[go: up one dir, main page]

WO2019170286A1 - Procédé et dispositif pour la fabrication additive à optimisation automatique de composants de pièces - Google Patents

Procédé et dispositif pour la fabrication additive à optimisation automatique de composants de pièces Download PDF

Info

Publication number
WO2019170286A1
WO2019170286A1 PCT/EP2019/000071 EP2019000071W WO2019170286A1 WO 2019170286 A1 WO2019170286 A1 WO 2019170286A1 EP 2019000071 W EP2019000071 W EP 2019000071W WO 2019170286 A1 WO2019170286 A1 WO 2019170286A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter
layer
component
observation data
artificial intelligence
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/EP2019/000071
Other languages
German (de)
English (en)
Inventor
Joachim Bamberg
Katrin Friedberger
Frank Stiehler
Christoph Ader
Frederik ELISCHBERGER
Alexander Ladewig
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MTU Aero Engines AG
Original Assignee
MTU Aero Engines AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by MTU Aero Engines AG filed Critical MTU Aero Engines AG
Publication of WO2019170286A1 publication Critical patent/WO2019170286A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/4097—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by using design data to control NC machines, e.g. CAD/CAM
    • G05B19/4099—Surface or curve machining, making 3D objects, e.g. desktop manufacturing
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/10—Processes of additive manufacturing
    • B29C64/141—Processes of additive manufacturing using only solid materials
    • B29C64/153—Processes of additive manufacturing using only solid materials using layers of powder being selectively joined, e.g. by selective laser sintering or melting
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/30—Auxiliary operations or equipment
    • B29C64/386—Data acquisition or data processing for additive manufacturing
    • B29C64/393—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y10/00—Processes of additive manufacturing
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/49—Nc machine tool, till multiple
    • G05B2219/49018—Laser sintering of powder in layers, selective laser sintering SLS
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/49—Nc machine tool, till multiple
    • G05B2219/49023—3-D printing, layer of powder, add drops of binder in layer, new powder

Definitions

  • the present invention relates to a method and a device for the self-optimizing, additive production of component components according to the preamble of claim 1 or the preamble of claim 10.
  • DE 10 2015 207 254 A1 discloses a method for producing a dreidimensio cal object by layered solidification of a powdery organizingmate rials by electromagnetic radiation, wherein an irregularity determination of a presence of a Jerusalemirregulartician with respect to at least one vinparame ter is carried out during manufacture and during scanning with The elektagnetic beam scanning is interrupted at least one current point of the cross-section to be solidified on the basis of a result of Irregularticiansar.
  • An object of an embodiment of the present invention is to improve the quality of the manufactured component component and to accelerate an optimization of the production parameters.
  • a method for self-optimizing, additive manufacturing of component components has the following steps: a) starting a reference construction job by means of additive production of a component in a building device; b) observing the additive production of the reference construction job and acquiring observation data; and / or c) evaluating a solidification process of a building material at least partially solidified during the additive production of the reference construction job and acquiring evaluation data; d) transmitting the observation data and / or the evaluation data to a computing device with artificial intelligence implemented; e) optimizing at least one parameter for the additive production by the artificial intelligence implemented in the computing device; f) transmitting the at least one parameter to a control device of the building device and further performing the remaining construction job using the at least one transmitted parameter Pa; and g) iterative execution of steps b) to f) during the further execution of the reference construction job.
  • the artificial intelligence implemented in the computing device comprises a neural network, wherein the observation data and the evaluation data are input to an input layer of the neural network and the at least one optimized additive manufacturing parameter is output from an output layer of the neural network.
  • step a) comprises the following substeps: a) at least one powder layer in a construction area on a platform or on one or more component component layers located on the platform; a2) locally solidifying the at least one powder layer by selective exposure by means of a high-energy beam in the construction area to form a layer of the component component; a3) lowering the platform by a predefined layer thickness; and a4) repeating steps al) to a3) until the component component is completed.
  • step b) comprises an optical method, in particular optical tomography, and / or an acoustic method, in particular ultrasound sound analysis, and / or a thermography / laser thermography and / or an eddy current examination and / or a melt monitoring.
  • a correlating parameter is preferably acquired between the layer production quantities and the layer production result of the reference component.
  • a correlation value of an optically observed layer surface is determined as the correlating parameter, whereby a correlation between the production process of the layer surface (s), for example by a high-energy beam, and the production result, for example by a Melting result, can be produced.
  • the correlation value and thus the correlating parameter can be determined as a gray value by the optical method.
  • a correlating parameter of training describes the structure, for example, can also be a stretch, a medium and / or a maximum grain size.
  • the gray value of a local area for example an area of less than pm, can also be referred to as a pixel and is a measure of the intensity of the melting light due to the melting process by means of a high-energy beam.
  • a plurality of gray values can be determined at each exposure as a pixel image or a gray-scale image, wherein each pixel of the pixel image represents a gray value.
  • step c) comprises a thermography / laser thermography and / or an eddy current test.
  • the parameter in step e) preferably has a scanning speed of the high-energy beam, an energy input of the high-energy beam into the powder layer, a type of protective gas flow over the construction area, a scanning pattern or scanning strategy of the high-energy beam, in particular an exposure surface of the high-energy beam, a strip angle, a particle size a powder in the powder layer, a type of layer as an up-skin, down-skin, in-skin component component and / or a size of the predefined layer thickness.
  • Process parameters may be, for example, a length of an exposure path of the high energy beam (hatch vector length), a distance between two exposure paths of the high energy beam (Hatch distance), an exposure direction of the high energy beam, also relative to a gas flow direction, a particle size of a powder in the powder layer, and a layer thickness.
  • Process parameters are in particular of the device for self-optimizing, additive production of component components predetermined Pa Parameters that are involved in a solidification of the powder layer directly or indirectly.
  • the artificial intelligence can in particular be trained to obtain the correlating parameter and to use it as an input variable.
  • the artificial intelligence can use and evaluate the gray value of a pixel image or of a gray value image as an input vector.
  • a limit value or a limit range for one, some or all input variables in the above-described example, can be used by one of the artificial intelligence for one, some or all of the gray values for the evaluation.
  • the threshold may be pre-determined, trained or determined during previous steps of the method.
  • a gray value of a pixel may be an intensity of a melting light.
  • Artificial intelligence may be trained to incorporate pixels, in particular their discrete values on a finite scale, into an assessment strategy.
  • a (discrete) gray value below a (discrete) threshold as a positive factor, a (discrete) gray value above the (discrete) threshold as a negative factor can be included in the evaluation strategy.
  • a weighting coefficient or a weighting coefficient image can be assigned to one or more of the parameters to be optimized, in particular in relation to a position in the powder bed or the layer to be produced.
  • observation data and / or evaluation data in particular correlating parameters from previous steps, can be used in the evaluation strategy of a current shift.
  • the artificial intelligence can then based on a variety of positive and negative factors, in particular local over one or more pixel corresponding lengths adjust the (said) parameter, for example, reduce the energy input locally in the production of a next layer or locally adjust other parameters and so optimize.
  • the adaptation of the parameter can not be done locally. It can be provided that the adaptation depends on a causality between the correlating parameter and other input variables in the form of a causality vector, in the form of weighting coefficients or in the form of variables in Activation functions takes place. In this case, the causality can be determined, for example, by one or more training steps.
  • correlating parameters such as a type of defect, a number of defects or a defect size can be included in the evaluation strategy.
  • a pixel image of gray levels may be an input vector of an input layer in a neural network.
  • the input vector may additionally contain further variables. These quantities may include the observation data, the evaluation data and / or further process parameters.
  • a target value of the artificial intelligence evaluation strategy may be that the gray values of an image or at least a portion of the image upon completion of a layer are all below a threshold or within a threshold.
  • the artificial intelligence can adjust the parameters step by step during the construction job. It can be provided that the artificial intelligence over several layers attempts to reach the target value. It is also possible to simulate the parameters and compare a result of the simulation with expected results from a knowledge base created, for example, in an artificial intelligence training.
  • Artificial intelligence may be trained to optimize one or more parameters of the method in step e) for localized gray levels in certain violations of the threshold or boundary to obtain a more consistent halftone image, for example, a more uniform gray tone image Melting, or even to reach the above target value.
  • the optimization of the parameter can be location-dependent, that is, for example, at the local site or in this local area, in which a violation of the limit or leaving the border area was detected, take place.
  • causal-dependent adaptation can no longer be compellingly comprehensible and can only emerge in the course of a training session or even during a construction job.
  • a combination of local and causal adaptations is also possible.
  • the artificial intelligence selects an ideal combination of parameters from a multiplicity of possible combinations of parameters for the optimization.
  • the artificial intelligence can adjust other input variables, the weighting coefficients or modified the activation functions, if it recognizes that there are several possible combinations for optimizing the parameters.
  • comparable gray values can be achieved by optimizing a combination of the parameters energy input and web speed of the high-energy beam, the artificial intelligence then accessing further secondary variables and / or training variables from a database, for example noise or geometry-dependent and location-dependent gray-scale differences the layer.
  • observation data from step b) or the evaluation data from step c) acquire a correlating parameter between layer production values and layer production result of the reference component, where in the layer production variables in particular the transmitted parameters from step f), particularly preferably an optimized parameter from step e).
  • the method according to the invention can be designed such that the artificial intelligence is trained to optimize the parameter such that a target value of the observation data and / or the evaluation data, in particular a target value of a correlating parameter, is reached or approximated.
  • the artificial intelligence transmits first observation data and / or first evaluation data, which in a first run of the method is transmitted to the artificial intelligence when a first layer is set up. were compared with second observation data and / or second evaluation data transmitted to artificial intelligence in a later than the first pass of the method in a subsequent layer construction, and
  • the observation data comprise a correlating parameter, which is determined by an optical tomography and represents a measure of a light intensity of a melting light, that the parameter is a power of an energy input of a high-energy beam, and that the artificial intelligence Power of the energy input locally reduced when a comparison of the correlating parameter with training data can expect a too large number of Albertstel sources in the structure of the cured melt in this layer.
  • This procedure represents a very special artificial intelligence assessment strategy in order to optimize the parameter in step e). Further and / or additional features for the artificial intelligence assessment strategy are already indicated above in this application.
  • the transmission of the observation data and the evaluation data to the computing device and the transmission of the at least one parameter to the control device takes place online via a network, in particular via the Internet.
  • the method has a step for storing the observation data, the evaluation data and / or the at least one parameter in a data bank, preferably a cloud. More preferably, a plurality of building devices are networked with the database. Learning can be further accelerated by networking individual autonomous additive manufacturing systems.
  • an apparatus for self-optimizing additive manufacturing of component components having a component component manufacturing component manufacturing apparatus has a device for observing additive manufacturing of a reference construction job and acquiring observation data; an apparatus for evaluating a method of obtaining a building material at least partially solidified in the additive production of the reference construction job and acquiring evaluation data; an apparatus for transmitting the observation data and the evaluation data to an artificial intelligence implementing computing apparatus that optimizes at least one additive manufacturing parameter; a device for transmitting the at least one parameter to a control device of the Bauvor direction, which performs the remaining construction job using the at least one transmitted parameter on.
  • the device according to the invention achieves the same advantages as the method according to the invention.
  • a means in the sense of the present invention may be embodied as hardware and / or software, in particular a data or signal-connected, preferably digital, processing, in particular microprocessor unit (CPU or GPU), preferably with a memory and / or bus system. and / or one or more programs or program modules.
  • the CPU may be adapted to handle instructions implemented as a program stored in a memory system, to capture input signals from a data bus, and / or to output output signals to a data bus.
  • the GPU may be designed to efficiently perform the necessary operations for training the potentially deep neural network. However, the training should not be limited exclusively to the GPU, but may, depending on the effort, also be performed on parts on the CPU or on other, separate, application-specific hardware such as TPUs (tensor processing units).
  • a storage system may comprise one or more, in particular different, storage media. have, in particular optical, magnetic, solid state and / or other non-volatile media.
  • one or more, in particular special all, steps of the method are completely or partially automated, in particular by the controller or her (e) means.
  • Fig. 1 is a construction device which can be used in the method of the present inven tion
  • FIG. 2 is a flow chart of an embodiment of the method according to the present invention.
  • Fig. 3 is a principle of optical tomography
  • Fig. 4 different radiation with different spectra, which arise in egg ner heating of the powder layer and can be detected by the optical tomography;
  • Fig. 7 shows an example of a neural network.
  • Fig. 1 shows a schematic representation of a building apparatus 10 which can be used in the method of the present invention. It is a construction device 10 for producing a metallic component component 30, in particular special a metallic component component 30 of a turbomachine, by means of selective laser melting (Selective Laser Melting SLM).
  • the component component 30 may be, for example, a complex rotor blade or vane High-pressure turbine act.
  • the construction device 10 comprises a powder feeder or coater 18 for applying a powder layer 28 of a metallic material 22 in a construction area 40 above a platform 12.
  • the metallic material 22 is stored in a reservoir 20 and is tion over the Pulverzut 18, which in particular as Coater is formed, layer by layer on the platform 12 or on itself already on the platform 12 located powder layers 28 applied.
  • the metallic material 22 may consist in particular of a titanium or nickel alloy.
  • the average grain size of the metallic material 22 used may be about 10 to 100 mih.
  • One or more applied powder layers 28 are layered and locally fused and / or sintered in the building area 40 to form at least a portion of a layer of the component component 30 by means of a laser beam 16 emitted by a laser source 14.
  • a laser beam 16 emitted by a laser source 14.
  • an Nd: YAG laser is used in the illustrated embodiment: Its laser power can be between 400 and 1000 W, depending on the type of component.
  • the control of the laser beam 16 results in a prescribed component geometry of the component component 30.
  • the material not required for the construction of the component component 30 is transferred by means of the coater 18 into an overflow container 24. The unneeded material is indicated at 26.
  • the construction device 10 comprises an induction device 32 which has two induction coils 42, 44.
  • the two induction coils 42, 44 form a crossing region and are constructed according to the so-called cross-coil concept.
  • the induction device 32 is about the powder layer 28 relation ship as the platform 12 designed to be movable.
  • the induction device 32 is configured to heat or heat a portion of the component component 30 by local fusion and / or bonding with the material 22 of the powder layer 28 by means of inductive heating at a temperature or temperature range the solidification temperature of the metallic material used 22 is trainees form.
  • high temperature nickel-base alloys as a material 22, such as M247
  • said temperature range is above from about 1250 to 1260 ° C.
  • the induction device 32 is thereby controlled and regulated by means of a control device (not shown). On the one hand, this relates to the power of the induction device 32 or of the individual induction coils 42, 44 as well as their position above the platform 12.
  • the shape and the material structure of the component component 30 are determined beforehand as a computer-generated model (CAD model) in a computer.
  • the layer information generated therefrom is input as corresponding data in the control device of the building apparatus 10. These data then serve to control the individual components of the construction device 10.
  • At least one powder layer 28 is applied in the construction area 40 directly on the platform 12 or on one or more powder layer 28 already located on the platform 12.
  • the powder layer 28 is locally solidified by selectively exposing the high energy beam 16 in the build area 40 to form a layer of the component component 30.
  • at least partial heating of the material 22 in the powder layer 28 may be effected by the induction device 32 in a ductile heating manner.
  • the platform 12 is lowered by a predefined layer thickness, and the previous passes are repeated until the component component 30 is completed.
  • the present invention is not limited to the laser melting method.
  • the device component 30 may be fabricated by other additive techniques, such as selective laser sintering (SLS), selective heat sintering (SHS), fused deposition modeling (FDM), 3D printing, electron beam melting (EBM), cladding Cladding or metal powder application method (MPA).
  • SLS selective laser sintering
  • SHS selective heat sintering
  • FDM fused deposition modeling
  • EBM electron beam melting
  • cladding Cladding metal powder application method
  • FIG. 2 shows a flowchart of an embodiment of the method according to the present invention, by means of which the additive production of the component components 30 can be optimized on its own.
  • a reference building job is started by means of additive production of a component component 30 in the building apparatus 10.
  • a step b the additive production of the reference construction job is observed, and observation data is acquired.
  • the observation data can be highly complex and multidimensional data. The observation happens online during the execution of the reference construction job.
  • a solidification process of a building material solidified in the additive production of the reference construction job is evaluated, and evaluation data is acquired.
  • the rating data may include facts such as crack size, Rissan number, etc.
  • the observation is non-destructive and in egg nem period in which one to five subsequent layers are solidified.
  • the rating is done online during the execution of the reference construction job.
  • the observation data and the evaluation data are transmitted to a computing device and input into an input layer of a neural network implemented in the computing device.
  • At least one parameter for the additive production is optimized by the artificial intelligence implemented in the computing device.
  • a step f) the at least one parameter is transmitted to a control device of the building device 10.
  • the at least one parameter is implemented in a construction job program, in which CAD data of the component component 30 as well as other manufacturing parameters are incorporated.
  • the remaining construction job is continued using the at least one transmitted parameter.
  • the steps b) to f) are carried out iteratively using the at least one parameter transmitted in the previous step f), for example until the component component 30 is completed or reaches a predetermined quality level.
  • step h an offline follow-up of component component 30 can take place.
  • an optical method in particular an optical tomography shown in FIG. 3, can be used.
  • optical tomography one or more powder layers 28 of the component component 30 are imaged.
  • slice images of the component component 30 are determined during their additive production by means of a detection device 31.
  • the detection device 31 can detect a measured variable in a spatially resolved manner, which characterizes an energy input into the pulse 28 of the component component 30.
  • the detection device 31 can be, for example, a CMOS, an sCMOS or a CCD sensor, which detects infrared radiation as a measured variable.
  • a slice image can be composed of several, for example 100 to 1000 individual images, which for example can have an exposure time between 1.0 ms and 5000 ms.
  • Fig. 4 shows the laser beam 16 having, for example, a wavelength of 1064 nm.
  • Reference numerals 45, 46 and 47 denote beams in different spectrums radiated from the powder layer 28.
  • the reference numeral 45 denotes heat radiation in the visible infrared region.
  • the reference numeral 46 designates reflected laser light.
  • the reference numeral 47 denotes a plasma radiation in the range between 400 and 600 nm. At least the radiations 45 and 47 can be detected by corresponding detection means 31.
  • a two-dimensional image of the powder layer 28 or a three-dimensional image of the component component 30 is then based on the determined layer images he witnesses, which can optionally be displayed on a display device. From the he averaged slice images, the observation data are acquired in step b), which are then transferred to the computing device at step d) and input to the input layer of the neural network.
  • step b) it is possible to compare the image of the component component 30 in step b) with a desired image of the component component 30, wherein as a target image, a data model and / or an X-ray image of the component component 30 and / or an image of a Reference component can be used. Deviations between the image and the target image may be used as the observation data.
  • an acoustic method in particular special ultrasonic sound analysis, can be used.
  • ultrasonic signals are emitted by a transmitter device of an ultrasonic transducer device at least to egg nem portion of the solidified component component 30.
  • the transmitter device can be arranged below, above or to the side of the platform 12.
  • a receiving device receives the ultrasonic signals and determines at least one parameter that characterizes the ultrasonic signals.
  • This parameter can be the transit time of the reflected ultrasound signals, the sound amplitude of the reflected ultrasound signals or at least one frequency component of the reflected ultrasound signals, wherein the at least one parameter can be determined, in particular, over a predetermined period of time.
  • a plurality of the ultrasonic transducer devices as an array, in particular phase-shifted, are controlled.
  • Step c) may have a thermography / laser thermography exemplified in FIG. 5.
  • a thermographic image of at least one image or an image sequence 51 of a single applied and at least partially solidified layer 28 is produced by a thermography device 52, 53, 54 during step a).
  • the thermography device 52, 53, 54 has a (laser) scanner 53, a thermal camera 52 and a dichroic mirror 54.
  • the layer 28 may optionally be subjected to an additional, controlled heat treatment below the melting temperature of the material 22 prior to the thermographic image of the associated image.
  • the heat treatment can by the Laser source 14 or by the induction device 32 done.
  • the heat through the laser beam 16 during solidification or the heat through the additional heat treatment causes a radiant heat emanating from the layer 28, the occurrence of at least one crack 56 in the layer 28 has a characteristic heat history at the crack 56, wherein the heat history and thus the Crack 56 be made visible on the associated thermographic recording.
  • the cracks can be detected by absorption (so-called laser trap), emission or by a lateral heat accumulation or a lateral heat conduction.
  • the controlled heat treatment, a heat radiation in the layer 28 he testify, which is in the infrared range at the edge of the visible spectrum and in the Erfas sungsspektrum the thermography device 52, 53, 54.
  • an eddy current test shown by way of example in FIG. 6 can take place.
  • an eddy current scan is generated for example in a frequency range of 1 MHz to 10 MHz in the at least partially ver consolidated region of the powder layer 28, wherein a scanning depth preferably corresponds to a multiple of the layer thickness.
  • the eddy current test is suitable for crack testing. If the eddy current scan flows evenly in the material, its electrical resistance is homogeneous and damage can be ruled out. If cracks or foreign bodies are present in the material, the specific resistance and thus the eddy current density change with respect to the remaining material.
  • a linear eddy current array 61 is arranged in a ridge 62.
  • the linear eddy current array 61 may alternatively be arranged in the powder feed 18.
  • a We belstromscan is shown, in which a plurality of defects 63, 64, 65 are shown.
  • the reference numeral 63 denotes cracks
  • the reference numeral 64 denotes pores
  • the reference numeral 65 denotes not or insufficiently molten powder 22.
  • a material characterization of the at least partially solidified region of the powder layer 28 may take place, taking into account a preceding effect. Belstromscans of solidified areas deeper powder layers 28 are determined. With each eddy current scan a multi-frequency measurement can be carried out.
  • the observation data and evaluation data acquired in the above-described steps b) and c) are transmitted to the artificial intelligence implementing computing apparatus.
  • step e) the at least one additive manufacturing parameter is optimized by the artificial intelligence implemented in the computing device, and at step f) the at least one parameter is transmitted to a controller of the building device 10 so that the remaining construction job is used tion of the at least one transmitted parameter is continued.
  • the artificial intelligence implemented in the computing device has a neuronal network, wherein the observation data and the evaluation data are input to an input layer of the neural network and the at least one optimized parameter for the additive production is output from an output layer of the neuron network becomes.
  • Fig. 7 shows an example of a neural network having an input layer 71, an intermediate layer 72 and an output layer 73.
  • the input layer 71 is supplied with corresponding input values by an input vector.
  • a neuron can process one input value or several input values.
  • the neural network has successive layers of neurons connected to interconnections in the form of weighting coefficients Wn, ij.
  • Wn weighting coefficients
  • a neuron counteracts the multiplication and addition-weighted activations, ie the initial values, of all the neurons connected to it and evaluates, based on the sum and an activation function ordered to it, on how high the activation is for this neuron.
  • the activations U3, k of the output layer 73 of the neural network can be concatenations of very many linear combinations and depend on the weights used and the input values and the particular activation used. functions.
  • the connecting elements add and / or multiply the output signals of the preceding neurons by weighting coefficients Wn, ij and Wnj, k, respectively.
  • weight coefficients Wn, ij and Wnj, k are variable and are determined mutually independently. However, it can also be provided that the weight coefficients are changed on the basis of an evaluation of the production of a layer in the same construction job.
  • the values of the weight coefficients Wn, ij connecting the input layer with the intermediate layer can be considered as the respective coupling strengths between neurons of the intermediate layer U2j and the neurons of the input layer Ul, i. If the output layer U3, k of the neural network consists only of a single neuron U3, I, a single output value from the last neuron of the neural network is generated according to a particular combination of input signal values supplied to the input layer of the neural network.
  • the neural network can have several intermediate layers, so that so-called deep learning is possible.
  • the neural network is trained to output the at least one parameter based on the input observation data and evaluation data such that the quality of the component component 30 reaches a predetermined quality level.
  • the predetermined quality level may be, for example, a maximum allowable number of cracks in an area or volume unit or a maximum allowable size of the cracks.
  • the predetermined quality level can be set arbitrarily.
  • the parameter output from the output layer of the neural network and optimized in step e) can be a scanning speed of the high energy beam 16, an energy input of the high energy beam 16, a type of protective gas flow over the building area 40, a scanning pattern of the high energy beam 16, a particle size of a powder 22 in the powder layer 28, a kind of the layer as up-skin, down-skin, in-skin of the component component 30 and / or a size of the predefined th layer thickness.
  • the transmission of the observation data and the evaluation data to the computing device in step d) and the transmission of the at least one parameter to the control device in step f) can take place online via a network, in particular the Internet.
  • the computing device may have read / write access to a data server.
  • observation data, the evaluation data and / or the at least one parameter can be stored in a database, preferably a cloud.
  • the steps a) to g) can advantageously be carried out in real time. It is possible to network several building devices 10 with the database in order to accelerate the learning process of the neural network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Materials Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Powder Metallurgy (AREA)

Abstract

La présente invention concerne un procédé et un dispositif pour la fabrication additive à optimisation automatique de composants de pièces (30), caractérisé par les étapes suivantes : a) démarrage d'un travail de construction de référence ; b) observation de la fabrication additive du travail de construction de référence et acquisition de données d'observation ; c) évaluation d'un processus de solidification d'un matériau de construction au moins partiellement solidifié lors de la fabrication additive du travail de construction de référence et acquisition de données d'évaluation ; d) transfert des données d'observation et d'évaluation à un dispositif de calcul comprenant une intelligence artificielle implémentée ; e) optimisation d'au moins un paramètre par l'intelligence artificielle ; f) transmission de l'au moins un paramètre à un dispositif de commande du dispositif de construction (10) et poursuite de l'exécution du travail de construction restant en utilisant l'au moins un paramètre transmis ; et g) exécution itérative des étapes b) à f) durant la poursuite de l'exécution du travail de construction de référence.
PCT/EP2019/000071 2018-03-07 2019-03-07 Procédé et dispositif pour la fabrication additive à optimisation automatique de composants de pièces Ceased WO2019170286A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102018203444.3 2018-03-07
DE102018203444.3A DE102018203444A1 (de) 2018-03-07 2018-03-07 Verfahren und Vorrichtung zum selbstoptimierenden, additiven Herstellen von Bauteilkomponenten

Publications (1)

Publication Number Publication Date
WO2019170286A1 true WO2019170286A1 (fr) 2019-09-12

Family

ID=65991745

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2019/000071 Ceased WO2019170286A1 (fr) 2018-03-07 2019-03-07 Procédé et dispositif pour la fabrication additive à optimisation automatique de composants de pièces

Country Status (2)

Country Link
DE (1) DE102018203444A1 (fr)
WO (1) WO2019170286A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210247325A1 (en) * 2020-02-10 2021-08-12 Stratasys, Inc. Method for multivariate testing, development, and validation of a material for an additive manufacturing device
CN114514083A (zh) * 2019-09-27 2022-05-17 弗兰德有限公司 利用硬化的增材制造方法
CN115526083A (zh) * 2022-10-25 2022-12-27 四川汇利实业有限公司 一种基于有限元分析的pvdc涂布方法、电子设备及系统
DE102021207503A1 (de) 2021-07-14 2023-01-19 Volkswagen Aktiengesellschaft Verfahren zum Erzeugen von Steuerdaten für ein Fertigungsbauteil für zumindest eine Fertigungsvorrichtung mittels einer elektronischen Recheneinrichtung, Computerprogrammprodukt sowie elektronische Recheneinrichtung
CN116461120A (zh) * 2023-05-17 2023-07-21 浙江恒耀电子材料有限公司 酚醛复合材料的制备方法及其系统
US12459202B2 (en) 2024-01-19 2025-11-04 3D Systems, Inc. Flow rate control in extrusion deposition process

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102019122983A1 (de) * 2019-08-27 2021-03-04 Eos Gmbh Electro Optical Systems Verfahren zur generativen Fertigung von Bauteilen, Vorrichtung, Verfahren zur Steuerung und Speichermedium
DE102019124811B4 (de) 2019-09-16 2021-05-12 H-Next Gmbh Ultraschallsystem und bildgebendes Ultraschallverfahren
DE102019127952A1 (de) 2019-10-16 2021-04-22 Trumpf Laser- Und Systemtechnik Gmbh Verfahren zum Betreiben einer Einrichtung zur additiven Herstellung eines dreidimensionalen Objekts sowie Verfahren zum Erstellen eines Prozessfensters zur Durchführung des vorgenannten Verfahrens
EP3943220A1 (fr) * 2020-07-24 2022-01-26 Aixway3D GmbH Dispositif et procédé pour un système pulvérulent permettant une meilleure efficacité d'utilisation de la poudre dans un procédé de fabrication additive
DE102021130792A1 (de) 2021-11-24 2023-05-25 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Verfahren zum Vergüten eines Bauteils in einem Schneid- und/oder Umformwerkzeug

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011008774A1 (de) 2011-01-18 2012-07-19 Mtu Aero Engines Gmbh Verfahren und Vorrichtung zur Prüfung der generativen Herstellung eines Bauteils
EP2666612A1 (fr) 2012-05-25 2013-11-27 MTU Aero Engines GmbH Procédé et dispositif de représentation d'au moins un composant en trois dimensions
EP2747934A1 (fr) 2011-08-27 2014-07-02 MTU Aero Engines GmbH Procédé et dispositif destinés à la fabrication générative d'une pièce
DE102014212246B3 (de) 2014-06-26 2015-08-06 MTU Aero Engines AG Verfahren und Vorrichtung zur Qualitätssicherung
DE102015207254A1 (de) 2015-04-21 2016-12-01 Eos Gmbh Electro Optical Systems Vorrichtung und Verfahren zur generativen Herstellung eines dreidimensionalen Objektes
US20170050382A1 (en) * 2015-08-21 2017-02-23 Voxel8, Inc. Closed-Loop 3D Printing Incorporating Sensor Feedback
US20170144378A1 (en) * 2015-11-25 2017-05-25 Lawrence Livermore National Security, Llc Rapid closed-loop control based on machine learning
DE102016201290A1 (de) * 2016-01-28 2017-08-17 Siemens Aktiengesellschaft Verfahren zur Qualitätssicherung und Vorrichtung

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SG11201810504TA (en) * 2016-05-24 2018-12-28 Divergent Technologies Inc Systems and methods for additive manufacturing of transport structures

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011008774A1 (de) 2011-01-18 2012-07-19 Mtu Aero Engines Gmbh Verfahren und Vorrichtung zur Prüfung der generativen Herstellung eines Bauteils
EP2747934A1 (fr) 2011-08-27 2014-07-02 MTU Aero Engines GmbH Procédé et dispositif destinés à la fabrication générative d'une pièce
EP2666612A1 (fr) 2012-05-25 2013-11-27 MTU Aero Engines GmbH Procédé et dispositif de représentation d'au moins un composant en trois dimensions
DE102014212246B3 (de) 2014-06-26 2015-08-06 MTU Aero Engines AG Verfahren und Vorrichtung zur Qualitätssicherung
DE102015207254A1 (de) 2015-04-21 2016-12-01 Eos Gmbh Electro Optical Systems Vorrichtung und Verfahren zur generativen Herstellung eines dreidimensionalen Objektes
US20170050382A1 (en) * 2015-08-21 2017-02-23 Voxel8, Inc. Closed-Loop 3D Printing Incorporating Sensor Feedback
US20170144378A1 (en) * 2015-11-25 2017-05-25 Lawrence Livermore National Security, Llc Rapid closed-loop control based on machine learning
DE102016201290A1 (de) * 2016-01-28 2017-08-17 Siemens Aktiengesellschaft Verfahren zur Qualitätssicherung und Vorrichtung

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114514083A (zh) * 2019-09-27 2022-05-17 弗兰德有限公司 利用硬化的增材制造方法
CN114514083B (zh) * 2019-09-27 2024-02-23 弗兰德有限公司 利用硬化的增材制造方法
US20210247325A1 (en) * 2020-02-10 2021-08-12 Stratasys, Inc. Method for multivariate testing, development, and validation of a material for an additive manufacturing device
US12158432B2 (en) * 2020-02-10 2024-12-03 Stratasys, Inc. Method for multivariate testing, development, and validation of a material for an additive manufacturing device
DE102021207503A1 (de) 2021-07-14 2023-01-19 Volkswagen Aktiengesellschaft Verfahren zum Erzeugen von Steuerdaten für ein Fertigungsbauteil für zumindest eine Fertigungsvorrichtung mittels einer elektronischen Recheneinrichtung, Computerprogrammprodukt sowie elektronische Recheneinrichtung
CN115526083A (zh) * 2022-10-25 2022-12-27 四川汇利实业有限公司 一种基于有限元分析的pvdc涂布方法、电子设备及系统
CN116461120A (zh) * 2023-05-17 2023-07-21 浙江恒耀电子材料有限公司 酚醛复合材料的制备方法及其系统
CN116461120B (zh) * 2023-05-17 2023-10-03 浙江恒耀电子材料有限公司 酚醛复合材料的制备方法及其系统
US12459202B2 (en) 2024-01-19 2025-11-04 3D Systems, Inc. Flow rate control in extrusion deposition process

Also Published As

Publication number Publication date
DE102018203444A1 (de) 2019-09-12

Similar Documents

Publication Publication Date Title
WO2019170286A1 (fr) Procédé et dispositif pour la fabrication additive à optimisation automatique de composants de pièces
DE102016115241A1 (de) Adaptiver generativer fertigungsprozess unter verwendung des vor-ort-laser-ultraschalltestens
EP3542927A1 (fr) Procédé d'irradiation sélective d'une couche de matière, procédé de préparation d'un ensemble de données, dispositif et produit de programme informatique
EP2905592A1 (fr) Procédé et dispositif de détermination de contraintes résiduelles d'un composant
DE102016205432A1 (de) Verfahren und Vorrichtung zum additiven Herstellen zumindest eines Bauteilbereichs eines Bauteils
DE102011008774A1 (de) Verfahren und Vorrichtung zur Prüfung der generativen Herstellung eines Bauteils
EP3403745A1 (fr) Dispositif de fabrication en couche et procédé de fabrication en couche destinés à la fabrication additive d'au moins une zone de composant d'un composant
EP3956736B1 (fr) Procédé mis en oeuvre par ordinateur pour la détermination de défauts d'un objet fabriqué au moyen d'un processus de fabrication additive
WO2018167024A1 (fr) Procédé pour la détermination de valeurs de paramètres de processus d'impression, procédé pour la commande d'une imprimante 3d, support de stockage lisible par ordinateur et imprimante 3d
DE102020002263A1 (de) Vorrichtung und Verfahren zum Erlernen einer Fokuspositionsverschiebung einer Laserbearbeitungsvorrichtung und Laserbearbeitungssystem, das eine Fokuspositionsverschiebung korrigiert
DE112021000437T5 (de) Defektdetektionsverfahren, Defektdetektionsvorrichtung und Vorrichtung zur additiven Fertigung
EP3488305B1 (fr) Procédé et dispositif de détermination de la qualité d'un composant
EP4619183A1 (fr) Procédé de fourniture d'une instruction de processus pour la fabrication additive, au moyen d'un apprentissage automatique
WO2018210436A1 (fr) Optimisation de l'introduction d'énergie dans la couche inférieure
WO2023083929A1 (fr) Procédé, dispositif de planification et produit-programme informatique pour planifier une exposition localement sélective d'une région de travail au rayonnement d'un faisceau d'énergie, et procédé, dispositif de fabrication et produit-programme informatique pour la fabrication additive de composants à partir d'un matériau en poudre
EP3807031B1 (fr) Calcul de trajets d'exposition à faible distorsion des pièces
DE102019208266A1 (de) Überwachung der maschinellen Fertigung von Werkstücken
DE102016210538A1 (de) Verfahren und Vorrichtung zum Fertigen von Objekten mit verbesserter Oberflächenbeschaffenheit
WO2023083575A1 (fr) Procédé, dispositif de planification et produit-programme informatique de planification d'une exposition localement sélective d'une région de travail au rayonnement d'un faisceau d'énergie, et procédé, dispositif de fabrication et produit-programme informatique pour la fabrication additive de composants à partir d'un matériau en poudre
DE102017207832A1 (de) Positionsspezifischer Energieeintrag
EP3656489A1 (fr) Procédé de régulation pour la fabrication additive
WO2023078762A1 (fr) Procédé, dispositif de planification et produit-programme informatique de planification d'une exposition localement sélective d'une zone de travail au rayonnement d'un faisceau d'énergie, et procédé, dispositif de production et produit-programme informatique pour la fabrication additive de composants à partir d'un matériau en poudre
EP4045212A1 (fr) Procédé de fonctionnement d'un dispositif de fabrication additive d'un objet tridimensionnel et procédé de création d'une fenêtre de traitement pour mettre en oeuvre ledit procédé
WO2020173519A1 (fr) Procédé de construction en couches et dispositif de construction en couches pour la fabrication additive d'au moins une zone d'élément structural d'un élément structural, ainsi que produit de programme informatique et support de stockage
DE102023114366A1 (de) Verfahren und Vorrichtung zur Generierung von Steuerdaten für eine Vorrichtung zur additiven Fertigung eines Bauteils

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19714313

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19714313

Country of ref document: EP

Kind code of ref document: A1