System for optimizing an additive manufacturing process and method thereof

Abstract

The present invention relates to a system for optimizing the additive manufacturing of an object performed by an additive manufacturing device, comprising: a data acquisition module, configured to obtain data of the additive manufacturing process of the object; a simulation module, configured to run a process simulation that simulates the additive manufacturing process of the object based on the obtained data; an instruction generation module, configured to provide process instructions corresponding to the process simulation for the additive manufacturing device to perform the additive manufacturing process; a monitoring module, configured to compare the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N-1 time point; and a control module, configured to prompt the simulation module, on the basis of a result of the comparison performed by the monitoring module, to run a new process simulation based on the data obtained at the N time point.

Description

[0001] Description

[0002] System for optimi zing an additive manufacturing process and method thereof

[0003] The present invention relates to a system for optimi zing the additive manufacturing of an obj ect . The invention further relates to a corresponding method, an additive manufacturing system, a computer program product and a non-transient computer-readable data storage medium .

[0004] The invention is mostly described with respect to a laser powder bed fusion process but the principles of the invention have a broader scope and apply equally well to other additive manufacturing processes .

[0005] Herein and in the forthcoming, independent of the grammatical term usage , individuals with male , female or other gender identities are included within the term .

[0006] Additive manufacturing processes ( or 3D printing processes ) comprise a wide variety of techniques through which obj ects can be produced by a manufacturing device programmed to follow instructions based on a three-dimensional digital model . The manufacturing device fabricates an obj ect through the addition of material , commonly in the form of layers , on which materials are deposited and added to previously finished layers . Depending on how the layers are added together ( for example by melting or sintering the material ) di f ferent additive manufacturing methods have been devised .

[0007] A challenge common to all the additive manufacturing methods is to keep the inaccuracies under tolerance values , in order to ful fil target quality standards . Inaccuracies are particularly concerning in manufacturing processes at a macro and meso-scale levels . When inaccuracies during the fabrication of an obj ect are above tolerance thresholds , it might be necessary to plan for a post-production stage , where adj ustments are introduced . This not only increases the downtime of the additive manufacturing device , but it entails additional costs .

[0008] Against this background, a problem addressed by the present invention is to provide solutions aiming at eliminating or at least reducing the post-processing stages .

[0009] This problem is solved according to the invention by a system having the features of claim 1 and / or by a computer- implemented method having the features of claim 11 and / or by a computer program product having the features of claim 12 and / or by a non-transient computer-readable data storage medium having the features of claim 13 .

[0010] A first aspect of the invention provides a system for optimi zing the additive manufacturing of an obj ect performed by an additive manufacturing device , comprising : a data acquisition module , configured to obtain data of the additive manufacturing process of the obj ect ; a simulation module , configured to run a process simulation that simulates the additive manufacturing process of the obj ect based on the obtained data ; an instruction generation module , configured to provide process instructions corresponding to the process simulation for the additive manufacturing device to perform the additive manufacturing process ; a monitoring module , configured to compare the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N- l time point ; and a control module , configured to prompt the simulation module , on the basis of a result of the comparison performed by the monitoring module , to run a new process simulation based on the data obtained at the N time point . The system of the invention thus plans and monitors the additive manufacturing process , detects inaccuracies in real time as the additive manufacturing process is performed, and provides the necessary adj ustments . An additive manuf cturing device can be any device adapted to perform an additive manufacturing process in any of its variants . Additive manufacturing devices can comprise conventional 3D printers .

[0011] The data obtained by the system can comprise measured values by sensors , e . g . temperature sensors or sensors adapted to measure the mechanical properties of an obj ect . The data can further comprise metadata about the manufacturing process , which can be provided by a user or acquired from the additive manufacturing machine . The data can be in the form of image data or text data .

[0012] In the present invention, a process simulation is to be understood as a software application, which can be based on a model comprising physical characteristics of the obj ect to be manufactured and / or the additive manufacturing device . The software application can contain an algorithm, configured to find solutions to the model .

[0013] Process instructions comprise information about the configuration settings of the additive manufacturing device in order to perform the additive manufacturing process following a process simulation . Process instructions can include adj ustments of relevant parameters for the performance of the additive manufacturing process , such as the power and / or the scanning speed of the additive manufacturing device .

[0014] The di f ferent modules and units mentioned in this application are broadly understood as entities capable of acquiring, obtaining, receiving or retrieving generic data and / or instructions through a user interface and / or programming code and / or executable programs or any combination thereof . In particular, the computing module , the application module and the di f ferent units mentioned hereafter are adapted to run programming code and executable programs and to deliver the results for further processing . The different modules and units mentioned hereafter, or parts thereof, may therefore each contain, at least, a central processing unit, CPU, and / or at least one graphics processing unit, GPU, and / or at least one field-programmable gate array, FPGA, and / or at least one application-specific integrated circuit, ASIC and / or any combination of the foregoing. Each of them may further comprise a working memory operatively connected to the at least one CPU and / or a non-transitory memory operatively connected to the at least one CPU and / or the working memory.

[0015] All the parts of the system of the invention may be realized in hardware and / or software, cable-bound and / or wireless, and in any combination thereof. Any of the parts of the system may comprise an interface to an intranet or the Internet, to a cloud computing service, to a remote server and / or the like .

[0016] In particular, each of the modules and units of the system, or the system as a whole, may be implemented partially and / or completely in a local apparatus, e.g. a computer, in a system of computers and / or partially and / or completely in a remote system, in particular in an edge or cloud computing platform.

[0017] In systems based on cloud computing technology, a large number of devices is connected to a cloud computing system via the Internet. The devices may be located in a remote facility connected to the cloud computing system. For example, the devices can comprise, or consist of, equipment, sensors, actuators, robots, and / or machinery in an industrial set-up (s) .

[0018] The devices can be medical devices and equipment in a healthcare unit. The devices can be home appliances or office appliances in a residential / commercial establishment.

[0019] The cloud computing system may enable remote configuring, monitoring, controlling, and maintaining connected devices (also commonly known as 'assets' ) . Also, the cloud computing system may facilitate storing large amounts of data period!- cally gathered from the devices , analyzing the large amounts of data, and providing insights ( e . g . , Key Performance Indicators , Outliers ) and alerts to operators , field engineers or owners of the devices via a graphical user interface ( e . g . , of web applications ) . The insights and alerts may enable controlling and maintaining the devices , leading to ef ficient and fail-safe operation of the devices . The cloud computing system may also enable modi fying parameters associated with the devices and issues control commands via the graphical user interface based on the insights and alerts .

[0020] The cloud computing system may comprise a plurality of servers or processors ( also known as ' cloud infrastructure ' ) , which are geographically distributed and connected to each other via a network . A dedicated platform (hereinafter referred to as ' cloud computing platform' ) is installed on the servers / processors for providing above functionality as a service (hereinafter referred to as ' cloud service ' ) . The cloud computing platform may comprise a plurality of software programs executed on one or more servers or processors of the cloud computing system to enable delivery of the requested service to the devices and its users .

[0021] One or more application programming interfaces (API s ) are deployed in the cloud computing system to deliver various cloud services to the users .

[0022] A second aspect of the present invention provides a computer- implemented method for optimi zing an additive manufacturing process of an obj ect performed by an additive manufacturing device , comprising the following steps : obtaining data of the additive manufacturing process of the obj ect ; running a process simulation based on the obtained data ; providing process instructions to the additive manufacturing device based on the process simulation; performing the additive manufacturing process , based on the generated process instructions ; monitoring the performing of the additive manufacturing process with the obtention of data at di f ferent time points ; compar- ing the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N- l time point ; and deciding on continuing the monitoring of the additive manufacturing process or adj usting the additive manufacturing, wherein adj usting the additive manufacturing comprises : running a new process simulation based on the data obtained at the N time point ; providing new process instructions based on the new process simulation; and performing the additive manufacturing, based on the generated new process instructions .

[0023] In particular, the method according to the second aspect of the invention may be carried out by the system according to the first aspect of the invention . The features and advantages disclosed herein in connection with the computing device are therefore also disclosed for the method, and vice versa .

[0024] According to a third aspect , the invention provides a computer program product comprising executable program code configured to , when executed, perform the following steps : obtaining data of the additive manufacturing process of the obj ect ; running a process simulation based on the obtained data ; providing process instructions to the additive manufacturing device based on the process simulation; monitoring the performing of the additive manufacturing process with the obten- tion of data at di f ferent time points ; comparing the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N- l time point ; and deciding on continuing the monitoring of the additive manufacturing process or adj usting the additive manufacturing, wherein adj usting the additive manufacturing comprises : running a new process simulation based on the data obtained at the N time point ; and providing new process instructions based on the new process simulation .

[0025] According to a fourth aspect , the invention provides a nontransient computer-readable data storage medium comprising executable program code configured to , when executed, perform the following steps : obtaining data of the additive manufacturing process of the obj ect ; running a process simulation based on the obtained data ; providing process instructions to the additive manufacturing device based on the process simulation; monitoring the performing of the additive manufacturing process with the obtention of data at di f ferent time points ; comparing the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N- l time point ; and deciding on continuing the monitoring of the additive manufacturing process or adj usting the additive manufacturing, wherein adj usting the additive manufacturing comprises : running a new process simulation based on the data obtained at the N time point ; and providing new process instructions based on the new process simulation .

[0026] The non-transient computer-readable data storage medium may comprise , or consist of , any type of computer memory, in particular semiconductor memory such as a solid-state memory . The data storage medium may also comprise , or consist of , a hard disk drive , a CD, a DVD, a Blu-Ray-Disc, an USB memory stick or the like .

[0027] According to a fi fth aspect , the invention provides a data stream comprising, or configured to generate , executable program code configured to , when executed, perform the following steps : obtaining data of the additive manufacturing process of the obj ect ; running a process simulation based on the obtained data ; providing process instructions to the additive manufacturing device based on the process simulation; monitoring the performing of the additive manufacturing process with the obtaining of data at di f ferent time points ; comparing the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N- l time point ; and deciding on continuing the monitoring of the additive manufacturing process or adj usting the additive manufacturing, wherein adj usting the additive manuf cturing comprises : running a new process simulation based on the data obtained at the N time point ; and providing new process instructions based on the new process simulation .

[0028] According to a sixth aspect , the invention provides an additive manufacturing system with an additive manufacturing device and a system according to the first aspect of the present invention, wherein the additive manufacturing device is configured to perform an additive manufacturing process of an obj ect , and wherein the system according to the first aspect of the present invention is configured to provide process instructions for the additive manufacturing device to perform the additive manufacturing process .

[0029] The system according to the first aspect of the invention can be provided as an application program interface (API ) to the additive manufacturing device .

[0030] One of the main finding of the present invention is to provide a system that is capable to adj ust an additive manufacturing process in real time and to detect departures from a manufacturing plan scheduled with the help of a process simulation . This is achieved by a combination of a monitoring module , configured to compare sets of data obtained at di fferent times , and a simulation module , configured to generate , on demand, new process simulations when the comparison shows deviations , e . g . beyond a certain threshold for the parameters . The interaction of the monitoring module and the simulation module is controlled by a control module , such that an updated process simulation can be provided as the additive manufacturing process progresses . An instruction generation module produces for each process simulation a set of process instructions to be provided to the additive manufacturing device to modi fy the manufacturing strategy on the fly, which means , i . e . immediately and / or instantly as the additive manufacturing process progresses . The system as described above allows for a simple implementation of a computer-implemented method comprising a number of steps . Initially, data regarding the striven additive manufacturing is obtained and therewith an initial process simulation is generated, which is set as a reference for the additive manufacturing process to be performed . The manufacturing process is started and continuously monitored, gathering information on parameters that enter the process simulation, e . g . through the measurement of local temperature and mechanical properties of the obj ect . I f a departure above some tolerance is detected, a new simulation process is generated, which takes into account the discrepancies found and issues an alternative schedule for the additive manufacturing process , aimed at eliminating or at least minimi zing issues that would require a post-processing of the obj ect .

[0031] One advantage of the present invention is that it provides a system and method to adj ust the additive manufacturing of an obj ect on the fly, i . e . as the additive manufacturing process progresses . This continuous adj ustment can reduce or even eliminate the need for a post-processing step and leads to a most ef ficient additive manufacturing .

[0032] A further advantage of the present invention is that the system and method are applicable regardless of the particular additive manufacturing variant or category . The scope of the invention is applicable to , e . g . processes based on material j etting, material extrusion or powder bed fusion .

[0033] Advantageous embodiments and further developments follow from the dependent claims as well as from the description of the di f ferent preferred embodiments illustrated in the accompanying figures .

[0034] According to some embodiments , refinements , or variants of embodiments , the additive manufacturing comprises a powder bed fusion process , preferably a laser powder bed fusion process . In laser powder bed fusion an obj ect is manufactured by a selective melting of the material with a directed laser beam . This additive manufacturing process is especially suited for the production of geometrically complex structures , since the layer thickness is very thin, typically of the order of 10 to 200 micrometers .

[0035] The potential of laser powder bed fusion to achieve high detail resolution makes the present invention especially advantageous when applied in combination with this process .

[0036] According to some embodiments , refinements , or variants of embodiments , the process simulation is a thermo-mechanical simulation, wherein the obtained data comprises an information about the materials to be used for the additive manufacturing process and information about the geometric structure of the obj ect . I f the process simulation is based on some thermo-mechanical model , a better control of the temperature and deformation of the obj ect as the additive manufacturing is performed can be achieved . Temperature and mechanical properties can be acquired as a function of time . When combined with an information about the material or materials to be used and the geometric structure of the obj ect , a success ful process simulation can thus be generated . For instance , in geometric points of the obj ect with fewer layers , such as spiky edges or thin and elongated structures , the risk of overheating or mechanical deformation can be high . A process simulation which includes thermo-mechanical information can make sure that the steering power ( e . g . a laser power ) , when going through these areas , is accordingly adj usted .

[0037] According to some embodiments , refinements , or variants of embodiments , the simulation module is further configured to run the process simulation based on a scanning strategy, wherein the scanning strategy comprises adj usting a scanning speed and / or a steering power of the additive manufacturing device , and / or adj usting the hold time of single melt events comprised in the scanning path . The scanning strategy influences to a large extend the temperature that the material reaches when building a new layer and thus has an impact on the mechanical properties that the obj ect acquires . The process simulation can modi fy the scanning speed and the applied power of the additive manufacturing device to modi fy the thermo-mechanical properties of the manufactured obj ect . Additionally, the scanning path can be modi fied through a redefinition of the single melt events ( also referred to as melt tracks or also called vectors ) , which define the scanning path . This modi fication can comprise a rerouting and / or a change in the length of the vectors .

[0038] According to some embodiments , refinements , or variants of embodiments , the process simulation is further based on a support structure strategy . This is especially advantageous when the thermo-mechanical parameters cannot be adj usted with a scanning strategy alone and as a result overheating or deformation might appear . In this case , the process simulation can also incorporate elements to modi fy the initial build strategy, for instance by determining build support structures to be assigned to forthcoming layers . Additionally, the support structure strategy can also comprise the assignment of build support structures to be applied during a postprocessing stage . The process simulation can be further configured to optimi ze the build modi fications introduced by the adj ustments in the support structure strategy by taking into account the whole layers , such that the post-processing stage can be reduced to a bare minimum . In other words , the support structure strategy can be applied most advantageously by taking into account the obj ect as a whole .

[0039] According to some embodiments , refinements , or variants of embodiments , the system further comprises a structure evaluation module , configured to identi fy surfaces of the obj ect during the additive manufacturing process where support structures could be implemented . This identi fication can com- prise an identi fication of critical structures , which can be performed based on the thermo-mechanical information obtained by the monitoring module . The information gathered by the structure evaluation module can be advantageously combined as part of the support structure strategy . The structure evaluation module can be in operation during the whole additive manufacturing of the obj ect and can be continuously updated .

[0040] According to some embodiments , refinements , or variants of embodiments , the simulation module comprises a machinelearning unit , which is configured to implement a simulation algorithm based on a machine-learning model , trained and adapted to generate a process simulation .

[0041] Herein and in the forthcoming, a machine-learning model refers in particular to an arti ficial neural network ( or encoder ) , which is to be understood as a computing system based on a collection of connected units or nodes aggregated into layers able to transmit signals to each other, preferably comprising at least partially a trans former neural network architecture . According to some embodiments , refinements , or variants of embodiments , the architecture of the arti ficial neural network or parts thereof is implemented in a server or a cloud computing platform, from where it can be integrated as a pre-trained part of other neural network architectures .

[0042] The simulation algorithm is preferably trained using a supervised approach . To this end, a training dataset can comprise data from previously completed additive manufacturing processes , and also data from synthetically generated simulations using a thermo-mechanical model . In some embodiments of the invention this can be achieved with the implementation of a sampling module , configured to sample varying geometries for an obj ect from a statistical shape model . From the set of geometries , simulations can be performed with di f ferent sets of initial calibration data, e . g . regarding scanning speed and steering power of an additive manufacturing device . This set of reference simulations can be generated with conven- tional methods , where the material of the obj ects can be additionally varied .

[0043] In some embodiments of the invention, the machine-learning unit is further configured to optimi ze the simulation algorithm .

[0044] According to some embodiments , refinements , or variants of embodiments , the monitoring module is further configured to make the comparison based on multiple layers of the additive manufacturing process . In these embodiments , data from the di f ferent layers is collected . Including more than one layer in the comparison enables a more global and encompassing comparison . Accordingly, extending the comparison to a certain number of layers results in a more accurate evaluation of the additive manufacturing process .

[0045] According to some embodiments , refinements , or variants of embodiments , the system of the invention further comprises a digital twin generation module , configured to generate , based on the process simulation generated by the simulation module , a digital twin of production corresponding to the additive manufacturing of the obj ect .

[0046] A so-called digital twin is a digital representation of a tangible or intangible obj ect , product or system of obj ects or products from the real world in the digital world . It is irrelevant whether the counterpart already exists in the real world or will exist in the future . Digital twins enable an overlapping exchange of data . They are more than j ust data and consist of models of the represented obj ect and can also contain simulations , algorithms and services that describe or influence the properties or behavior of the represented obj ect or of fer services about it . As such, digital twins can replicate the characteristics of obj ects , products and systems and map them on a digital platform, thereby being able to simulate their behaviour under di f ferent conditions . A digital twin in the industrial environment is a real-time digital replica of all or some of the characteristics of a physical product , obj ect or system of products . The main advantage of digital twins is that they can simulate scenarios in advance and thus provide advisory features and support for an informed decision-making . In particular, digital twins may enable an inspection of the present condition of a physical product , the simulation of what-i f scenarios , and thereby the prevention of future setbacks .

[0047] Through the generation of a digital twin based on a generated process simulation, a user has an additional tool to anticipate inaccuracies when the additive manufacturing process is performed under the settings resulting from the process simulation . In some preferred embodiments , the system of the invention further comprises a user interface , configured to allow a user to monitor the digital twin and validate or overwrite the corresponding process simulation .

[0048] The digital twin generation module can comprise an arti ficial intelligence unit , which is configured to implement an artificial neural network, trained and adapted to generate a digital twin of production based on a given process simulation generated by the simulation module .

[0049] According to some embodiments , refinements , or variants of embodiments , the process instructions comprise information for multiple layers of the additive manufacturing process . Process instructions are thus not limited to one layer ( the forthcoming layer for the additive manufacturing process ) , and accordingly do not need to be communicated layer by layer, but they can encompass either a limited number of layers to be deposited on top of the current layer, or the whole set of layers of the build j ob . Providing process instructions to the additive manufacturing device for all the future layers , i . e . in order to bring the build j ob to completion, can be advantageous in order to reduce the frequency of communication between the system and the additive manufacturing device . In these embodiments , communication with the additive manufacturing device is established only after a comparison falls out of tolerance values . The process simulation generated by the simulation module typically comprises the whole additive manufacturing process , and thus the process instructions per layer can be extracted therefrom for the whole set of layers .

[0050] According to some embodiments , refinements , or variants of embodiments , the system further comprises a database module , configured to store the obtained data and the process simulations . The storage of information is advantageous not only for data traceability and for ful filling protocol requirements , but also as a repository of training datasets , e . g . for the training of simulation algorithms of di f ferent systems according to the embodiments of the invention .

[0051] Although here , in the foregoing and also in the following, some functions are described as being performed by modules or units , it shall be understood that this does not necessarily mean that such modules or units are provided as entities separate from one another . In cases where one or more modules or units are provided as software , the modules or units may be implemented by program code sections or program code snippets , which may be distinct from one another but which may also be interwoven or integrated into one another .

[0052] Similarly, in cases where one or more modules or units are provided as hardware , the functions of one or more modules or units may be provided by one and the same hardware component , or the functions of several modules or units may be distributed over several hardware components , which need not necessarily correspond to the modules or units . Thus , any apparatus , system, method and so on which exhibits all of the features and functions ascribed to a speci fic module or unit shall be understood to comprise , or implement , said module or said unit . In particular, it is a possibility that all modules or units are implemented by program code executed by the computing device , for example a server or a cloud computing platform .

[0053] Where appropriate , the above-mentioned configurations and developments can be combined implementations can be combined with each other as desired, as far as this is reasonable .

[0054] Further possible configurations , developments and implementations of the invention also include combinations , which are not explicitly mentioned, of features of the invention which have been described previously or are described in the following with reference to the embodiments . In particular, in this case , a person skilled in the art will also add individual aspects as improvements or supplements to the basic form of the present invention .

[0055] The present invention is described in greater detail in the following on the basis of the embodiments shown in the schematic figures of the drawings , in which :

[0056] Fig . 1 is a schematic depiction of a system for optimi zing the additive manufacturing of an obj ect performed by an additive manufacturing device according to an embodiment of the present invention;

[0057] Fig . 2 is a block diagram showing an exemplary embodiment of a computer-implemented method for optimi zing the additive manufacturing of an obj ect performed by an additive manufacturing device according to an embodiment of the present invention;

[0058] Fig . 3 is a schematic diagram showing an example of a support structure strategy according to an embodiment of the present invention;

[0059] Fig . 4 is a schematic illustration of an additive manufacturing system comprising an additive manufacturing device and the system of the invention; Fig . 5 is a schematic block diagram illustrating a computer program product according to an embodiment of the third aspect of the present invention; and

[0060] Fig . 6 is a schematic block diagram illustrating a non- transitory computer-readable data storage medium according to an embodiment of the fourth aspect of the present invention .

[0061] The appended drawings are intended to provide further understanding of the embodiments of the invention . They illustrate embodiments and, in conj unction with the description, help to explain principles and concepts of the invention . Other embodiments and many of the advantages mentioned become apparent in view of the drawings . The elements in the drawings are not necessarily shown to scale .

[0062] In the drawings , like , functionally equivalent and identically operating elements , features and components are provided with like reference signs in each case , unless stated otherwise .

[0063] The numeration of the steps in the methods are meant to ease their description . They do not necessarily imply a certain ordering of the steps . In particular, several steps may be performed concurrently .

[0064] The detailed description includes speci fic details for the purpose of providing a thorough understanding of the present invention . However, it will be apparent to those skilled in the art that the present invention may be practised without these speci fic details .

[0065] Fig . 1 shows a schematic depiction of a system for optimi zing the additive manufacturing of an obj ect P performed by an additive manufacturing device AMD according to an embodiment of the present invention . The system 100 depicted in Fig . 1 comprises a data acquisition module 10 , a simulation module 20 , an instruction generation module 30 , a monitoring module 40 , a control module 50 , a structure evaluation module 60 , a digital twin generation module 70 and a database module 80 .

[0066] The data acquisition module 10 is configured to obtain data of the additive manufacturing process of the obj ect P . This data can comprise at least a description of the manufacturing process to be performed by the additive manufacturing device AMD . Some calibration data can also be provided, for instance regarding the characteristics of the additive manufacturing device AMD, or regarding the thermo-mechanical characteristics of the obj ect P to be manufactured . The data obtained by the data acquisition module 10 may comprise measurement data points of temperature and mechanical deformation of di f ferent parts of the obj ect P under construction as a function of time . It can also comprise information about the material or materials to be used for the manufacturing of the obj ect P and the geometric characteristics of the obj ect P .

[0067] The data acquisition module 10 can be any device capable of receiving and processing di f ferent data types , such as the ones detailed above . In preferred embodiments , the input data interface 10 can be connected to the additive manufacturing device AMD and / or to a set of sensors ( e . g . temperature or stress sensors ) , wired or wireless or with a combination thereof .

[0068] The simulation module 20 is configured to run a process simulation that simulates the additive manufacturing process of the obj ect P based on the data obtained by the data acquisition module 10 . The simulation module 20 is designed to generate process simulations on demand . In particular, it can generate an initial process simulation, which is run on calibration data ( including, e . g . , information about the material or materials to be used for the manufacturing of the obj ect P, the geometric characteristics of the obj ect P, the power and scanning speed of the additive manufacturing device AMD, etc . ) . This initial process simulation can be used to schedule the additive manufacturing process .

[0069] In the embodiment shown in Fig . 1 , the simulation module 20 comprises a machine-learning unit 210 , configured to implement a simulation algorithm based on a machine-learning model , trained and adapted to generate the process simulation . An arti ficial neural network can comprise a deep learning model adapted to implement di f ferent data analysis methods , in particular those comprising a trans former neural network architecture .

[0070] The simulation algorithm can be trained using a training dataset comprising data from previously completed additive manufacturing processes , or data from synthetically generated simulations using a thermo-mechanical model , e . g . the one used to generate the process simulations .

[0071] In some embodiments of the invention, the machine-learning unit 210 is further configured to optimi ze the simulation algorithm .

[0072] The instruction generation module 30 is configured to provide process instructions corresponding to a process simulation to the additive manufacturing device AMD for it to perform the additive manufacturing process . Process instructions comprise information about the configuration settings of the additive manufacturing device AMD in order to perform the additive manufacturing process following a process simulation . Process instructions can include adj ustments of relevant parameters for the performance of the additive manufacturing process , such as the power and / or the scanning speed of the additive manufacturing device AMD . The process instructions can comprise information for the manufacturing of multiple layers of the additive manufacturing process , either for a limited number of layers to be deposited on top of the current layer, or fer the whole set of layers of the build j ob . The process instructions can be communicated as a signal , including an executable file in a machine readable format that can be read, processed and executed by the operation software of the additive manufacturing device AMD .

[0073] The monitoring module 40 is configured to continuously monitor the additive manufacturing process . This is achieved by acquiring data from the additive manufacturing process ( e . g . temperature and mechanical properties of the obj ect P measured with a number of sensors ) and comparing it with the data obtained at a previous time point . The comparison can consist of di f ferent ways of identi fying discrepancies or deviations in a number of monitoring parameters , e . g . the temperature distribution or the geometric accuracy . This can be determined i f those monitoring parameters fall out the tolerances defined by certain thresholds for the parameters . In some embodiments of the invention the comparison takes into account information on more than one layer of the additive manufacturing process . In these embodiments , data from di f ferent layers is collected .

[0074] The control module 50 is configured to prompt the simulation module 20 , on the basis of the outcome of the comparison performed by the monitoring module 40 , to run a new process simulation based on the obtained data at a certain time point . The interaction of the monitoring module 40 and the simulation module 20 is thus coordinated, mediated and controlled by the control module 50 .

[0075] In some embodiment of the invention, such as the one depicted in Fig . 1 , the system comprises a structure evaluation module 60 , which is configured to identi fy surfaces of the obj ect P during the additive manufacturing process where support structures could be implemented . The process simulation and the determination of the relevant parameters for the additive manufacturing device AMD to perform the manufacturing of an obj ect P is mostly based on a scanning strategy . In some in stances , a variation of the parameters related to the scanning strategy cannot bring them within the tolerance limits . In these cases , the process simulation can be further based on a support structure strategy, which incorporate elements to modi fy the initial build strategy . In this respect , the structure evaluation module 60 can provide an identi fication of critical structures , which can be performed based on the thermo-mechanical information obtained by the monitoring module 40 . This identi fication can then be combined as part of the support structure strategy, and is instrumental to determine , e . g . build support structures to be assigned to forthcoming layers of the additive manufacturing process , or in the given case , build support structures to be applied during a post-processing stage to previously built layers . The structure evaluation module 60 can be in operation during the whole additive manufacturing of the obj ect P and can be continuously updated .

[0076] The embodiment illustrated in Fig . 1 also comprises a digital twin generation module 70 . The digital twin generation module 70 is configured to generate , based on the process simulation generated by the simulation module 20 , a digital twin of production corresponding to the additive manufacturing of the obj ect P . Through the generation of a digital twin based on a generated process simulation, a user has an additional tool to anticipate inaccuracies when the additive manufacturing process is performed under the settings resulting from a process simulation . In some preferred embodiments , the system of the invention further comprises a user interface , configured to allow a user to monitor the digital twin and validate or overwrite the corresponding process simulation .

[0077] The digital twin generation module 70 can comprise an arti ficial intelligence unit (not shown) , which is configured to implement an arti ficial neural network, trained and adapted to generate a digital twin of production based on a given process simulation generated by the simulation module 20 . Fig. 1 additionally shows a database module 80, which is configured to store the obtained data at different times and the process simulations that are generated by the simulation module 20. The database module 80 provides storage for data in order to fulfill traceability and other protocol requirements. The database module 80 can also be deployed as a repository of training datasets, e.g. for the training of simulation algorithms as the ones described according to some embodiments of the invention.

[0078] Fig. 2 is a block diagram showing an exemplary embodiment of a computer-implemented method for optimizing the additive manufacturing of an object P performed by an additive manufacturing device according to an embodiment of the present invention. The method can be preferably implemented with the computing system 100 described with respect to Fig. 1. The method comprises a number of steps.

[0079] In a step SI, data of the additive manufacturing process of the object P is obtained. This data can comprise meta-data about the process, e.g. about the material or materials to be used for the additive manufacturing process, or geometric data about the object P to be performed, e.g. coming from a CAD / CAM software, or real-time data of temperature and mechanical properties of the manufactured object P, as measured e.g. with a number of sensors.

[0080] In another step S2, a process simulation based on the obtained data is run. The process simulation encompasses the additive manufacturing as a whole, and thus simulates the building of the different layers until the build job is completed. According to the invention, an initial process simulation with calibration data as input is provided, which is taken as a reference to plan the additive manufacturing process.

[0081] In a subsequent step S3, process instructions are provided to an additive manufacturing device AMD based on the process simulation. These process instructions contain information about the configuration settings of the additive manufacturing device AMD and can be communicated as an executable file in a format that can be read, processed and executed by the operation software of the additive manufacturing device AMD.

[0082] In a step S4, the additive manufacturing process is performed by the additive manufacturing device AMD, based on the generated process instructions corresponding to the initial process simulation.

[0083] In a step S5, the additive manufacturing process is monitored through the obtention of data at different time points. The obtained data can correspond to temperature measurements and measurements of the mechanical properties of the in-process object P. In general, the obtained data can be related to any parameter relevant for the process simulation.

[0084] In a step S6, the data obtained at an N time point during the performing of the additive manufacturing process is compared with the data obtained at a previous N-l time point. These time points define a sequence, starting with the beginning of the additive manufacturing process. Data obtained at the starting time can be compared with the data used to run the initial process simulation.

[0085] In a step S7, it is decided, based on the result of the comparison in step S6, whether to continue monitoring the additive manufacturing process, i.e. to go the step S5, or to adjust, in a step S8, the additive manufacturing. If the comparison shows that the differences between the data obtained at an N time point and the data obtained at an N-l time point are within some tolerance the additive manufacturing process does not need to be adjusted. Tolerances can be defined, e.g., in the form of thresholds for the measured parameters. If, on the contrary, the differences go above some tolerance, the additive manufacturing process has to be corrected, in order to avoid inaccuracies that could compromise the target quality .

[0086] The adjusting of the additive manufacturing in step S8 comprises a number of steps.

[0087] In a step S9, a new process simulation based on the data obtained at the N time point is run. This can lead to a change in the scanning strategy and / or a change in the support structure strategy, where corresponding parameters such as the scanning speed can get modified.

[0088] In a step S10, new process instructions based on the new process simulation are provided.

[0089] In a step Sil, the additive manufacturing device AMD continues performing the additive manufacturing process based on these new process instructions.

[0090] In preferred embodiments of the invention, the method then goes back to step S5 and monitors the additive manufacturing process further. This sequence of steps starting from the step S5 can be repeated until the additive manufacturing process has been completed.

[0091] Fig. 3 is a schematic diagram showing an example of a support structure strategy according to an embodiment of the present invention. In the first row of Fig. 3, an object P is shown from two different lateral perspectives. The pictures are based on a process simulation that simulates the additive manufacturing of the object P. This object P is being manufactured by an additive manufacturing device AMD, corresponding to the step S4 illustrated in Fig. 2. The dotted line LI denotes the layer that is currently being built. A monitoring (step S5 in Fig. 2) of the additive manufacturing process is taking place in parallel, which reaches the LI layer at a time point N. The data obtained in the monitoring at the N time point is compared (step S6 in Fig. 2) with the data ob- tained in the monitoring at a previous N- l time point , which corresponds to one of the layers below LI (not shown in the figure ) . As a result of the comparison, in this case some of the monitored parameters were out of the allowed tolerances . Accordingly, the control module 50 prompts the simulation module 20 to run a new process simulation . The process simulation can be first restricted to a change in the scanning strategy . In the example illustrated in Fig . 3 , the scanning strategy cannot bring the monitored parameters within allowed tolerances and a process simulation is performed including a support structure strategy .

[0092] The second row of Fig . 3 shows a modi fication of the build strategy, which follows from running a process simulation including an adj ustment of the support structure strategy . A number of critical structures were identi fied, e . g . by the structure evaluation module 60 , where support structures could be implemented . The new process simulation provides a number of added support structures Strl to Str4 , which are added to keep the inaccuracies of the obj ect P to be manufactured under tolerance values .

[0093] The introduced adj ustments modi fy the initial build strategy . The support structures Strl and Str3 are assigned to forthcoming layers , which lay in the immediate future of the additive manufacturing process . However, the support structures Str2 and Str4 will at least partially need to be implemented during a post-processing stage . The process simulation corresponding to the second row of Fig . 3 can preferably be configured to optimi ze the build modi fications introduced by the adj ustments in the support structure strategy by taking into account the additive manufacturing process as a whole , such that the post-processing stage can be reduced to a bare minimum .

[0094] Fig . 4 is a schematic illustration of an additive manufacturing system 500 , comprising an additive manufacturing device AMD and the system 100 of the invention . The additive manu- facturing device AMD can be any device adapted to perform an additive manufacturing process in any of its variants, preferably a laser powder bed fusion process. The system 100 is either implemented or connected (wired or wireless) to the additive manufacturing device 200. The additive manufacturing device AMD is configured to perform an additive manufacturing process of an object P based on the process instructions provided by the system 100. In some embodiments, the system 100 is provided as an application program interface (API) to the additive manufacturing device AMD.

[0095] Fig. 5 shows a schematic block diagram illustrating a computer program product 300 according to an embodiment of the third aspect of the present invention. The computer program product 300 comprises executable program code 350 configured to, when executed, perform a number of steps. In a step SI, data of the additive manufacturing process of the object P is obtained. In a step S2, a process simulation based on the obtained data is run. In a step S3, process instructions are provided to an additive manufacturing device AMD based on the process simulation. In a step S5, the performing of the additive manufacturing process by an additive manufacturing device AMD is monitored with the obtaining of data at different time points. In a step S6, the data obtained at an N time point during the performing of the additive manufacturing process is compared with the data obtained at a previous N-l time point. In a step S7, it is decided, based on the result of the comparison in step S6, whether to continue monitoring the additive manufacturing process, i.e. to go to step S5, or to adjust, in a step S8, the additive manufacturing, wherein adjusting the additive manufacturing comprises at least two steps. In a step S9, a new process simulation based on the data obtained at the N time point is run. In a step S10, new process instructions based on the new process simulation are provided, such that the additive manufacturing device AMD continues performing the additive manufacturing process based on these new process instructions. Fig . 6 shows a schematic block diagram illustrating a non- transitory computer-readable data storage medium 400 according to an embodiment of the fourth aspect of the present invention . The data storage medium 400 comprises executable program code 450 configured to , when executed, perform the steps S I to S 10 detailed in relation to the description of Fig . 5 .

[0096] The non-transient computer-readable data storage medium may comprise , or consist of , any type of computer memory, in particular semiconductor memory such as a solid-state memory . The data storage medium may also comprise , or consist of , a CD, a DVD, a Blu-Ray-Disc, an USB memory stick or the like .

[0097] The previous description of the disclosed embodiments are merely examples of possible implementations , which are provided to enable any person skilled in the art to make or use the present invention . Various variations and modi fications of these embodiments will be readily apparent to those skilled in the art , and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the present disclosure . Thus , the present invention is not intended to be limited to the embodiments shown herein but it is to be accorded the widest scope consistent with the principles and novel features disclosed herein . Therefore , the present invention is not to be limited except in accordance with the following claims .

Claims

Patent claims1. A system (100) for optimizing the additive manuf cturing of an object (P) performed by an additive manufacturing device (AMD) , the system (100) comprising: a data acquisition module (10) configured to obtain data of the additive manufacturing process of the object (P) ; a simulation module (20) configured to run a process simulation that simulates the additive manufacturing process of the object (P) based on the obtained data; an instruction generation module (30) configured to provide process instructions corresponding to the process simulation for the additive manufacturing device (AMD) to perform the additive manufacturing process; a monitoring module (40) configured to compare the data obtained at an N time point during the performing of the additive manufacturing process with the data obtained at a previous N-l time point; and a control module (50) configured to prompt the simulation module (20) , on the basis of a result of the comparison performed by the monitoring module (30) , to run a new process simulation based on the data obtained at the N time point, wherein the process simulation is a thermo-mechanical simulation, and wherein the obtained data comprises an information about the materials to be used for the additive manufacturing process and information about the geometric structure of the object (P) , and wherein the process simulation is further based on a support structure strategy.

2. The system according to claim 1, wherein the additive manufacturing comprises a powder bed fusion process, preferably a laser powder bed fusion process.

3. The system according to any of the preceding claims, wherein the simulation module (20) is further configured to run the process simulation based on a scanning strategy, wherein the scanning strategy comprises adjusting a scanning speed and / or a steering power of the additive manufacturing device (AMD) , and / or adjusting the hold time of single melt events comprised in the scanning path.

4. The system according to any of the preceding claims, further comprising a structure evaluation module (60) , configured to identify surfaces of the object (P) during the additive manufacturing process where support structures (Strl; Str2; Str3; Str4) could be implemented.

5. The system according to any of the preceding claims, wherein the simulation module (20) comprises a machinelearning unit (210) , which is configured to implement a simulation algorithm based on a machine-learning model, trained and adapted to generate a process simulation.

6. The system according to any of the preceding claims, wherein the monitoring module (30) is further configured to make the comparison based on multiple layers of the additive manufacturing process.

7. The system according to any of the preceding claims, further comprising a digital twin generation module (70) , configured to generate, based on the process simulation generated by the simulation module (20) , a digital twin of production corresponding to the additive manufacturing of the object (P) .

8. The system according to any of the preceding claims, wherein the process instructions comprise information for more than one layer of the additive manufacturing process.

9. The system according to any of the preceding claims, further comprising a database module (80) , configured to store the obtained data and the process simulations.

10. An additive manufacturing system (500) , the additive manufacturing system (500) comprising: an additive manufacturing device (AMD) which is configured to perform an additive manufacturing process of an object (P) , and a system (100) according to the any of the claims 1 to 11, wherein the system (100) according to the any of the preceding claims is configured to provide process instructions for the additive manufacturing device (AMD) to perform the additive manufacturing process.

11. A computer-implemented method for optimizing an additive manufacturing process of an object (P) performed by an additive manufacturing device (AMD) , preferably implemented within or executed by a system (100) according to any of the claims 1 to 10, the computer-implemented method comprising the steps: obtaining (SI) data of the additive manufacturing process of the obj ect (P) ; running (S2) a process simulation based on the obtained data; providing (S3) process instructions to the additive manufacturing device (AMD) based on the process simulation; performing (S4) the additive manufacturing process based on the generated process instructions; monitoring (S5) the performing (S4) of the additive manufacturing process with the obtaining of data at different time points ;comparing (S6) the data obtained at an N time point during the performing (S4) of the additive manufacturing process with the data obtained at a previous N-l time point; and deciding (S7) on continuing the monitoring (S5) of the additive manufacturing process or adjusting (S8) the additive manufacturing, wherein the adjusting (S8) of the additive manufacturing comprises:- running (S9) a new process simulation based on the data obtained at the N time point;- providing (S10) new process instructions based on the new process simulation; and- performing (Sil) the additive manufacturing, based on the generated new process instructions.

12. A computer program product (300) comprising executable program code (350) , which is configured, when executed, to perform the following steps: obtaining (SI) data of the additive manufacturing process of the obj ect (P) ; running (S2) a process simulation based on the obtained data; providing (S3) process instructions to the additive manufacturing device (AMD) based on the process simulation; monitoring (S5) the performing of the additive manufacturing process with the obtaining of data at different time points; comparing (S6) the data obtained at an N time point during the performing (S4) of the additive manufacturing process with the data obtained at a previous N-l time point; and deciding (S7) on continuing the monitoring (S5) of the additive manufacturing process or adjusting (S8) the additivemanufacturing, wherein adjusting (S8) the additive manufacturing comprises:- running (S9) a new process simulation based on the data obtained data at the N time point; and- providing (S10) new process instructions based on the new process simulation.

13. A non-transient computer-readable data storage medium (400) comprising executable program code (450) , which is configured, when executed, to perform the following steps: obtaining (SI) data of the additive manufacturing process of the obj ect (P) ; running (S2) a process simulation based on the obtained data; providing (S3) process instructions to the additive manufacturing device (AMD) based on the process simulation; monitoring (S5) the performing (S4) of the additive manufacturing process with the obtaining of data at different time points ; comparing (S6) the data obtained at an N time point during the performing (S4) of the additive manufacturing process with the data obtained at a previous N-l time point; and deciding (S7) on continuing the monitoring (S5) of the additive manufacturing process or adjusting (S8) the additive manufacturing, wherein adjusting (S8) the additive manufacturing comprises:- running (S9) a new process simulation based on the data obtained at the N time point; and- providing (S10) new process instructions based on the new process simulation.

Images