CN111372755A - 增材制造图像的卷积神经网络评估以及以其为基础的增材制造*** - Google Patents
增材制造图像的卷积神经网络评估以及以其为基础的增材制造*** Download PDFInfo
- Publication number
- CN111372755A CN111372755A CN201880075731.9A CN201880075731A CN111372755A CN 111372755 A CN111372755 A CN 111372755A CN 201880075731 A CN201880075731 A CN 201880075731A CN 111372755 A CN111372755 A CN 111372755A
- Authority
- CN
- China
- Prior art keywords
- build
- additive manufacturing
- artificial intelligence
- neural network
- intelligence module
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
- B22F10/20—Direct sintering or melting
- B22F10/28—Powder bed fusion, e.g. selective laser melting [SLM] or electron beam melting [EBM]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
- B22F10/80—Data acquisition or data processing
- B22F10/85—Data acquisition or data processing for controlling or regulating additive manufacturing processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F12/00—Apparatus or devices specially adapted for additive manufacturing; Auxiliary means for additive manufacturing; Combinations of additive manufacturing apparatus or devices with other processing apparatus or devices
- B22F12/90—Means for process control, e.g. cameras or sensors
-
- 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
- B33Y30/00—Apparatus for additive manufacturing; Details thereof or accessories therefor
-
- 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
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F2203/00—Controlling
- B22F2203/03—Controlling for feed-back
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F2999/00—Aspects linked to processes or compositions used in powder metallurgy
-
- 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
- G05B2219/49007—Making, forming 3-D object, model, surface
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Materials Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Optics & Photonics (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Analytical Chemistry (AREA)
- Plasma & Fusion (AREA)
- Powder Metallurgy (AREA)
Abstract
本发明公开了一种增材制造***,该增材制造***使用受过训练的人工智能模块作为闭回路控制结构的一部分,以用于在过程中调节初始构建参数集来改善部件质量。闭回路控制结构包括考虑过程中构建层图像的慢速控制回路,并且可包括考虑熔体池监测数据的快速控制回路。使用来自多个卷积神经网络(CNN)的输出训练人工智能模块,该多个卷积神经网络负责评估过程中捕获的构建层图像和过程后捕获的成品部件的图像。该过程后图像可包括分段成品部件的二维图像和成品部件的三维CAT扫描图像。
Description
技术领域
本发明涉及增材制造(AM)领域。
背景技术
AM机可用于根据逐层构建过程构建成品部件。例如,激光粉末床熔融AM机使用激光或电子束中的任一者来熔化和熔融粉末材料。粉末床熔融过程涉及使用辊或刀片将粉末材料薄层铺展在先前的层上,并且根据部件的所需几何形状以受控方式在粉末层上扫描激光或电子束以形成层。部件的几何计算机模型被转换为AM构建参数文件,其中AM机的各种控制参数被定义用于控制每个构建层的扫描和熔融操作。
虽然AM对于制造通过传统减材制造难以制造和/或耗时的部件以及对于在存在AM机的远程位置“按需”制造部件显示出良好的前景,但是对由AM制造的部件质量的担忧减缓了其在关键行业中的广泛采用。例如,由AM制造的部件有时表现出孔隙率、空隙和差的表面光洁度,因此妨碍AM在安全关键应用(诸如航空航天和医疗应用)中的接受度。这对成品AM部件的质量控制检查造成了额外的负担,特别是对于旨在用于安全关键应用的部件,诸如医疗设备和飞行器部件。
在各种出版物中已提出,可将人工智能应用于AM以改善成品部件的质量。然而,这些出版物缺乏关于如何将人工智能应用于AM以改善成品部件的质量的任何有用的细节或实际描述。
发明内容
本公开提供了根据AM构建过程用于在AM机中逐层构建部件的AM***,其中该***包括用于在过程中调节初始构建参数集的闭回路控制结构。如本文所用,术语“过程中”是指部件处于正在AM机中被构建的过程中的时间段。术语“过程中”与术语“过程后”不同,“过程后”在本文中用来指部件在AM机中已被构建之后的时间段。
本公开的闭回路控制结构包括具有受过训练的人工智能模块的慢速控制回路,并且还可包括具有状态机的快速控制回路。如本文所用,“慢速控制回路”意指具有整秒级的控制器增益更新周期的控制回路,并且“快速控制回路”意指具有微秒级的控制器增益更新周期的控制回路。受过训练的人工智能模块可以是具有循环人工神经网络的深度学习模块。
在一个实施方案中,AM***包括:熔体池监测***,该熔体池监测***被布置成采集表示在过程中由能量源形成的熔体池的实时熔体池数据;以及构建层图像传感器,该构建层图像传感器被布置成在过程中采集部件层的层图像。初始构建参数集、对应于构建过程的基于时间顺序的经调节构建参数、层图像以及熔体池数据作为输入被传输到慢速控制回路的受过训练的人工智能模块。熔体池数据可作为输入被传输到快速控制回路的状态机。
根据本公开,可使用来自第一卷积神经网络(CNN)和至少一个第二CNN的评估数据来训练受过训练的人工智能模块,该第一卷积神经网络被配置为评估过程中采集的层图像,该至少一个第二CNN被配置为评估过程后采集的成品零件的图像。例如,CNN可被配置成评估过程后采集的分段成品部件的二维图像,并且另一个CNN可被配置成评估过程后通过成品部件的计算机断层摄影(CT)扫描采集的部件的三维图像。
附图说明
本发明的实质和操作模式现在将结合附图在本发明的以下具体实施方式中更全面地描述,其中:
图1为根据本发明的实施方案形成的AM***的示意图;
图2为图1所示AM***的AM机的示意图;
图3为根据本发明的一个方面的基本闭回路AM控制***的框图,其中层图像由卷积神经网络(CNN)评估以提供反馈;
图4为根据本发明的一个方面的增强数据收集架构的框图,其中成品部件的过程后图像数据与AM机在过程中收集的数据相对应地收集;
图5为根据本发明的一个方面的可用于训练人工智能模块的训练架构的框图;并且
图6为表示循环神经网络(RNN)可如何接合到有限状态机(FSM)的简化示例的框图。
具体实施方式
图1中示出了根据本发明的实施方案形成的AM***10。AM***10包括AM机20,在图2中更详细地示出。AM机20可以是包括粉末贮存器22、粉末床24以及粉末刮刀26的类型的激光粉末床机的形式,部件P在该粉末床中构建,该粉末刮刀用于将新的粉末层从粉末贮存器22转移到粉末床24中。粉末贮存器的高度使用粉末递送致动器23调节,并且粉末床24的高度使用制造致动器25调节。AM机20还包括激光器28形式的能量源,以及扫描器***30,该扫描器***用于以受控方式在粉末床24中的每个新的粉末层上方从能量源28重新定向并扫描光束32以形成部件P。应当理解,光束30与粉末床24中的粉末层相互作用并形成后熔体池33,该后熔体池固化并与部件P熔融在一起以构建该部件。上述类型的AM机购自英国的雷尼绍公司(Renishaw plc of the United Kingdom)。
AM机20可配备有熔体池监测***35,该熔体池监测***具有一个或多个熔体池传感器37,这些熔体池传感器被布置成采集表示过程中的熔体池33的实时熔体池数据39。AM机20还配备有构建层图像传感器38,该构建层图像传感器被布置成采集过程中的部件层的层图像。另外,空间频率调制成像(SPIFI)可用于直接通过光束32收集关于熔体池33的状态的信息;参见例如Young、Michael D.等人的“具有来自空间光调制器的振幅或相位光栅的空间频率调制成像(Spatial Frequency Modulated Imaging(SPIFI)with amplitude orphase grating from a spatial light modulator)”,SPIE会议记录,第10069卷,id.100692P 8pp.(2017)。AM机20的各种组件连接到被配置为控制构建过程的基于微处理器的控制器21。
AM***10可包括构建参数配置模块40,该构建参数配置模块被编程为生成用于在AM机20中构建部件P的初始构建参数集。初始构建参数集可作为构建参数配置文件41存储在存储器中,该存储器可由AM机20的处理和控制电子器件访问。初始构建参数集41可至少部分地基于输入到构建参数配置模块40的部件P的几何模型。作为非限制性示例,该几何模型可被提供为描述部件P的一个或多个数字CAD/CAM文件,并且构建参数配置模块40可以是被编程为读取CAD/CAM模型信息并生成激光控制设置、扫描器运动控制命令、层厚度设置和用于操作AM机20以构建部件P的其他控制参数的计算机模块。构建参数配置模块40可以是AM机20的一部分,或者可以独立于AM机20并与其通信。用于根据CAD/CAM文件生成AM构建参数的可商购获得的软件的示例为购自比利时的Materialise N.V.公司(MaterialiseN.V.of Belgium)的MagicsTM数据制作软件。
AM***10包括用于在过程中调节初始构建参数集41的闭回路控制结构42。在图3所示的基本实施方案中,闭回路控制结构42包括CNN 46形式的受过训练的人工智能(AI)模块,该CNN被训练并被配置为评估由构建层图像传感器38在过程中采集的部件P的层图像48。在框50中使用由CNN 46提供的评估结果(该结果可指示每个捕获的层图像48与该层的预期或期望外观相对应的程度)来计算过程中AM机20的经调节构建参数,以在框52中继续构建过程时影响后续层的构建。评估结果可以是将每个构建层图像48分配到预先确定的类别(例如,非常好、良好、一般、差等)中的分类的形式。
在对应于图1的另一个实施方案中,闭回路控制结构42包括慢速控制回路54和快速控制回路58,该慢速控制回路具有深度学习循环AI模块56形式的受过训练的AI模块,该快速控制回路具有状态机60。
在慢速控制回路54中,由构建参数配置模块40生成的初始AM构建参数41被输入到深度学***、电压、电流等),由构建层图像传感器38在过程中采集的构建层图像48,以及由熔体池监测***35在过程中采集的熔体池数据39。熔体池数据39可在输入到深度学***均熔体池数据39。预处理可为可调节的以具有较短或较长的帧速率。
深度学***台上运行,并且这可显著改善AI模块的处理吞吐量。
在快速控制回路58中,可将熔体池数据39连同来自深度学习AI模块56的输出一起输入到状态机60。来自深度学习AI模块56的状态机输出可用作快速控制回路58的一部分,该快速控制回路可被配置为快速过程控制增益更新上的单独的状态可变内部控制回路。例如,可将来自上述LSTM的状态机输出输入到状态机60并用于促进熔体池控制的快速回路闭合。
在图6中,状态机60的简单示例被示出为具有如由Mealy FSM表示的三种不同状态,其中来自每种状态的输出取决于当前状态和对FSM的输入。这三种状态是“保持”,其中保持控制方案;“较低能量密度”(较低ED),其中控制方案有利于降低通过光束32输入到粉末床24的比能量密度(ED);以及“较高能量密度”(较高ED),其中控制方案有利于升高通过光束32输入到粉末床24的比能量密度。同样在该示例中,对FSM的输入是来自受过训练的RNN 56的输出,该输出预测熔体池33的状态。该预测是基于图5由图4的增强数据赋予RNN56的训练。
图6示例中的每种状态表示不同或改变的控制方案。这些控制方案可被实现为简单的增益控制反馈回路或被实现为复杂的随机最佳控制器。本领域的技术人员将认识到,这仅仅是用于控制快速回路58的状态机60可如何与来自RNN 56的输出进行接合的简化示例,并且许多其他的和更复杂的配置是可能的,包括不同的控制方案状态,以及这些控制方案状态改变底层控制器的许多可能的具体实施的方式。
如在图1中可见,来自受过训练的深度学习AI模块56的慢速回路反馈和来自状态机60的快速回路反馈可用于计算框50中的经调节AM构建参数,以用于以改善部件质量的方式操作AM机20。
现在参考图4和图5描述根据本发明的实施方案的训练深度学习AI模块56的方法。用于训练深度学习AI模块56的教师数据可通过操作AM机20收集以按图4所示的数据增强模式来构建部件。应当理解,负责评估过程中的构建层图像48的基本CNN 46可由一个或多个另外的CNN 72和82增强,该一个或多个另外的CNN被配置为评估在过程后采集的成品部件的图像,如框70和框80分别所示。实际图像48也可在构建层图像数据库49中收集。
在框70中,由AM机20构建的部件P在过程后被分段,例如通过切割该部件并以已知的层深度抛光暴露的截面,然后使用成像相机捕获暴露表面的二维(2D)图像74。然后可由CNN 72评估和分类过程后捕获的2D图像74。例如,可能的分类76可包括熔化不足、恰好合适和熔化过度。在给定层深度处的过程后2D图像可与过程中采集的层的相关联图像48直接相关。该关系可由软件应用程序控制,该软件应用程序被编程为同步图4中的数据增强以允许根据实际数据在重建的虚拟部件构建上训练RNN 56。虚拟部件构建的数量将仅受到多少可用数据用于收集的限制。
软件应用程序的虚拟部件构建方面可允许模拟受过训练的RNN 56将如何使用实际数据来起作用,并且可允许改进和/或验证集成计算材料工程(ICME)模型。另外,可使用虚拟构建数据来构建更好的预测模型,以将高级控制方案诸如模型预测控制(MPC)实施到图6所示的快速58回路控制方案中。
在框80中,例如使用计算机辅助断层摄影(CAT)设备在过程后扫描由AM机20构建的部件P,以捕获整个部件的三维(3D)图像84。然后可由CNN 82评估和分类过程后捕获的3D图像84。例如,分类86可指示成品部件的孔隙度的程度和/或成品部件中存在空隙的程度。
如上所述,可在构建层图像数据库49中收集过程中构建层图像48。还可收集其他的过程中数据以用于训练深度学习AI模块56。例如,由熔体池监测***35在过程中采集的快速过程熔体池数据39可存储在二进制数据库67中,并且在层正在制造时由AM机20生成的基于时间顺序的数据62可存储在基于时间顺序的参数数据库68中。
如图5所示,如结合图4所述收集的数据可用作输入以训练深度学习AI模块56。表征构建层图像48的CNN 46的输出可充当一个教师输入在训练操作模式下提供给深度学习AI模块56。类似地,分别表征过程后图像72和82的来自CNN 72和CNN 82的输出可充当另外的教师输入在训练操作模式期间提供给深度学习AI模块56。快速过程熔体池数据39可由预处理器64预处理,并且在训练操作模式期间输入到深度学习AI模块56。存储在基于时间顺序的参数数据库68中的基于时间顺序的数据62也可作为输入在训练操作模式期间提供给深度学习AI模块56。初始AM构建参数41可作为另外的输入在训练操作模式期间提供给深度学习AI模块56。
深度学习AI模块56的各种输入应正确同步以进行训练,并且必须有足够的可用数据以使训练有效。来自深度学习AI模块56的LSTM组件的输出可在训练操作模式期间提供给状态机60,以稍后在AM***10以常规生产模式操作时促进熔体池控制的快速回路闭合。对状态机60的输入提供记录,该记录可允许针对控制模拟来评估改变的控制方案状态(例如,在图6中),以帮助评估受过训练的RNN 56对快速控制回路58的影响。
使用如上所述的过程中信息和过程后信息训练AI模块56将使得能够根据与良好生产实践相关联的若干视角可靠地确定AM部件和对应的AM过程是否良好。用于部件构建的整个数据集将被捕获以用于生产记录。首先,可展示和认证用于制造部件的AM配置数据文件的完整性(即“数据完整性”)。第二,可展示和认证用于构建该部件的AM过程的完整性(即“过程完整性”)。第三,可展示和认证过程性能生成了具有高密度、最小孔隙度或无孔隙度以及良好内部晶粒结构的良好部件(即,“性能完整性”)。以类似的方式,所述的AM部件的过程认证可类似于用于提供医疗设备正根据规范正确运行的检验和确认证据的设计质量(DQ)、安装质量(IQ)、操作质量(OQ)和性能质量(PQ)量度。IQ、OQ和PQ分别类似于数据、过程和制造完整性。在这种情况下,正确AM构建文件的安装是IQ。实时验证过程完整性(OQ)正确,并且近乎实时验证制造完整性(PQ)将来自机器学习AI的过程中组件和过程后组件。机器学习AI模块56将使用良好度的量度来确定我们实际具有的良好度的程度(通过习得的过程中测量值和过程后测量值之间非线性关系的循环记忆),然后对该过程进行实时自动校正,使得良好度(通过非线性相关性间接估计)将最大化。DQ等同于与设计/构建文件相关联的AM设计规则检查,其可集成用于金属的ICME或一些其他基于物理的设计协议。
本发明旨在推进通过AM方法制造大型且复杂的组件。本发明将得到在增材制造机上制造的更高质量的部件并减少检查负担。
虽然已结合示例性实施方案描述了本发明,但具体实施方式并不旨在将本发明的范围限制于所述的特定形式。本发明旨在涵盖可包括在权利要求书的范围内的所述实施方案的此类替代形式、修改形式和等同形式。
Claims (8)
1.一种用于根据增材制造构建过程逐层构建部件的增材制造***,所述增材制造***包括:
增材制造机,所述增材制造机包括粉末床和能量源,其中相对于所述粉末床中的粉末层扫描来自所述能量源的能量束以通过熔融构建所述部件的每个层;
构建参数配置文件,所述构建参数配置文件存储用于在所述增材制造机中构建所述部件的初始构建参数集,其中所述初始构建参数集至少部分地基于所述部件的几何模型;
闭回路控制结构,所述闭回路控制结构用于在过程中调节所述初始构建参数集,所述闭回路控制结构包括具有受过训练的人工智能模块的慢速控制回路;和
构建层图像传感器,所述构建层图像传感器被布置成在过程中采集所述部件层的层图像;
其中所述初始构建参数集、对应于所述构建过程的基于时间顺序的经调节构建参数以及所述层图像作为输入被传输到所述受过训练的人工智能模块。
2.根据权利要求1所述的增材制造***,还包括:
快速控制回路,所述快速控制回路具有状态机;和
熔体池监测***,所述熔体池监测***被布置成采集表示在过程中由所述能量源形成的熔体池的实时熔体池数据;
其中所述熔体池数据作为输入被传输到所述受过训练的人工智能模块并且作为输入被传输到所述状态机。
3.根据权利要求1所述的增材制造***,其中使用来自第一卷积神经网络和至少一个第二卷积神经网络的评估数据训练所述受过训练的人工智能模块,所述第一卷积神经网络被配置为评估过程中采集的层图像,所述至少一个第二卷积神经网络被配置为评估过程后采集的成品部件的图像。
4.根据权利要求3所述的增材制造***,其中所述至少一个第二卷积神经网络包括被配置为评估分段部件的二维图像的卷积神经网络。
5.根据权利要求3所述的增材制造***,其中所述至少一个第二卷积神经网络包括被配置为评估部件的三维图像的卷积神经网络。
6.根据权利要求1所述的增材制造***,其中所述受过训练的人工智能模块是具有循环人工神经网络的深度学习模块。
7.一种训练人工智能模块以用于对增材制造机进行闭回路控制的方法,所述增材制造机能够操作以执行增材制造过程来构建部件,所述方法包括:
向所述人工智能模块输入对应于多个部件的增材制造构建参数配置文件;
向所述人工智能模块输入由所述增材制造机在过程中收集的基于时间顺序的参数数据;
向所述人工智能模块输入由卷积神经网络生成的构建层图像分类数据,所述卷积神经网络被配置为评估过程中捕获的构建层图像;
向所述人工智能模块输入由至少一个其他卷积神经网络生成的过程后图像分类数据,所述至少一个其他卷积神经网络被配置为评估过程后捕获的部件的图像;以及
使用所述人工智能模块评估所述增材制造构建参数配置文件、所述基于时间顺序的参数数据、所述构建层图像分类数据和所述过程后图像分类数据。
8.根据权利要求7所述的方法,还包括:
向所述人工智能模块输入由所述增材制造机在过程中收集的熔体池数据;以及
使用所述人工智能模块评估所述熔体池数据。
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201762608045P | 2017-12-20 | 2017-12-20 | |
US62/608,045 | 2017-12-20 | ||
PCT/US2018/065880 WO2019125970A1 (en) | 2017-12-20 | 2018-12-15 | Convolutional neural network evaluation of additive manufacturing images, and additive manufacturing system based thereon |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111372755A true CN111372755A (zh) | 2020-07-03 |
CN111372755B CN111372755B (zh) | 2022-02-18 |
Family
ID=66992803
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201880075731.9A Active CN111372755B (zh) | 2017-12-20 | 2018-12-15 | 增材制造图像的卷积神经网络评估以及以其为基础的增材制造*** |
Country Status (6)
Country | Link |
---|---|
US (1) | US11112771B2 (zh) |
EP (1) | EP3727798A4 (zh) |
JP (1) | JP7128278B2 (zh) |
CN (1) | CN111372755B (zh) |
CA (1) | CA3081678C (zh) |
WO (1) | WO2019125970A1 (zh) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210150313A1 (en) * | 2019-11-15 | 2021-05-20 | Samsung Electronics Co., Ltd. | Electronic device and method for inference binary and ternary neural networks |
CN112916987A (zh) * | 2021-02-02 | 2021-06-08 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制方法和*** |
CN113000860A (zh) * | 2021-02-26 | 2021-06-22 | 西安理工大学 | 一种激光增材制造中的扫描点温度预测控制方法 |
CN113084193A (zh) * | 2021-03-22 | 2021-07-09 | 中国人民解放军空军工程大学 | 一种激光选区熔化技术原位质量综合评价方法 |
CN114619119A (zh) * | 2022-03-29 | 2022-06-14 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制*** |
US12039430B2 (en) * | 2019-11-15 | 2024-07-16 | Samsung Electronics Co., Ltd. | Electronic device and method for inference binary and ternary neural networks |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3850300A2 (en) | 2018-10-19 | 2021-07-21 | Inkbit, LLC | High-speed metrology |
JP2022506523A (ja) | 2018-11-02 | 2022-01-17 | インクビット, エルエルシー | インテリジェント付加製造方法 |
US11354466B1 (en) | 2018-11-02 | 2022-06-07 | Inkbit, LLC | Machine learning for additive manufacturing |
EP3856481A2 (en) | 2018-11-16 | 2021-08-04 | Inkbit, LLC | Inkjet 3d printing of multi-component resins |
AU2020205973A1 (en) | 2019-01-08 | 2021-07-15 | Inkbit, LLC | Reconstruction of surfaces for additive manufacturing |
EP3884237A1 (en) | 2019-01-08 | 2021-09-29 | Inkbit, LLC | Depth reconstruction in additive fabrication |
US20220281177A1 (en) * | 2019-08-27 | 2022-09-08 | The Regents Of The University Of California | Ai-powered autonomous 3d printer |
EP4028228A4 (en) * | 2019-09-10 | 2023-09-27 | Nanotronics Imaging, Inc. | SYSTEMS, METHODS AND MEDIA FOR MANUFACTURING PROCESSES |
JP7320884B2 (ja) | 2019-09-10 | 2023-08-04 | ナノトロニクス イメージング インコーポレイテッド | 製造プロセスのためのシステム、方法、および媒体 |
US10994477B1 (en) | 2019-11-01 | 2021-05-04 | Inkbit, LLC | Optical scanning for industrial metrology |
US11712837B2 (en) | 2019-11-01 | 2023-08-01 | Inkbit, LLC | Optical scanning for industrial metrology |
DE102020102863A1 (de) * | 2020-02-05 | 2021-08-05 | Festo Se & Co. Kg | Parametrierung einer Komponente in der Automatisierungsanlage |
US10926473B1 (en) | 2020-02-20 | 2021-02-23 | Inkbit, LLC | Multi-material scanning for additive fabrication |
CN117283873A (zh) * | 2020-06-10 | 2023-12-26 | 戴弗根特技术有限公司 | 用于制造产品的装置和方法 |
US10994490B1 (en) | 2020-07-31 | 2021-05-04 | Inkbit, LLC | Calibration for additive manufacturing by compensating for geometric misalignments and distortions between components of a 3D printer |
US20220134647A1 (en) * | 2020-11-02 | 2022-05-05 | General Electric Company | In-process optical based monitoring and control of additive manufacturing processes |
EP4319967A1 (en) | 2021-04-06 | 2024-02-14 | Abb Schweiz Ag | Method of producing three-dimensional object, control system and additive manufacturing device |
CA3234882A1 (en) * | 2021-10-15 | 2023-04-20 | Christopher Edward COUCH | Manufacturing equipment control via predictive sequence to sequence models |
CN114226757B (zh) * | 2021-12-14 | 2023-04-11 | 上海交通大学 | 一种融合温度和图像信息的激光ded制造控制***和方法 |
EP4272932A1 (en) * | 2022-05-06 | 2023-11-08 | United Grinding Group Management AG | Manufacturing assistance system for an additive manufacturing system |
CN116408462B (zh) * | 2023-04-12 | 2023-10-27 | 四川大学 | 一种激光金属增材沉积内部孔隙状态实时预测方法 |
CN116559196B (zh) * | 2023-05-06 | 2024-03-12 | 哈尔滨工业大学 | 一种电弧增材制造缺陷检测***及方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140271964A1 (en) * | 2013-03-15 | 2014-09-18 | Matterrise, Inc. | Three-Dimensional Printing and Scanning System and Method |
WO2017039444A1 (en) * | 2015-08-31 | 2017-03-09 | Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno | Method and apparatus for layerwise production of a tangible object. |
CN107097407A (zh) * | 2017-06-29 | 2017-08-29 | 上海大学 | 智能监控3d打印的喷头工作状态的方法、应用和装置 |
CN107402217A (zh) * | 2017-07-27 | 2017-11-28 | 哈尔滨工业大学(威海) | 基于视觉传感的激光增材制造缺陷的在线诊断方法 |
CN107457996A (zh) * | 2016-06-03 | 2017-12-12 | 波音公司 | 用于直接写入***的实时检查和校正技术 |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7771417B2 (en) * | 2005-02-24 | 2010-08-10 | Iridex Corporation | Laser system with short pulse characteristics and its methods of use |
WO2012146943A2 (en) * | 2011-04-27 | 2012-11-01 | Within Technologies Ltd | Improvements for 3d design and manufacturing systems |
US20130015596A1 (en) * | 2011-06-23 | 2013-01-17 | Irobot Corporation | Robotic fabricator |
US9855698B2 (en) * | 2013-08-07 | 2018-01-02 | Massachusetts Institute Of Technology | Automatic process control of additive manufacturing device |
ZA201505683B (en) * | 2014-08-15 | 2017-11-29 | Central Univ Of Technology Free State | Additive manufacturing system and method |
US20170002467A1 (en) * | 2015-07-02 | 2017-01-05 | Fei Company | Adaptive control for charged particle beam processing |
CN107921536A (zh) * | 2015-07-18 | 2018-04-17 | 伏尔肯模型公司 | 通过空间控制的材料熔合的增材制造 |
US11079745B2 (en) | 2015-11-25 | 2021-08-03 | Lawrence Livermore National Security, Llc | Rapid closed-loop control based on machine learning |
US11179894B2 (en) * | 2016-05-12 | 2021-11-23 | Hewlett-Packard Development Company, L.P. | Managing thermal contributions between layers during additive manufacturing |
US10414149B2 (en) * | 2016-10-21 | 2019-09-17 | Microsoft Technology Licensing, Llc | Material estimate for fabrication of three-dimensional object |
US10234848B2 (en) * | 2017-05-24 | 2019-03-19 | Relativity Space, Inc. | Real-time adaptive control of additive manufacturing processes using machine learning |
US11511373B2 (en) * | 2017-08-25 | 2022-11-29 | Massachusetts Institute Of Technology | Sensing and control of additive manufacturing processes |
US11027362B2 (en) * | 2017-12-19 | 2021-06-08 | Lincoln Global, Inc. | Systems and methods providing location feedback for additive manufacturing |
-
2018
- 2018-12-15 CN CN201880075731.9A patent/CN111372755B/zh active Active
- 2018-12-15 CA CA3081678A patent/CA3081678C/en active Active
- 2018-12-15 WO PCT/US2018/065880 patent/WO2019125970A1/en unknown
- 2018-12-15 EP EP18890178.9A patent/EP3727798A4/en active Pending
- 2018-12-15 US US16/955,334 patent/US11112771B2/en active Active
- 2018-12-15 JP JP2020529480A patent/JP7128278B2/ja active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140271964A1 (en) * | 2013-03-15 | 2014-09-18 | Matterrise, Inc. | Three-Dimensional Printing and Scanning System and Method |
WO2017039444A1 (en) * | 2015-08-31 | 2017-03-09 | Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno | Method and apparatus for layerwise production of a tangible object. |
CN107457996A (zh) * | 2016-06-03 | 2017-12-12 | 波音公司 | 用于直接写入***的实时检查和校正技术 |
CN107097407A (zh) * | 2017-06-29 | 2017-08-29 | 上海大学 | 智能监控3d打印的喷头工作状态的方法、应用和装置 |
CN107402217A (zh) * | 2017-07-27 | 2017-11-28 | 哈尔滨工业大学(威海) | 基于视觉传感的激光增材制造缺陷的在线诊断方法 |
Non-Patent Citations (2)
Title |
---|
JAN PETRICH: "《MACHINE LEARNING FOR DEFECT DETECTION FOR PBFAM USING HIGH RESOLUTION LAYERWISE IMAGING COUPLED WITH POST-BUILD CT SCANS》", 《SOLID FREEFORM FABRICATION 2017:AN ADDITIVE MANUFACTURING CONFERENCE》 * |
VOLKER RENKEN: "《Development of an adaptive,self-learning control concept for an additive manufacturing process》", 《CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210150313A1 (en) * | 2019-11-15 | 2021-05-20 | Samsung Electronics Co., Ltd. | Electronic device and method for inference binary and ternary neural networks |
US12039430B2 (en) * | 2019-11-15 | 2024-07-16 | Samsung Electronics Co., Ltd. | Electronic device and method for inference binary and ternary neural networks |
CN112916987A (zh) * | 2021-02-02 | 2021-06-08 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制方法和*** |
CN112916987B (zh) * | 2021-02-02 | 2022-02-15 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制方法和*** |
CN113000860A (zh) * | 2021-02-26 | 2021-06-22 | 西安理工大学 | 一种激光增材制造中的扫描点温度预测控制方法 |
CN113084193A (zh) * | 2021-03-22 | 2021-07-09 | 中国人民解放军空军工程大学 | 一种激光选区熔化技术原位质量综合评价方法 |
CN113084193B (zh) * | 2021-03-22 | 2022-10-21 | 中国人民解放军空军工程大学 | 一种激光选区熔化技术原位质量综合评价方法 |
CN114619119A (zh) * | 2022-03-29 | 2022-06-14 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制*** |
CN114619119B (zh) * | 2022-03-29 | 2023-01-13 | 北京理工大学 | 一种电弧增材制造在线监测及实时控制*** |
Also Published As
Publication number | Publication date |
---|---|
WO2019125970A1 (en) | 2019-06-27 |
CN111372755B (zh) | 2022-02-18 |
CA3081678C (en) | 2022-08-16 |
JP7128278B2 (ja) | 2022-08-30 |
US11112771B2 (en) | 2021-09-07 |
EP3727798A1 (en) | 2020-10-28 |
EP3727798A4 (en) | 2021-10-27 |
CA3081678A1 (en) | 2019-06-27 |
US20210089003A1 (en) | 2021-03-25 |
JP2021504197A (ja) | 2021-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111372755B (zh) | 增材制造图像的卷积神经网络评估以及以其为基础的增材制造*** | |
CN109203479B (zh) | 用于先进增材制造的***和方法 | |
JP7174108B2 (ja) | 付加的に製造された部品の微細構造を制御するための付加製造付加製造システム及び方法 | |
US10500675B2 (en) | Additive manufacturing systems including an imaging device and methods of operating such systems | |
US12017301B2 (en) | Systems and methods for compression, management, and analysis of downbeam camera data for an additive machine | |
TWI774999B (zh) | 透過電子裝置監測積層製造的方法、三維列印裝置及相關電腦可讀媒體 | |
US10520919B2 (en) | Systems and methods for receiving sensor data for an operating additive manufacturing machine and mapping the sensor data with process data which controls the operation of the machine | |
US10635085B2 (en) | Systems and methods for receiving sensor data for an operating additive manufacturing machine and adaptively compressing the sensor data based on process data which controls the operation of the machine | |
Cannizzaro et al. | In-situ defect detection of metal additive manufacturing: an integrated framework | |
CN113613813A (zh) | 基于热模型和传感器数据在增材制造过程中校正构建参数的***和方法 | |
JP2021513158A (ja) | 熱及び歪みモデリングを用いて付加製造スキャンパスを生成する方法及び装置 | |
Wegener et al. | A conceptual vision for a bio-intelligent manufacturing cell for Selective Laser Melting | |
JP6758532B1 (ja) | 数値制御装置および付加製造装置の制御方法 | |
Guo et al. | A deep-learning-based surrogate model for thermal signature prediction in laser metal deposition | |
JP2021088736A (ja) | 品質予測システム | |
WO2023059627A1 (en) | Learning closed-loop control policies for manufacturing | |
Yang | Model-based predictive analytics for additive and smart manufacturing | |
EP4249153A1 (en) | Tool for scan path visualization and defect distribution prediction | |
US20220291661A1 (en) | Additive manufacturing simulations | |
Chaturvedi et al. | Data-Driven Models in Machine Learning: An Enabler of Smart Manufacturing | |
US11858042B2 (en) | Open loop parameter optimization for additive manufacturing | |
Kumar et al. | Applications of Artificial Intelligence and Machine Learning Using Additive Manufacturing Techniques | |
Liao-McPherson et al. | Layer-to-Layer Melt Pool Control in Laser Power Bed Fusion | |
Upadhyay | Fast to run model for thermal fields during metal additive manufacturing simulations | |
Jyeniskhan et al. | Exploring the Integration of Digital Twin and Additive Manufacturing Technologies |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |