between the contact surfaces of the melt strands and / or layers in all spatial directions, mechanical properties, and strength. The derived component parameters provide comprehensive information regarding the produced component quality (dimensional accuracy, surface quality, and strength) and form the basis for simplified process certification.

[0026] In an advantageous embodiment of the invention, the AI / ML function applies AI / ML data to the determined process and / or component parameters. The AI / ML function uses algorithms designed to extract patterns and relationships from AI / ML data and derive predictions for new, unknown data. It is an iterative process in which the AI / ML function is continuously adapted and improved through repeated exposure to the AI / ML data.

[0027] In a further embodiment of the invention, the AI / ML data was determined before the start of component production. The AI / ML data therefore includes process and / or component parameters from previously manufactured components.

[0028] In a further embodiment of the invention, the AI / ML data was determined by determining process data and / or component parameters from the production of other components. The AI / ML data is optionally updated using recorded process and / or component parameters during additive manufacturing.

[0029] In a further embodiment of the invention, the AI / ML data were determined through reference measurements on components. The reference measurements comprise standardized, reproducible measurements on prototype printed components.

[0030] In a further embodiment of the invention, the reference measurements include tensile and / or compression tests of printed components. These tensile and / or compression tests allow conclusions to be drawn about the component quality (dimensional accuracy, surface quality, and strength) of the printed component, optionally with spatial resolution.

[0031] In a further embodiment of the invention, the reference measurements comprise process data from recorded components with different calibrations. The calibrations relate in particular to process data of the additive manufacturer, such as feed rate, temperature, pressure, etc.

[0032] In a further embodiment of the invention, a neural network is trained using the AI / ML data and / or an AI / ML function is used to apply the AI / ML function. Reinforced learning is optionally used, but unsupervised machine learning and supervised machine learning can also be used.

[0033] In a further embodiment of the invention, the application of the AI / ML function creates a correlation between the monitored process data and / or component parameters and the achieved strengths. For this purpose, the AI / ML data includes reference measurements from tensile and / or compression tests of printed components as well as calibration measurements of the achieved strengths.

[0034] In a further development of the invention, the component properties are determined in different spatial directions. In a further aspect of the invention, the component properties are determined in three or more spatial directions. The spatial resolution depends on the component itself and the quality to be achieved, and is adjustable.

[0035] In a further embodiment of the invention, measurement data of process parameters and / or component parameters are acquired during the execution of the manufacturing steps. A user can therefore determine whether the acquired measurement data matches the stored target data while the individual process steps of the additive manufacturing process are still being executed.

[0036] In an advantageous development of the invention, the acquisition of measurement data of process parameters and / or component parameters takes place continuously. In particular, the acquisition takes place during the additive manufacturing process. The measurement data includes, for example, temperatures and residence times of the melt during the discharge and preparation processes, component / layer temperatures, melt pressure during the discharge and preparation processes, print speed and acceleration values ​​of the print head, general geometric shape and dimensions of the component, and vibration measurements.

[0037] Embodiments of the method according to the invention are shown schematically in simplified form in the drawings and are explained in more detail in the following description.

[0038] They show: Fig. 1: Embodiment of the method according to the invention, correction code Fig. 2: Process steps of an embodiment of the method according to the invention Fig. 3: Process steps of an embodiment of the method according to the invention, determination and storage of characteristic values Fig. 4: Process steps of a further embodiment of the method according to the invention, determination and storage of characteristic values Fig. 5: Embodiment of the method according to the invention Fig. 6: Embodiment of the method according to the invention, implementation of process data and component data

[0039] Fig. Figure 1 shows an exemplary embodiment of the additive manufacturing of a component using the method 1 according to the invention. The starting point for implementing additive manufacturing is a description of the workpiece using a data set. Using 3D modeling software (e.g., a CAD program), the data set for the structural design of the component to be manufactured is created 100. The data set contains the three-dimensional data for processing for production using the additive manufacturing process.

[0040] Subsequently, preprocessing 110 takes place on the build platform in such a way that the data set comprises a volume model of the component to be manufactured and is exported in another form that represents the self-contained surface geometry of the object. A manufacturing data set is generated from the data set, which contains a preparation of the workpiece's geometry in layers or slices suitable for additive manufacturing. This data transformation is referred to as slicing 120.

[0041] In addition, the additive manufacturer requires additional process parameters and tool paths for production, e.g., the height of the layers to be produced, the orientation of the writing vectors, i.e., the direction and length of the path. These process parameters and tool paths are generated in the following process step 130 and sent to the additive manufacturer. The process parameters and tool paths with the component parameters are created to form the target parameter set of the component to be additively manufactured 10. In addition to these target process data, the created target parameter set contains data on the process temperature, the material volume to be dispensed, the print weight, and / or the print volume.

[0042] The actual manufacturing steps 140 then take place, beginning with the first manufacturing step. In each manufacturing step, a sub-area of ​​the layers of the component to be manufactured is produced. In this exemplary embodiment, the first two layers of the component are additively manufactured 150 according to the 10 process and component parameters stored in the target parameter set. The continuously recorded 23 measurement data of the actual process data and actual component data of the individual manufacturing steps are analyzed in-situ for each sub-area 24a, 24b (see Fig. 3, Fig. 4). The analysis 24a, 24b is performed separately for each layer, and an actual data set is created 20 and saved for each manufactured layer. Furthermore, a digital twin is created and saved 30 for each manufactured layer.

[0043] Analysis 24a, 24b of the 23 acquired measurement data for the first two layers reveals no deviation from the 10 process and component parameters stored in the target parameter set, or the deviation is within an adjustable tolerance. Additive manufacturing continues with the 10 process and component parameters stored in the target parameter set.

[0044] During production of the third layer, the analysis 24a, 24b shows that the tolerance for a deviation of the 23 recorded measurement data from the 10 process and component parameters stored in the target parameter set has been exceeded 160; the third layer has two defective sub-areas X with manufacturing defects. In this exemplary embodiment, the defective sub-areas X have too small a volume compared to the 10 process and component parameters stored in the target parameter set; the additive manufacturer has applied too little material. Complements for the two defective sub-areas X are determined, i.e., the missing volume is determined. From the complements, a correction code printable by the additive manufacturer is determined 32, which replaces the original print code when printing continues. Additive manufacturing is therefore continued with the correction code 170.The following layers have sub-areas C that are manufactured using the correction code 170, 180 and have a larger volume than if they were manufactured using the original print code. The recorded measurement data from all additively manufactured sub-areas and layers are combined and saved into an actual data set. Like the created target parameter set, the saved actual data set contains, in addition to the actual process data, data on the process temperature, the dispensed material volume, the print weight, and / or the print volume.

[0045] Fig. 2 shows an embodiment of process steps of the method 1 according to the invention. The method 1 begins with the reading in of 13 of the process steps, which are generated on the basis of the previously created 130 process parameters and tool paths (see Fig. 1). Starting with the first process step, a counter is set to 1 14 and the first process step is executed 140. During this manufacturing step, measurement data from the manufacturing step and the component parameters of the component are recorded 23. These recorded 23 measurement data are compared 24a with the stored 10 target data. For this purpose, the difference between the corresponding recorded 20 actual data and the stored 10 target data is calculated, in this embodiment, the difference between the applied and the material volume to be applied. For the comparison 24a, an AI / ML function is applied to the recorded 23 measurement data from the process data of the manufacturing steps and the recorded 23 component parameters. The AI / ML function applies AI / ML data to the determined 24a process and / or component parameters. The recorded 23 measurement data and the result of the comparison 24a are stored in an actual data set 30.

[0046] In one embodiment, the comparison 24a is displayed visually without any time delay. A user can therefore determine whether the 23 recorded measurement data match the 10 stored target data while the individual process steps 140 are still being executed.

[0047] After the comparison 24a, the analysis 24b follows, which determines whether the 23 actual data items recorded in this first process step match the 10 process and component parameters stored in the target parameter set for the first process step or whether they are within the adjustable tolerance. For analysis 24b, an AI / ML function is also applied to the 23 measured data items from the process data of the production steps and the 23 component parameters recorded.

[0048] A query A1 is then issued as to whether all process steps have been carried out. If this is not the case, a further query A2 is issued as to whether the tolerances of the component parameters of the component are maintained when continuing with the originally read-in 10 process steps. For this purpose, the results of the analyses 24a, 24b are evaluated. If this is the case (“Yes”), the 23 recorded measurement data are also saved 30 with the comparison 24a and the analysis 24b in an actual data set. If query A2 is negative (“No”), i.e. if the 23 actual data recorded in this first process step do not match the 10 process and component parameters stored for the first process step in the target parameter set or if their tolerance is exceeded, the complements are formed and the correction code for the following process steps is created 31. An AI / ML function is also applied to the 31 correction code to be created 31 to create the correction code.

[0049] For the comparison 24a, the analysis 24b, the query A2 and the creation 31 of the correction code, comparison data from previous additive manufacturing of components as well as reference measurements of components are applied 25. The reference measurements include tensile and compression tests of additively manufactured components as well as process data from recorded (stored) components with different calibrations.

[0050] Only then is the counter incremented by 1 (32) and the next (second) process step executed with the correction code (140). The process described here (1) continues until the counter indicates that all process steps have been executed, i.e., query A1 returns a "Yes." The actual data set and the target parameter set are then saved in a data set (30). This saved data set (30) is the so-called digital twin of the additively manufactured component. The process is terminated (200).

[0051] Fig. 3 shows a further embodiment of process steps of the method 1 according to the invention. In contrast to the previous embodiment (see Fig. 3) In this exemplary embodiment, after the adjustment 24a and the analysis 24b, a determination 24c of characteristic values, in particular mechanical values, of the component takes place. The determination 24c of characteristic values ​​takes place like the adjustment 24a and the analysis 24b of the 23 measured values ​​recorded for each process step during additive manufacturing. The mechanical properties of the component and their characteristic values ​​play a decisive role in the component's applications. The mechanical properties of the component include the strength of a material, its deformability, its stiffness, and its toughness. Mechanical properties determine how a component reacts when forces are exerted on it; the mechanical characteristics express the mechanical properties in comprehensible numerical values.

[0052] The 23 measured data provide the basis for deriving component properties, such as adhesion between the individual print layers and between the contact surfaces of the melt strands, predominantly based on 3D data, determined positioning accuracy in X, Y and Z coordinates (e.g. using linear position measuring systems), positioning speeds and accelerations when depositing the melt strand, mass flow of the extrusion process, continuous mass determination of the component (scale in the print bed and / or through 3D volume determination) temperatures (melt, build chamber and print bed temperatures as well as component temperature control in general) to ensure optimal fusion of the layers and strength in general. For optimal setting andIn addition to obtaining the listed parameters, additional reference measurements through tensile / compression tests on printed and process-recorded specimens with different calibrations can be used to select the process parameters. Depending on the material, optimal slicing or process parameters can be determined and continuously verified through monitoring (23, 24a, 24b, 24c).

[0053] For the comparison 24a, the analysis 24b, the determination 24c of characteristic values, and the query A2, an AI / ML function is applied as in the previous embodiment. The AI / ML function contains the AI / ML data that was determined before the start of component production. For the application 24a, 24b, 24c of the AI / ML function, a neural network was trained using the AI / ML data and / or an AI / ML function was used. The AI / ML data was created by determining process data and / or component parameters from the production of other components. Furthermore, the AI / ML data was determined through reference measurements on components already additively manufactured. The reference measurements include tensile and / or compression tests of additively printed components as well as process data from recorded components with different calibrations.

[0054] Fig. 4 shows a further embodiment of process steps of the method 1 according to the invention. In this embodiment, the 13 process steps of the component to be manufactured that have been read in are stored 30 as a target parameter set. In furthermore, this embodiment corresponds to the previous one (see Fig. 4). The application 24a, 24b, 24c of the AI / ML function creates a correlation between the monitored process data and / or component parameters and the achieved strengths.

[0055] Fig. 5 shows an embodiment of the method 1 according to the invention for determining mechanical characteristics of additively manufactured components. For this purpose, a target parameter set of a component to be additively manufactured is created 10. This target parameter set is saved and can be retrieved for additive manufacturing of the component. Furthermore, an actual data set is created 20 during the additive manufacturing process. For this purpose, measurement data is continuously recorded in situ 23 during the additive manufacturing process. The recorded 23 measurement data are summarized, and the actual data set is created 20 from the summarized measurement data. The actual data set and the target parameter set are saved in one data set 30. This saved 30 data set is the so-called digital twin of the additively manufactured component.

[0056] Fig. 6 shows a further embodiment of the method 1 according to the invention. Here, a target parameter set of the component to be additively manufactured is also created 10. In this embodiment, in addition to the above embodiment (see Fig. 5) Target process parameters and target component parameters are read in 11, 12. In particular, the target parameter set contains spatially high-resolution data on the target process data and target component data of the component. The resolution depends on the component to be additively manufactured. To create 20 the actual data set, actual process parameters and actual component parameters are also read in 21, 22, whereby the actual process parameters and actual component parameters are created based on the recorded 23 measurement data. The recorded 23 measurement data are summarized, and the actual data set is created from the summarized measurement data 20. The actual data set and the target parameter set are saved in a data set as a digital twin 30. LIST OF REFERENCE SYMBOLS 1 procedure 10 Create target parameter set 11 Reading target process parameters 12 Reading target component parameters 13 Reading process steps 14 Set counters 20 Create actual data record 21 Reading actual process parameters 22 Reading actual component parameters 23 Collect sensor data 24a Compare sensor data / calculate the difference between recorded actual data and target data 24b Analysis of whether the difference between actual data and target data is within the tolerance 24c Determination of the characteristic values 25 Reading comparison data / reference measurements 30 Create and save target parameter set and actual data set in one data set (digital twin) 31 Adjust process step / create correction code 32 Increase counter by 1 / next process step 100 Creation of the building structure 110 Preprocessing 120 slices 130 Generation of process parameters 140 Execute process step 150 actual parameters correspond to target parameters 160 Actual parameters do not correspond to target parameters 170 Continuation of the process steps using correction code 180 Process end with correction code 200 End of process A1 Query whether process finished / all process steps executed? A2 Query whether tolerances are achieved when continuing the original process steps A3 Query whether correction code is created C Parts produced using correction code X Faulty sub-areas

Claims

[1] Method (1) for determining mechanical characteristics of additively manufactured components with the following process steps: • Executing (140) several additive manufacturing steps to produce a component • Recording (23) of measurement data of process data of the manufacturing steps and / or recording of the component parameters, • Determining (24a, 24b, 24c) component properties of the component, wherein for determining (24a, 24b, 24c) the component properties an AI / ML function is applied to the recorded (23) measurement data of process data of the manufacturing steps and / or the recorded (23) component parameters. [2] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 1, characterized by that the process data and / or the component parameters include physical and / or geometric parameters. [3] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 1 or 2, characterized by that spatial coordinates are partially assigned to the process data and / or component parameters. [4] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the part parameters include the general geometric shape and dimensions of the part and / or the printing materials. [5] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the component parameters include the change in mass during the execution of the manufacturing steps. [6] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 5, characterized bythat the mass of the component is determined by a continuous mass determination of the component. [7] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 6, characterized by that the mass is determined using a scale in the print bed and / or by 3D volume determination and / or mass flow determination. [8] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the process data includes the determined positioning accuracy in X, Y and Z coordinates. [9] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 6, characterized by that the positioning accuracy is determined by linear position measuring systems. [10] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the distance between the melt strands and / or the pressing of the melt strands and / or the layers is determined in all spatial directions during the manufacturing process. [11] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 10, characterized by that the spacing of the melt strands and / or the pressing of the melt strands are determined by measuring the 2D / 3D height difference before and after the application of a new layer. [12] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 10, characterized bythat the height difference is determined taking into account the nozzle distance from the previous layer during the deposition process of the current layer and / or the measured mass flow and / or the viscosity and flow behavior. [13] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the process data include the positioning speeds, the acceleration of the print head, the printing speed, the mass flow of the extrusion process, the vibrations and / or the pressure of melt when depositing the melt strand. [14] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the process data includes temperature. [15] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 10, characterized by that the temperatures include the temperatures of the printing material, the melt, the build space, the print bed and / or the component and / or the top layer during the process. [16] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the process data are determined during application and / or processing (23). [17] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that component properties are derived (24a, 24b, 24c) from the determined (23) process and / or component parameters. [18] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 17, characterized by that the component properties include the adhesion between the individual printing layers and between the contact surfaces of the melt strands and / or layers in all spatial directions, mechanical properties and strength. [19] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the AI / ML function applies AI / ML data to the determined (24a, 24b, 24c) process and / or component parameters. [20] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 19, characterized by that the AI / ML data was collected before the component began to be manufactured. [21] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 20, characterized by that the AI / ML data was obtained by determining process data and / or component parameters from the production of other components. [22] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 21, characterized by that the AI / ML data was determined through reference measurements on components. [23] Method for determining mechanical characteristics of additively manufactured components according to claim 22, characterized by that the reference measurements include tensile and / or compression tests of printed components. [24] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 22 or 23, characterized by that the reference measurements include process data from recorded components with different calibrations. [25] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that for the application (24a, 24b, 24c) of the AI / ML function trained using AI / ML data. [26] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 25, characterized by that the application (24a, 24b, 24c) of the AI / ML function creates a correlation between the monitored process data and / or component parameters and the achieved strengths. [27] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the component properties are determined in different spatial directions. [28] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 27, characterized bythat the component properties are determined in three spatial directions. [29] Method (1) for determining mechanical characteristics of additively manufactured components according to one or more of the preceding claims, characterized by that the acquisition (23) of measurement data of process parameters and / or component parameters takes place during the execution (140) of the manufacturing steps. [30] Method (1) for determining mechanical characteristics of additively manufactured components according to claim 27, characterized by that the recording (23) of measurement data of process parameters and / or component parameters takes place continuously.

Images