en
×

分享给微信好友或者朋友圈

使用微信“扫一扫”功能。
作者简介:

周安,女,1998年出生,硕士研究生。主要研究方向为激光材料表面工程。E-mail:1178435126@qq.com

通讯作者:

刘秀波,男,1968年出生,博士,教授,博士研究生导师。主要研究方向为表面工程与摩擦学、激光加工。E-mail:liuxiubosz@163.com

中图分类号:TG665;TP216

DOI:10.11933/j.issn.1007−9289.20221212001

参考文献 1
PENG L M,SHAN Q C,WU Y J,et al.Additive manufacturing of magnesium alloys by selective laser melting technology:A review[J].Acta Metallurgica Sinca,2023,59(1):31-54.
参考文献 2
王虎,彭云,赵琳,等.选区熔化3D打印TiAl基合金的研究现状及展望[J].表面技术,2021,50(1):173-186.WANG Hu,PENG Yun,ZHAO Lin,et al.Research status and prospect of selection melting 3D printing TiAl-based alloys[J].Surface Technology,2021,50(1):173-186.(in Chinese)
参考文献 3
KURZYNOWSKI T,PAWLAK A,SMOLINA I.The potential of SLM technology for processing magnesium alloys in aerospace industry[J].Archives of Civil and Mechanical Engineering,2020,20(1):1-13.
参考文献 4
JAFARI D,WITS W W.The utilization of selective laser melting technology on heat transfer devices for thermal energy conversion applications:A review[J].Renewable and Sustainable Energy Reviews,2018,91:420-442.
参考文献 5
褚清坤,余春风,邓朝阳,等.TiC 含量对激光选区熔化 Inconel 625 合金微观组织及表面摩擦磨损性能的影响[J].中国表面工程,2021,34(1):76-84.CHU Qingkun,YU Chunfeng,DENG Chaoyang,et al.Effect of TiC content on microstructure and surface friction and wear properties of Inconel 625 alloy melted by laser selective area[J].China Surface Engineering,2021,34(1):76-84.(in Chinese)
参考文献 6
VOLPP J.Spattering effects during selective laser melting[J].Journal of Laser Applications,2020,32(2):022023.
参考文献 7
刘小辉,刘允中.激光选区熔化成形高强铝合金晶粒细化抑制裂纹研究现状[J].材料工程,2022,50(8):1-16.LIU Xiaohui,LIU Yunzhong.Research status of crack suppression of grain refinement of high-strength aluminum alloy by laser selective melting[J].Journal of Materials Engineering,2022,50(8):1-16.(in Chinese)
参考文献 8
CHEN J,HOU W,WANG X.Microstructure,porosity and mechanical properties of selective laser melted AlSi10Mg[J].Chinese Journal of Aeronautics,2020,33(7):2043-2054.
参考文献 9
WU B,JI X,ZHOU J,et al.In situ monitoring methods for selective laser melting additive manufacturing process based on images—A review[J].China Foundry,2021,18(4):265-285.
参考文献 10
KWON O,KIM H G,HAM M J,et al.A deep neural network for classification of melt-pool images in metal additive manufacturing[J].Journal of Intelligent Manufacturing,2020,31(2):375-386.
参考文献 11
NANDI S K,KUMAR R,AGRAWAL A.Computationally inexpensive semi-analytical thermal model to predict melt-pool dimensions for a single-track in selective laser melting[J].Journal of Manufacturing Processes,2022,80:469-479.
参考文献 12
ITO K,KUSANO M,DEMURA M,et al.Detection and location of microdefects during selective laser melting by wireless acoustic emission measurement[J].Additive Manufacturing,2021,40:101915.
参考文献 13
刘萌.3D 打印SLM技术在机械自动化加工中的应用研究[J].数字技术与应用,2015,33(4):107.LIU Meng.Application of 3D printing SLM technology in mechanical automation processing[J].Digital Technology and Application,2015,33(4):107.(in Chinese)
参考文献 14
YE D,HONG G S,ZHANG Y,et al.Defect detection in selective laser melting technology by acoustic signals with deep belief networks[J].The International Journal of Advanced Manufacturing Technology,2018,96(5):2791-2801.
参考文献 15
NAGARAJAN B,HU Z,SONG X,et al.Development of micro selective laser melting:The state of the art and future perspectives[J].Engineering,2019,5(4):702-720.
参考文献 16
龙旭,贾啟普,李娇,等.选区激光熔化成形TC4钛合金力学性能及其工艺关联性[J].中国表面工程,2022,35(2):215-223.LONG Xu,JIA Qipu,LI Jiao,et al.Mechanical properties and process correlation of TC4 titanium alloy formed by selective laser melting[J].China Surface Engineering,2022,35(2):215-223.(in Chinese)
参考文献 17
刘文浩,陈燕,王杰,等.SLM 成型零件型腔内表面电解辅助磁粒研磨加工研究[J].中国表面工程,2021,34(3):100-109.LIU Wenhao,CHEN Yan,WANG Jie,et al.Research on electrolytic-assisted magnetic particle grinding processing of inner surface of SLM molded parts[J].China Surface Engineering,2021,34(3):100-109.(in Chinese)
参考文献 18
李忠利,杜东方,雷盛.镍基合金激光选区熔化成形的缺陷形成及其控制综述[J].锻压装备与制造技术,2022,57(5):97-100.LI Zhongli,DU Dongfang,LEI Sheng.Review of defect formation and control of laser selective melting and forming of nickel-based alloy[J].Forging Equipment and Manufacturing Technology,2022,57(5):97-100.(in Chinese)
参考文献 19
伍方.选择性激光熔化纯钨材料的成形技术研究[D].上海:上海大学,2021.WU Fang.Research on forming technology of selective laser melting of pure tungsten materials[D].Shanghai:Shanghai University,2021.(in Chinese)
参考文献 20
毕轩.不锈钢选区激光熔化熔池及微观组织演化研究 [D].大连:大连理工大学,2021.BI Xuan.Study on laser melting pool and microscopic tissue evolution in stainless steel selection[D].Dalian:Dalian University of Technology,2021.(in Chinese)
参考文献 21
YADAV P,RIGO O,ARVIEU C,et al.In situ monitoring systems of the SLM process:On the need to develop machine learning models for data processing[J].Crystals,2020,10(6):524-550.
参考文献 22
李文龙,戈海龙,任远,等.图像处理技术在激光熔池温度检测的应用[J].激光技术,2018,42(5):599-604.LI Wenlong,GE Hailong,REN Yuan,et.al.Application of image processing technology in temperature detection of laser molten pool[J].Laser Technology,2018,42(5):599-604.(in Chinese)
参考文献 23
王奉涛,杨守华,吕秉华,等.金属增材制造过程熔池动态监测研究综述[J/OL].计算机集成制造系统:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.WANG Fengtao,YANG Shouhua,LV Binghua,et al.Research review on dynamic monitoring of melt pool in metal additive manufacturing process[J/OL].Computer Integrated Manufacturing System:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.(in Chinese)
参考文献 24
马婷.红外热成像仪原理与应用分析[C]//第十四届宁夏青年科学家论坛石化专题论坛论文集,2018-07-24,宁夏,2018:323-325,329.MA Ting.Principle and application analysis of infrared thermal imager[C]//Proceedings of the 14th Ningxia Young Scientists Forum Petrochemical Symposium,July 24,2018,Ningxia,2018:323-325,329.(in Chinese)
参考文献 25
CHENG B,LYDON J,COOPER K,et al.Infrared thermal imaging for melt pool analysis in SLM:A feasibility investigation[J].Virtual and Physical Prototyping,2018,13(1):8-13.
参考文献 26
BARTLETT J L,HEIM F M,MURTY Y V,et al.In situ defect detection in selective laser melting via full-field infrared thermography[J].Additive Manufacturing,2018,24:595-605.
参考文献 27
CLIJSTERS S,CRAEGHS T,BULS S,et al.In situ quality control of the selective laser melting process using a high-speed,real-time melt pool monitoring system[J].The International Journal of Advanced Manufacturing Technology,2014,75(5):1089-1101.
参考文献 28
ZHANG K,LIU T,LIAO W,et al.Photodiode data collection and processing of molten pool of alumina parts produced through selective laser melting[J].Optik,2018,156:487-497.
参考文献 29
BARRIOBERO-VILA P,ARTZT K,STARK A,et al.Mapping the geometry of Ti-6Al-4V:From martensite decomposition to localized spheroidization during selective laser melting[J].Scripta Materialia,2020,182:48-52.
参考文献 30
ABOUELNOUR Y,GUPTA N.In-situ monitoring of sub-surface and internal defects in additive manufacturing:A review[J].Materials & Design,2022,222:111063.
参考文献 31
REN C G,LO Y L,TRAN H C,et al.Emissivity calibration method for pyrometer measurement of melting pool temperature in selective laser melting of stainless steel 316L[J].The International Journal of Advanced Manufacturing Technology,2019,105(1):637-649.
参考文献 32
GUTKNECHT K,HAFERKAMP L,CLOOTS M,et al.Determining process stability of laser powder bed fusion using pyrometry[J].Procedia Cirp,2020,95:127-132.
参考文献 33
LUONG M P.Fatigue limit evaluation of metals using an infrared thermographic technique[J].Mechanics of Materials,1998,28(1-4):155-163.
参考文献 34
张勇.基于机器视觉的选区激光熔化成型质量监测的研究[D].厦门:厦门理工学院,2020.ZHANG Yong.Research on quality monitoring of selective laser melting molding based on machine vision[D].Xiamen:Xiamen University of Technology,2020.(in Chinese)
参考文献 35
王晓玮.熔池图像高速采集与实时处理技术研究[D].成都:电子科技大学,2020.WANG Xiaowei.Research on high-speed acquisition and real-time processing technology of molten pool images[D].Chengdu:University of Electronic Science and Technology of China,2020.(in Chinese)
参考文献 36
魏芬,吴怡,徐世武.基于机器学习与多光电二极管的可见光定位的实验研究[J/OL].激光与光电子学进展:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.WEI Fen,WU Yi,XU Shiwu.Experimental study on visible light localization based on machine learning and multiple photodiodes[J/OL].Laser and Optoelectronics:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.(in Chinese)
参考文献 37
MA P,HE X,WANG A.Design of online measurement system for molten pool morphology in selective laser melting(SLM)process[C]//2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture(AIAM),October 23-25,2021,Manchester,United Kingdom,IEEE,2021:198-204.
参考文献 38
赵德陈,林峰.金属粉末床熔融工艺在线监测技术综述[J].中国机械工程,2018,29(17):2100-2110,2118.ZHAO Dechen,LIN Feng.Review of online monitoring technology of metal powder bed melting process[J].China Mechanical Engineering,2018,29(17):2100-2110,2118.(in Chinese)
参考文献 39
KANKO J A,SIBLEY A P,FRASER J M.In situ morphology-based defect detection of selective laser melting through inline coherent imaging[J].Journal of Materials Processing Technology,2016,231:488-500.
参考文献 40
MAZZOLENI L,CAPRIO L,PACHER M,et al.External illumination strategies for melt pool geometry monitoring in SLM [J].JOM,2019,71(3):928-937.
参考文献 41
LIU Y,ZHANG M,SHI W,et al.Study on performance optimization of 316L stainless steel parts by high-efficiency selective laser melting[J].Optics & Laser Technology,2021,138:106872.
参考文献 42
朱锟鹏,王齐胜,林昕,等.基于熔池运动特征的选区激光熔融过程状态检测方法[J].计算机集成制造系统,2021,27(12):3403-3415.ZHU Kunpeng,WANG Qisheng,LIN Xin,et al.Selection laser melting process state detection method based on molten pool motion characteristics[J].Computer Integrated Manufacturing Systems,2021,27(12):3403-3415.(in Chinese)
参考文献 43
LI J,CAO L,XU J,et al.In situ porosity intelligent classification of selective laser melting based on coaxial monitoring and image processing[J].Measurement,2022,187:110232.
参考文献 44
LIN X,WANG Q,FUH J Y H,et al.Motion feature based melt pool monitoring for selective laser melting process[J].Journal of Materials Processing Technology,2022,303:117523.
参考文献 45
MODARESIALAM M,ROOZBAHANI H,ALIZADEH M,et al.In-situ monitoring and defect detection of selective laser melting process and impact of process parameters on the quality of fabricated SS 316L[J].IEEE Access,2022,10:46100-46113.
参考文献 46
LI J,ZHOU Q,CAO L,et al.A convolutional neural network-based multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Systems,2022,64:429-442.
参考文献 47
ANSARI M A,CRAMPTON A,GARRARD R,et al.A convolutional neural network(CNN)classification to identify the presence of pores in powder bed fusion images[J].The International Journal of Advanced Manufacturing Technology,2022,120(7):5133-5150.
参考文献 48
CHIEN C F,DAUZÈRE-PÉRÈS S,HUH W T,et al.Artificial intelligence in manufacturing and logistics systems:algorithms,applications,and case studies[J].International Journal of Production Research,2020,58(9):2730-2731.
参考文献 49
XING W,LYU T,CHU X,et al.Recognition and classification of single melt tracks using deep neural network:A fast and effective method to determine process windows in selective laser melting[J].Journal of Manufacturing Processes,2021,68:1746-1757.
参考文献 50
XING W,CHU X,LYU T,et al.Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process[J].Journal of Manufacturing Processes,2022,74:486-499.
参考文献 51
FANG Q,TAN Z,LI H,et al.In-situ capture of melt pool signature in selective laser melting using U-Net-based convolutional neural network[J].Journal of Manufacturing Processes,2021,68:347-355.
参考文献 52
YUAN B,GIERA B,GUSS G,et al.Semi-supervised convolutional neural networks for in-situ video monitoring of selective laser melting[C]//2019 IEEE Winter Conference on Applications of Computer Vision(WACV).January 7-11,2019,Waikoloa Village,HI,USA:IEEE,2019:744-753.
参考文献 53
RIEDER H,DILLHÖFER A,SPIES M,et al.Online monitoring of additive manufacturing processes using ultrasound[C]//Proceedings of the 11th European Conference on Non-destructive Testing.October 6-10,2014,Prague,Czech Republic 2014,1:2194-2201.
参考文献 54
WANG H,LI B,XUAN F Z.Acoustic emission for in situ process monitoring of selective laser melting additive manufacturing based on machine learning and improved variational modal decomposition[J].The International Journal of Advanced Manufacturing Technology,2022,122(5-6):2277-2292.
参考文献 55
LI J,ZHANG X,ZHOU Q,et al.A feature-level multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Processes,2022,84:913-926.
参考文献 56
FLEMING T G,NESTOR S G L,ALLEN T R,et al.Tracking and controlling the morphology evolution of 3D powder-bed fusion in situ using inline coherent imaging[J].Additive Manufacturing,2020,32:100978.
参考文献 57
VASILESKA E,DEMIR A G,COLOSIMO B M,et al.Layer-wise control of selective laser melting by means of inline melt pool area measurements[J].Journal of Laser Applications,2020,32(2):022057.
参考文献 58
陈楠.基于温度场检测的激光选区熔化实时扫描策略研究[D].武汉:华中科技大学,2020.CHEN Nan.Research on real-time scanning strategy of laser selection melting based on temperature field detection[D].Wuhan:Huazhong University of Science and Technology,2020.(in Chinese)
参考文献 59
LIN X,ZHU K,FUH J Y H,et al.Metal-based additive manufacturing condition monitoring methods:from measurement to control[J].ISA Transactions,2022,120:147-166.
参考文献 60
PENG X,KONG L.Development of a multi-sensor system for defects detection in additive manufacturing[J].Optics Express,2022,30(17):30640-30665.
参考文献 61
HONARVAR F,VARVANI-FARAHANI A.A review of ultrasonic testing applications in additive manufacturing:Defect evaluation,material characterization,and process control[J].Ultrasonics,2020,108:106227.
参考文献 62
吴世彪,窦文豪,杨永强,等.面向激光选区熔化金属增材制造的检测技术研究进展[J].精密成形工程,2019,11(4):37–50.WU Shibiao,DOU Wenhao,YANG Yongqiang,et al.Research progress on detection technology for additive manufacturing of melted metal for laser selection[J].Precision Forming Engineering,2019,11(4):37-50.(in Chinese)
参考文献 63
曹龙超,周奇,韩远飞,等.激光选区熔化增材制造缺陷智能监测与过程控制综述[J].航空学报,2021,42(10):199-233.CAO Longchao,ZHOU Qi,HAN Yuanfei,et al.A review of intelligent monitoring and process control of defects in laser selective melting additive manufacturing[J].Chinese Journal of Aeronautics and Astronautics,2021,42(10):199-233.(in Chinese)
目录contents

    摘要

    选区激光熔化(SLM)作为现代工业构件制造的一种主流技术,广泛应用于汽车、航空航天及医学等领域,对 SLM 工艺的监测及闭环控制方式进行系统梳理变得极为重要。针对 SLM 技术原理及熔池变化,从 SLM 成形过程中的熔池温度和形貌特征综述选区激光熔化监测技术发展进程及不足,分析闭环反馈技术的研究现状。研究表明:SLM 加工过程中熔池的变化状态是影响成形件质量的重要因素,通过光信号、声信号或多信号传感器可对熔池状态进行有效监测,而闭环控制需要算法分析、机器学习及传感器的协同配合才能实现实时反馈及控制。根据当前监测技术的实时性较差及系统反馈控制不够完善等问题,提出未来智能监测技术与实时闭环控制等发展方向,可为未来 SLM 成形高质量零件提供参考借鉴。

    Abstract

    Selective laser melting(SLM) is a prominent technology in modern industrial-component manufacturing, and it is widely used in automotive, aerospace, medical, and other fields. However, its shortcomings, such as limited stability and defects, hinder its potential industrial applications. Hence, a systematic review of in-process monitoring techniques and closed-loop control methods for SLM is crucial. The SLM system should be equipped with in-situ monitoring devices that can measure relevant quantities during the machining process. Furthermore, automated detection and localization of defects should be examined via in-process data analytics and statistical monitoring techniques. The SLM process involves rapid melting and solidification of the material, creating molten pool flows that can form defects such as porosities, incomplete fusion holes, and cracks. Monitoring techniques can effectively address these challenges by observing the melt-pool status and defects over time. Moreover, monitoring and sensing processes are widely employed in various industries for quality assurance, which can enhance machine uptime and reliability. Process monitoring is increasingly being adopted in SLM through the use of process sensors that record a broad range of optical, acoustic, and thermal signals. Consequently, the capability to acquire these signals holistically, combined with intelligence-based machine control, has the potential to enable SLM technology to replace traditional fabrication techniques. This review examines the research status of SLM technology principles and characteristics of the SLM process. Furthermore, the development process and limitations of monitoring technology for SLM are reviewed based on the melt pool temperature and morphology in the machining process, and the research status of closed-loop feedback is analyzed. The review suggests that the changing state of the molten pool is a crucial factor affecting the quality of the formed part in the SLM process. The molten pool state can be effectively monitored using optical signals, acoustic signals, or multisignal sensors. Meanwhile, closed-loop control requires algorithm analysis, machine learning, and sensor coordination to realize real-time feedback and control. To enable real-time feedback and reduce feedback transmission time, a comprehensive real-time feedback system can be established by integrating multiple sensors that can accurately monitor the interior of the molten pool. Currently, there are challenges with the poor real-time performance of existing monitoring technologies and imperfect system feedback control. The research status and future development directions of intelligent monitoring techniques and real-time closed-loop control are proposed. As monitoring technology continues to develop, machine learning can be leveraged to extract new features from input data distributions (such as images and videos), laying the foundation for future intelligent SLM process monitoring. To enhance the intelligence and automation level of the forming system, real-time monitoring and processing technology should be combined with SLM technology to minimize feedback and response times. This is vital for reducing resource waste in secondary processing and remanufacturing. Notably, ultrasonic monitoring has significant potential in monitoring systems that can dynamically analyze internal changes during the forming process and predict part quality. This study addresses a gap in the field of SLM monitoring techniques and offers a reference for producing high-quality parts using SLM technology in the future.

  • 0 前言

  • 增材制造技术的不断发展对所制造零件的硬度、韧性及抗冲击性等力学性能要求日趋提高。选区激光熔化(Selective laser melting,SLM)这一新型技术,不但能够满足材料、结构和功能的一体化设计,直接制造出终端金属产品,还能够实现复杂结构零部件的生产[1],克服生产周期长、加工难度大、综合成本高等技术难题,被广泛应用于航空航天、模具制造及医学等领域[2–4]。

  • SLM 技术能够制造出高性能、结构复杂的零件[5],但由于激光加工的物理本质决定了它在制备过程中仍存在较多问题,其中成形件的缺陷,如飞溅[6]、裂纹[7]和孔隙[8]等是制约其发展和应用的瓶颈。因此及时监测并抑制加工过程中存在的缺陷,可有效地提升 SLM 工艺成形质量,消除上述缺陷对该技术发展的限制。

  • SLM 过程监测是指在加工过程中对成形状态和缺陷进行及时监测。通过对 SLM 过程监测,能够实时了解熔池温度形态变化及缺陷的存在。而且,将监测设备与 SLM 成形设备相结合,可为反馈控制提供成形件的质量信息,从而在线调整工艺参数消除缺陷[9]。该技术能为提高 SLM 成形件的质量稳定性和闭环控制奠定基础,因此 SLM 过程监测成为当前研究热点。近年来,学者们探索了多种 SLM 监测技术。KWON 等[10]使用高速摄像机和现场可编程门阵列(Field programmable gate array,FPGA)芯片组成熔池图像采集系统,并使用深度神经网络框架对图像数据进行分类。NANDI 等[11]提出一种结合数值公式和对流冷却传导方式解析移动热源的算法,用于估计 SLM 过程中温度分布和熔池几何形状。 ITO 等[12]通过使用声发射(Acoustic emission,AE) 波形设备,实时监测 SLM 成形单层零件过程中产生的微缺陷。虽然一些监测技术和方法仍不够成熟,但在工艺过程中的监测能力不可替代。

  • 本文以 SLM 成形过程为线索,在对 SLM 技术原理及过程特征研究的基础上,针对熔池温度及形貌特征变化,详细综述当前 SLM 成形监测技术的研究现状,分析目前监测技术存在的不足,并对未来智能监测及闭环控制研究方向进行展望,可为 SLM 成形高质量零件提供参考借鉴。

  • 1 SLM 技术原理及熔池变化

  • SLM 设备基本架构分为光路、机械、控制等几个单元。光路单元由激光器、扫描振镜、F-θ 聚焦透镜等构成用于激光发射,在瞬时发射出高能量激光束使合金粉末熔化;机械单元主要由粉料缸、送粉装置等结构组成,存储粉末然后将其均匀地铺送至基材表面加工;控制单元包含多块控制卡和计算机,主要进行扫描路径规划,控制激光加工路线[13-15]

  • SLM 技术首先利用计算机辅助设计(CAD)绘制三维零件模型,将该模型进行切片操作后分层处理,得到每一层截面轮廓数据并进行路径规划,最后控制激光束按每层轮廓扫描路径选择性地逐层熔化金属粉末,进行快速凝固后逐层堆叠形成致密的三维金属零部件[16–18]。此技术原理如图1 所示。

  • 图1 SLM 技术原理图

  • Fig.1 Schematic diagram of the SLM technology

  • 激光束扫描粉末床熔化粉末形成熔池,SLM 成形过程采用直径较小的光斑作为激光源,使得该技术具有熔池尺寸小、移动速度快等特点[19],导致熔池形成前期形貌不断变化,随着激光束的远离,熔池界面受表面张力的作用逐渐稳定[20],最终保持一个固定的形貌,图2 展现了熔池的变化状态。针对激光扫描过程中熔池辐射强度和形状特征,重点监测熔池的温度及表面形貌,进一步识别与熔池相关的飞溅、气孔等缺陷。

  • 图2 熔池变化状态示意图[21]

  • Fig.2 Schematic diagram of change state in molten pool[21]

  • 2 熔池温度监测

  • 激光热加工所形成熔池的温度图像是 SLM 过程中所包含信息最丰富的特征之一[22],熔池温度变化决定了零件微观结构和力学性能,适当的温度分布有助于形成高质量零件,而温度分布不均会导致粉末不完全熔化或熔融粉末蒸发,因此记录和分析熔池的温度场及变化,对理解工艺内在机理和验证仿真模型具有重要价值。一般通过红外热成像仪、光电二极管及高温计等设备测量熔池热辐射、采集熔池真实温度等[23]

  • 2.1 红外热成像设备监测

  • 红外热成像通过监测特定波段的红外信号 (Infrared radiation,IR)计算温度值,从而得出表面温度分布图像[24]。通常使用红外热成像仪、红外相机等传感器进行温度的测量。CHENG 等[25]在 SLM 成形镍基合金过程中,使用近红外热成像仪(约 670 nm 的光谱范围)采集粉末层的热信号(图3),获得不同高度下的辐射温度分布,基于确定的辐射温度和热成像仪估算熔池尺寸,但难以获得真实温度。

  • 图3 热成像系统及设备[24]

  • Fig.3 Thermal image system setup and equipment [24]

  • 为了进一步扩展红外热成像监测技术的精确性,可采用分层方式对每一层熔池进行监测,通过表面所保留的热特征识别亚表面缺陷。 BARTLETT 等[26]开发并演示了一种新型的现场监测系统的能力,该系统使用长波红外(LWIR) 相机在 SLM 生产过程中采用分层方式测量相对表面温度,再使用原位扫描电子显微镜(Scanning electron microscope,SEM)对零件进行表征。如图4 所示,其中监测未熔合孔(Lack of fusion, Lof)缺陷的总成功率为 82%,并且监测成功率随着缺陷尺寸的增加而提高,证明分层进行红外监测的方法在识别缺陷方面非常有效。该方法还可用于统计分析 SLM 生产过程中存在的系统过程误差,扩展了红外监测的能力。

  • 图4 长波红外相机与 SEM 所监测缺陷[26]

  • Fig.4 Defects monitored by LWIR and SEM[26]

  • 上述研究证明了红外热成像仪在 SLM 成形过程中的可行性,且使用该技术监测熔池是较为直观的一种方式,但问题在于无法获得准确的熔池温度。因此,分层监测方式的提出能够有效改善这一不足,并在监测过程中获得较高的准确率。但是由于 SLM 成形过程中激光扫描速度极快,需要超高帧率的红外成像设备,但目前该类设备所需成本昂贵,难以实现广泛应用。

  • 2.2 光电二极管探测器监测

  • 光电二极管通过将光辐射转换为电压信号,能够低成本且精确地显示熔池温度信息[27]。因此,在 SLM 过程中使用光电二极管监测熔池行为是经济有效的。ZHANG 等[28]设计了光电二极管多探测器分割监测方式,通过改变激光功率观察光电二极管的波动范围,试验结果表明该方式可有效监测到熔池不稳定温度场变化。如图5 所示为光电二极管监测系统电路板。

  • 由于光电二极管具有体积小、灵敏度高等特点,可将其与 SLM 成形设备相结合实现监测与成形的一体化。BARRIOBERO-VILA 等[29]尝试采用 SLM280HL 设备制备 Ti-6Al-4V 合金火箭发动机叶轮,该设备集成了基于光电二极管的商用熔池监测系统(Melt pool monitoring,MPM),该系统允许在 SLM 过程中实时测量热发射,以定性的方式识别冷热点。MPM 系统使用两个具有不同专用光敏度的光电二极管探测每个不同范围的近红外波长,每 10 μs检测一次热辐射,如图6 所示为 MPM 系统获得的热辐射相关强度。

  • 图5 光电二极管监测系统电路板[28]

  • Fig.5 Circuit board of photodiode monitoring system[28]

  • 图6 MPM 系统获得的热辐射相关强度[29]

  • Fig.6 Intensity associated with the thermal emission acquired by the MPM system[29]

  • 光电二极管具有高精确度、低成本等优势,目前被广泛应用于熔池监测过程。同时为了优化加工过程,开发了 MPM 系统与 SLM 成型设备相结合的方式获得热辐射场,这种一体化设计极有效地提升了 SLM 设备的功能性。

  • 2.3 其他设备监测

  • 在 SLM 成形过程中,早期研究中使用高温计等设备来监测选择性激光熔化过程中的温度分布[30]。REN 等[31]首次提出基于提取真实熔池温度的模拟模型校准高温计测量值,通过有限元传热模拟和实验测试获得温度的估计值,与高温计获得的温度测量值平均误差仅为 1%。在高温计校准的基础上,将高温计与 SLM 设备结合,可实现熔池温度的实时测量。GUTKNECHT 等[32]将一个双色高温计集成到 SLM 设备激光轴上,依次收集熔池及其附近产生的辐射,通过适当的校准可获得熔池表面最高温度。研究表明高温计置于轴上测温是一种适合于熔池和过程监测的方式。

  • 光成像技术原理在于提取零件热历史变化,通过分析热历史特征得到温度分布图,达到检测熔池温度的目的。LOUGH 等[33]使用 Renishaw AM250 设备在不同的加工条件下制作了拉伸试样,以产生不同的热历史。通过对可见光和短波红外光(Visible and short-wave infrared,SWIR)相机所成像数据进行逐层处理,提取每个工艺条件下热历史中的特征,初步识别拉伸试样中引入的缺陷。如图7 所示为通过逐层监测试样中热历史的变化和内部缺陷。在未来的工作中,这种技术将在基于工程特性的 SLM 制造进行逐层的零件监控,以标记缺陷和确保零件质量。

  • 图7 逐层监测过程拉伸试样的热历史变化和内部缺陷[33]

  • Fig.7 Identification of changes in thermal history and internal defects in tensile test specimens through layer-to-layer process monitoring[33]

  • 以上研究表明高温计在 SLM 过程监测领域的有效性。使用 SWIR 等技术分析每层表面所保留热历史特征得到温度分布,SLM 过程中存在的热历史特征决定了微观结构(孔隙率、晶粒尺寸和相场) 和工程特性(密度、模量和屈服强度),因此该技术在未来工程领域的监测具有极大应用前景。

  • 综上所述,通过红外热成像仪、光电二极管及高温计、SWIR 等设备可监测熔池温度变化,红外热成像技术能够进行实时监控,但精度较低或成本较高,且红外成像技术需要将热辐射信号转换成真实温度,需要控制材料发射率、环境温度等参数,给实时温度监测带来了挑战;光成像监测大多使用离线处理方式,不具备实时性。目前上述技术均难以实现真正意义上的实时反馈控制,因此需在此基础上增加闭环控制系统,达到改善 SLM 成形件质量目的。而且上述技术所监测的温度场仅限切片表面,难以监测新层沉积与前一层相结合的过程,因此进行层间熔合过程的温度监测及分层控制是目前亟须解决的问题。

  • 3 熔池形貌监测

  • 熔池形态特征监测一般使用工业相机,如高速摄影机、数字单反等设备,并且通常与电子计算机断层扫描(Computed tomography,CT)相结合[34],进一步确定缺陷的尺寸与位置,但工业相机的采样频率低,在高速制备零件的过程中可能存在丢帧、噪声等问题,为了避免上述问题影响监测结果,同轴系统、算法分析与机器学习等监测技术被广泛应用。同时声信号在动态监测过程中被逐渐开发。

  • 3.1 同轴成像系统监测

  • SLM 熔池监测系统最常采用同轴布局,通过现场图像采集熔池区域的形貌信息,将监测系统所获得的信息作为熔池过热的预测因子[35],同时也可以为 SLM 过程中的实时反馈提供指导。同轴成像系统原理是激光源通过半反射镜面偏转到振镜,振镜将激光束聚焦在工作区域以熔化粉末。粉末熔化形成熔池,熔池产生的辐射通过振镜和半反射镜传输到分光镜,供传感器采集。如图8 所示为配有 CMOS 相机同轴光学监测系统,便于监测熔池形态变化。所示同轴传感方式,由分束器分离的辐射被传输到平面光电二极管和 CMOS 相机。平面光电二极管捕获一定波长范围内的激光辐射[36],高速 CMOS 相机负责收集熔池形貌特征[37]

  • 图8 SLM 工艺熔池同轴监测系统布置示意图[38]

  • Fig.8 Schematic of the molten pool coaxial monitoring system in SLM[38]

  • SLM 中同轴监测系统可在传感器选择和观测带宽设备使用不同的配置。KANKO 等[39]将同轴光路应用于低相干干涉测量,以在 SLM 成形过程中实时测量熔池高度,由于激光束作用导致熔池过热,内部产生剧烈波动,由此产生的球状缺陷也可被识别。此外,使用外部照明装置来观察熔池几何形状是一种选择,它可以独立于激光发射行为,实现熔池几何形状的可视化。MAZZOLENI 等[40] 设计了同轴成像系统,并测试两种不同的照明设置,即与工作激光器同轴的二极管激光束和照亮整个构建平台的横向低相干激光,研究使用外部照明源直接观察熔池几何形状的方法,发现外部照明有助于直接解释 SLM 熔化条件,并且可以通过对捕获的帧图像进行算法处理来确定实际扫描位置和速度。

  • 同轴监测可以很好地跟踪熔池变化,并同步输出简单信号,能够实现实时过程监测和反馈控制,因此常用于 SLM 监测过程中。但为了避免加工过程中引发的各种缺陷,监测系统需要以微秒级的速度进行快速采集和反应,以便在线调整工艺参数。并且同轴监测系统做到了多个传感器相结合的监测方式,但其中一些照明装置适用范围较差,需要开发合适的光学系统以适用于不同场景,目前同轴系统与机器算法相结合已有一定研究,但仅提供一种监测缺陷的可行性,需要进一步开发应用于 SLM 成形过程中。以上研究为了方便测量熔池尺寸,暂时从数据中去除飞溅物。然而研究表明,飞溅特征(尺寸、速度和方向)与构建对象的缺陷具有很强的相关性[41]。因此,在未来的工作中,除了熔池尺寸外,飞溅物尺寸及方向的计算同样需要进一步开发并实现到算法中,系统地对 SLM 工艺热特性进行研究,以实现更全面的监控系统。

  • 3.2 算法分析监测

  • 激光束高速熔融粉末过程中会产生熔池流动等动态现象,为了详细表征熔池成形过程中所监测到的动态变化,须引入新的运动特征来描述运动的熔池[42]。与传统熔池监测不同,该方法使用高速相机对熔池特征进行大量采集,采用新型算法对所采集图像进行分类从而实现实时监控,如反向传播神经网络(Back propagation neural network,BPNN)、支持向量机(Support vector machine,SVM)和深度置信网络(Deep belief networks,DBN)等智能机器学习算法[43]等。目前最常使用的算法为 k-means 聚类算法。LIN 等[44]构造了一个高维特征向量作为运动特征,通过阈值结合连通区域分析方法提取 IN625 粉末成形过程中的熔池和飞溅物状态。应用 k-means 聚类算法对不同工艺参数下的运动特征进行分类,构建熔池状态与工艺参数之间的联系,用于质量控制。图9 所示为典型熔池特征提取过程。结果表明提取的运动特征比传统的几何特征能更准确地描述熔池的变化,能同时区分熔化、部分熔化和缺陷的运动方向和熔化状态。该研究为 SLM 过程的智能在线监测提供了一种新方法。

  • 图9 熔池运动特征的提取过程[44]

  • Fig.9 Extraction procedure for the motion feature of melt pool[44]

  • MODARESIALAM 等[45]使用基于粒子分析(Particle analysis,PA)的 Lab-VIEW 软件设计了一种算法,使用高性能相机在每一层拍摄图像,由实时控制器计算图像粒子数并发送给用户界面(User interface,UI),在算法检测到任何熔覆层中的粒子异常时停止该过程,并发出警报。但是为了监视下一层的进程,须重新手动启动机器。图10 所示图像是在创建每个缺陷后由高性能相机逐层在线拍摄的。

  • 图10 缺陷的原位图像[45](a)改变激光束直径前的完好层(b)改变光斑尺寸后第一层缺陷的原位图像(c)第二层缺陷的原位图像(d)粉层重涂后缺陷的原位图像

  • Fig.10 In-situ image of defects[45] (a) Completed layer before changing the laser beam diameter; (b) In-situ image of defects of the first layer after changing the spot size; (c) In-situ image of defects of the second layer; (d) In-situ image of defects after single powder layer recoating

  • 在上述工作中,熔池区域比其他区域具有更高的权重,有效减少了由背景或噪声引起的不必要分类的可能性。k-means 聚类等新型算法被证实是一种有效、优越和可靠的分类方法,可用于 SLM 过程的熔池监测[46-48]。因此将多信号传感器与算法分析相结合的方式监测并分析熔池形貌特征,对零件成形机理及缺陷成因的研究有重要意义。但上述研究采用单一的算法分析仍有明显缺陷,如监测系统在监测到缺陷存在时能够停止工作,但须要重新手动启动机器进行后续工作,并未完全实现智能化监测。

  • 3.3 机器学习监测

  • 机器学习监测是使用宽范围的激光功率和扫描速度生成单条短线熔道,经过大量标注图像的训练后,利用深度神经网络(Deep neural network,DNN) 等算法识别熔体轨迹的位置,并对其进行分类,以确定合适的工艺参数,如图11 所示[49]。该方法提供了一个通用工具箱,以最小成本进行 SLM 中熔体轨迹的质量评估。

  • 图11 DNN 模型筛选 SLM 工艺参数的流程示意图[49]

  • Fig.11 Schematic flowchart for screening SLM process parameters using the DNN model[49]

  • XING 等[50]使用高速 CCD 摄像机采集 Q235A 钢成形过程熔池图像,使用卷积神经网络 (Convolutional neural networks,CNN)模型对图像特征进行分类,经验证达到 99.6%的分类精度。图12 所示为试验装置与监测系统示意图。

  • 图12 SLM 试验装置及监测系统示意图[50]

  • Fig.12 Experimental setup and schematic of the in-situ monitoring system of the SLM process[50]

  • 由于 CNN 能够精确识别熔池区域的复杂图像特征,FANG 等[51]提出一种基于 U-Net 的卷积神经网络图像分割方法来捕获熔池特征,并建立了实时监测系统,如图13 所示为 U-Net 对一些复杂情况的图像处理结果。U-Net 有一个带有跳跃链接的编码器-解码器结构,轻量级架构用于减少推理时间,使实时监控成为可能。与传统算法不同,U-Net 成功的消除了干扰,并以较低计算成本达到了最高的平均交并比(Mean intersection over union,MIOU)。因此,CNN 是一种可靠的方法,依据其特性及变形网络可以监测其他工艺参数对熔池特性的影响,从而提高 SLM 的生产效率。

  • 图13 U-Net 对一些复杂情况的图像处理结果[51]

  • Fig.13 Image processing results of U-Net for some complex situations[51]

  • 在上述 DNN 与 CNN 模型的基础上,训练大量标记数据较为繁琐,为了减轻这一工作量,半监督学习方式应运而生。YUAN 等[52]首次成功地将半监督学习应用于 SLM 监测,该团队设计了一个基于卷积神经网络的半监督原位视频监测框架,自动识别这些用于 SLM 原位监测的轨迹指标,如激光打印轨迹的平均宽度、连续性和其他表面形貌衍生的轨迹特性。图14 所示为光电图像、结构光测量图像与图像处理算法结果。结果表明半监督方法对于 SLM 监测是有前景的,并且易于实现。

  • 图14 示例轨迹[52](a)规则的光电图像(b)结构光测量的高度图(c)提出的图像处理算法的分割结果(d)从计算的轨迹指标标签

  • Fig.14 Example tracks[52] (a) Regular electro-optical images; (b) Height maps measured by structured light, (c) Segmentation results by proposed image processing algorithm; (d) Labels from calculated track metrics

  • 上述工作主要探寻完全无损、高效且误差率低的监测方式,重点聚焦于算法分析与机器学习相结合。由于 SLM 成形速度快且加工过程极为精细,为了实时准确地进行熔池监测,可以通过升级计算硬件和修改算法使图像处理时间优化到毫秒量级,最大程度实现缺陷的实时追踪。另外,采用聚类算法可以有效且精准地监测熔池形貌状态,但前期工作量巨大,须要采集足够熔池特征图像。半监督学习被提出且在试验中得到验证,但该方式所监测缺陷类型较为局限,须要增加更多缺陷类型以提高该系统的适用性。

  • 3.4 声信号监测

  • 声信号监测技术可对每层表面变化进行动态分析,能够更准确地描述 SLM 过程的复杂动力学。DILLHOEFER 等[53]首次进行了在线超声测量,将超声监测系统集成到 EOS 技术机器中,使用超声波监测制造过程中的层积,证明通过平台使用超声波在线监测复杂的 SLM 过程是可行的。通过评估超声信号,可以观测到成形过程中的表面动态。如图15 所示为新一层构建完成后超声监测到的短时间变化。

  • 图15 底波的详细视图在短时间的变化[53]

  • Fig.15 Detailed view of the backwall echo with a short time change[53]

  • WANG 等[54]提出一种基于机器学习和改进变分模态分解(Variational mode decomposition,VMD) 的声发射(AE)原位质量监测方法。基于鲸鱼优化算法(Whale optimization algorithm,WOA)和平均能量熵调整 VMD 参数,实现声发射信号的自适应分解。如图16 所示为 AEE-WOA-VMD 方法的分解结果。在单层多道的基础上,根据信号能量对每个子模式(单道轨迹)进行评价,提取用于 SLM 打印质量预测的特征向量。最后,采用人工神经网络(Artificial neural network,ANN) 和支持向量机(SVM)进行质量预测。结果表明,基于改进 VMD 的 SLM 打印质量预测效果优于经验模态分解(Empirical mode decomposition, EMD)方法。

  • 图16 AEE-WOA-VMD 方法的分解结果[54]

  • Fig.16 Decomposition results of AEE-WOA-VMD method[54]

  • LI 等[55]提出一种特征级多传感器融合方法,聚集声发射和光信号,开发了一个配备有麦克风和光电二极管的离轴原位监测系统,以捕获多轨道和多层熔化过程中的声信号和光信号。通过考虑激光扫描信息,开发了一种将 1D 感测信号转换为 2D 图像的信号到图像方法。最后,将转换后的图像用于训练 CNN 模型,以提取和融合来自两个单独传感器的特征,实现多个传感器执行现场质量监测。与基于单个传感器的方法相比,所提出的多传感器融合方法以略微增加计算时间为代价,显著提高了分类精度。

  • 超声监测在检测系统中具有很大潜力,为了更好地发挥超声监测的作用,应该专注于稳定监测条件,开发降噪模块,并根据缺陷在构件中的位置,对不同类型缺陷进行检测研究。目前超声监测仅限于制备单层、简单几何形状的零件,但该技术验证了基于声发射技术可实现 SLM 过程监测,为多层件的质量监测奠定了基础,因此未来研究应着重将该技术扩展到复杂精细零件中。

  • 综上所述,使用同轴监测系统与算法分析、机器学习相结合方式对完善熔池形貌的监测极为重要。但在高功率激光作用下,熔池会产生严重的蒸发效应,是实现实时监测的一大阻碍。因此目前对熔池的形貌特征进行实时监测和分析手段在稳步推进中,而设备研发与算法处理能力较为薄弱,导致目前缺陷监测的精确度受到限制,对于未来的工作,应继续研究新型设备,并且进一步增加分类类型提高该种算法对监测系统的适用性。机器学习方式中的图像处理需要采集大量标记数据,虽然已有研究人员提出半监督学习技术,但仍须大量研究,验证该技术的适用性。而声信号易受激光、噪声等干扰,须要开发降噪模块应对苛刻的使用环境,且当前声信号监测技术仍在初步阶段,对于监测复杂零件成形过程尚有难度,但该方法能够较为准确预测成形零件质量,具有很好的发展前景。

  • 4 基于监测系统实现闭环控制

  • 在 SLM 系统这样的开环过程中,过程监控是确定成形零件质量和为闭环控制做准备的关键。闭环反馈控制系统可根据 SLM 成形过程中熔池的温度分布,在线调整工艺参数(激光参数、扫描参数、粉末层厚度等),使成形零件内部温度分布均匀,防止过热导致气孔、裂纹等缺陷的存在。同时,该反馈系统也可通过熔池形貌变化,调整参数设置控制熔池尺寸,便于精准成形零件。 FLEMING 等[56]使用相干成像技术监测由于表面粗糙度、粉末堆积密度等缺陷形成的凸起或凹陷,分别通过激光熔融与再填充补偿纠正缺陷,成功实现手动闭环控制,更进一步接近全反馈控制。 VASILESKA 等[57]提出了一种基于同轴熔池监测的分层控制策略,通过实时控制每一层熔池面积达到闭环控制效果,如图17 所示为正常成形零件与分层控制成型对比。

  • 以上研究表明,通过实时监测建立完整闭环反馈系统可行且极具有效性,然而熔池空间范围小,需要高时间和空间分辨率的性能监测系统[58],以达到实时反馈所需条件。因此研发先进的计算硬件和改进机器学习算法有利于提高监测系统的实时性与精确性。目前在 SLM 闭环控制系统中,实时监测并及时调整工艺参数的研究刚刚兴起,减小系统反应时间难度较大,仍须进一步研究。

  • 图17 成形零件效果对比[57] (a)无控制 (b)分层控制

  • Fig.17 Comparison of formed parts (a) without and (b) with the layer-wise control[57]

  • 选区激光熔化成形过程监测技术在声学光学等领域快速发展,用于监测熔池形成中温度、形貌等变化,并且将其用于闭环反馈控制,如表1 展现了基于超声信号、射线及图像监测设备的优缺点。相较于其他监测设备,超声信号监测更适用于复杂结构零件中,而射线监测与图像监测熔池温度形貌更为直观,但射线监测成本较大,因此目前最常用监测方式仍为图像监测,且该类设备体积较小使用方便,常应用于多信号监测模板或与算法处理相结合。表2 总结了成形过程中熔池温度及形貌的监测方式特点。对于熔池温度监测,使用范围较广但难以实现实时反馈;而对于熔池形貌特征的监测,所采用监测设备及同轴系统所使用工具需要仍进行改进。同时机器学习方式能够有效进行实时监测,但对于半监督学习方式还须进一步深入。且采用声信号监测具有一定的应用前景,但其极易受外界环境干扰,仍须研究改进。

  • 表1 常用监测设备及优缺点对比[59-63]

  • Table1 Comparison of common monitoring equipment with their advantages and disadvantages[59-63]

  • 表2 选区激光熔化成形过程监测技术

  • Table2 In-process monitoring techniques of Selective Laser Melting monitoring

  • 5 结论与展望

  • 熔池温度与形貌特征是影响金属零件质量的主要因素,目前研究工作较为详尽,且基于监测系统实现闭环控制已有所研究。综述了 SLM 成形过程监测技术的研究进展,得出主要结论如下:

  • (1)在机器学习监测过程中,从手动提取图像特征,向自动提取特征并识别缺陷方向发展。大部分研究已证明了 CNN 从图像、视频和文本中提取特征的效率,从而成功地应用于各种目标检测、识别、分割和分类任务。但很少有人研究 CNN 在缺陷检测和工业物体识别方面的有效性。

  • (2)为达到真正意义上的实时反馈,减少反馈传送时间,采用多传感器相结合建立完整实时反馈系统,单一传感器系统采集信号单一且精确度较低,通过多传感器相结合方式,可对熔池内部进行全面、清晰且准确的实时监测。

  • (3)SLM 成形零件广泛应用于航空航天及军工等对工件质量要求很高的领域,为了提高成形系统的智能化与自动化水平,需要将实时监测与实时处理技术相结合用于 SLM 技术,尽可能缩短反馈与响应时间,对于减少二次加工与重新制造所用资源的浪费具有极大意义。超声监测在监测系统中具有极大的应用潜力,能够动态分析成形过程中的内部变化状态,预测零件质量。

  • 目前,光信号、声信号及多传感器相结合的方式已广泛应用于监测系统中,闭环控制同时需要算法处理及机器学习的同步进行,但为进行实时反馈且同步控制对设备反应速度及算法要求极高,当前研究仍存在一定局限性,对未来监测技术与闭环控制研究展望如下:

  • (1)随着监测技术的不断发展,针对机器学习监测从输入数据分布(即图像、视频)中提取新的特征这一优势,开展自动提取并识别缺陷的研究,这将为未来智能化监测 SLM 加工过程奠定基础。

  • (2)多传感器系统的设计需要考虑多传感信号的相互配合及影响,最大程度监测出 SLM 过程中存在的缺陷,多传感信号的融合及设计将成为未来 SLM 实时监测重要研究方向。

  • (3)深度学习对缺陷监测是一种非常有前景的解决方案,需要具备庞大的数据处理体系。与机器学习不同,深度学习具有强大的数学表达能力,通过对熔池状态的计算可迅速拟合函数,精准且高效计算出缺陷类型、大小、数量和分布状态等,且该方式很难受到外界因素的影响,具有极高的稳定性。根据深度学习与监测系统的协同作用机理,建立系统的模型构建理论,为实现 SLM 闭环控制提供指导方向。

  • (4)超声监测技术使用环境严苛,目前仍在试验阶段用于简单零件的监测,克服超声监测环境限制并将其用于复杂几何零件中具有极大的研究空间。

  • 参考文献

    • [1] PENG L M,SHAN Q C,WU Y J,et al.Additive manufacturing of magnesium alloys by selective laser melting technology:A review[J].Acta Metallurgica Sinca,2023,59(1):31-54.

    • [2] 王虎,彭云,赵琳,等.选区熔化3D打印TiAl基合金的研究现状及展望[J].表面技术,2021,50(1):173-186.WANG Hu,PENG Yun,ZHAO Lin,et al.Research status and prospect of selection melting 3D printing TiAl-based alloys[J].Surface Technology,2021,50(1):173-186.(in Chinese)

    • [3] KURZYNOWSKI T,PAWLAK A,SMOLINA I.The potential of SLM technology for processing magnesium alloys in aerospace industry[J].Archives of Civil and Mechanical Engineering,2020,20(1):1-13.

    • [4] JAFARI D,WITS W W.The utilization of selective laser melting technology on heat transfer devices for thermal energy conversion applications:A review[J].Renewable and Sustainable Energy Reviews,2018,91:420-442.

    • [5] 褚清坤,余春风,邓朝阳,等.TiC 含量对激光选区熔化 Inconel 625 合金微观组织及表面摩擦磨损性能的影响[J].中国表面工程,2021,34(1):76-84.CHU Qingkun,YU Chunfeng,DENG Chaoyang,et al.Effect of TiC content on microstructure and surface friction and wear properties of Inconel 625 alloy melted by laser selective area[J].China Surface Engineering,2021,34(1):76-84.(in Chinese)

    • [6] VOLPP J.Spattering effects during selective laser melting[J].Journal of Laser Applications,2020,32(2):022023.

    • [7] 刘小辉,刘允中.激光选区熔化成形高强铝合金晶粒细化抑制裂纹研究现状[J].材料工程,2022,50(8):1-16.LIU Xiaohui,LIU Yunzhong.Research status of crack suppression of grain refinement of high-strength aluminum alloy by laser selective melting[J].Journal of Materials Engineering,2022,50(8):1-16.(in Chinese)

    • [8] CHEN J,HOU W,WANG X.Microstructure,porosity and mechanical properties of selective laser melted AlSi10Mg[J].Chinese Journal of Aeronautics,2020,33(7):2043-2054.

    • [9] WU B,JI X,ZHOU J,et al.In situ monitoring methods for selective laser melting additive manufacturing process based on images—A review[J].China Foundry,2021,18(4):265-285.

    • [10] KWON O,KIM H G,HAM M J,et al.A deep neural network for classification of melt-pool images in metal additive manufacturing[J].Journal of Intelligent Manufacturing,2020,31(2):375-386.

    • [11] NANDI S K,KUMAR R,AGRAWAL A.Computationally inexpensive semi-analytical thermal model to predict melt-pool dimensions for a single-track in selective laser melting[J].Journal of Manufacturing Processes,2022,80:469-479.

    • [12] ITO K,KUSANO M,DEMURA M,et al.Detection and location of microdefects during selective laser melting by wireless acoustic emission measurement[J].Additive Manufacturing,2021,40:101915.

    • [13] 刘萌.3D 打印SLM技术在机械自动化加工中的应用研究[J].数字技术与应用,2015,33(4):107.LIU Meng.Application of 3D printing SLM technology in mechanical automation processing[J].Digital Technology and Application,2015,33(4):107.(in Chinese)

    • [14] YE D,HONG G S,ZHANG Y,et al.Defect detection in selective laser melting technology by acoustic signals with deep belief networks[J].The International Journal of Advanced Manufacturing Technology,2018,96(5):2791-2801.

    • [15] NAGARAJAN B,HU Z,SONG X,et al.Development of micro selective laser melting:The state of the art and future perspectives[J].Engineering,2019,5(4):702-720.

    • [16] 龙旭,贾啟普,李娇,等.选区激光熔化成形TC4钛合金力学性能及其工艺关联性[J].中国表面工程,2022,35(2):215-223.LONG Xu,JIA Qipu,LI Jiao,et al.Mechanical properties and process correlation of TC4 titanium alloy formed by selective laser melting[J].China Surface Engineering,2022,35(2):215-223.(in Chinese)

    • [17] 刘文浩,陈燕,王杰,等.SLM 成型零件型腔内表面电解辅助磁粒研磨加工研究[J].中国表面工程,2021,34(3):100-109.LIU Wenhao,CHEN Yan,WANG Jie,et al.Research on electrolytic-assisted magnetic particle grinding processing of inner surface of SLM molded parts[J].China Surface Engineering,2021,34(3):100-109.(in Chinese)

    • [18] 李忠利,杜东方,雷盛.镍基合金激光选区熔化成形的缺陷形成及其控制综述[J].锻压装备与制造技术,2022,57(5):97-100.LI Zhongli,DU Dongfang,LEI Sheng.Review of defect formation and control of laser selective melting and forming of nickel-based alloy[J].Forging Equipment and Manufacturing Technology,2022,57(5):97-100.(in Chinese)

    • [19] 伍方.选择性激光熔化纯钨材料的成形技术研究[D].上海:上海大学,2021.WU Fang.Research on forming technology of selective laser melting of pure tungsten materials[D].Shanghai:Shanghai University,2021.(in Chinese)

    • [20] 毕轩.不锈钢选区激光熔化熔池及微观组织演化研究 [D].大连:大连理工大学,2021.BI Xuan.Study on laser melting pool and microscopic tissue evolution in stainless steel selection[D].Dalian:Dalian University of Technology,2021.(in Chinese)

    • [21] YADAV P,RIGO O,ARVIEU C,et al.In situ monitoring systems of the SLM process:On the need to develop machine learning models for data processing[J].Crystals,2020,10(6):524-550.

    • [22] 李文龙,戈海龙,任远,等.图像处理技术在激光熔池温度检测的应用[J].激光技术,2018,42(5):599-604.LI Wenlong,GE Hailong,REN Yuan,et.al.Application of image processing technology in temperature detection of laser molten pool[J].Laser Technology,2018,42(5):599-604.(in Chinese)

    • [23] 王奉涛,杨守华,吕秉华,等.金属增材制造过程熔池动态监测研究综述[J/OL].计算机集成制造系统:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.WANG Fengtao,YANG Shouhua,LV Binghua,et al.Research review on dynamic monitoring of melt pool in metal additive manufacturing process[J/OL].Computer Integrated Manufacturing System:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.(in Chinese)

    • [24] 马婷.红外热成像仪原理与应用分析[C]//第十四届宁夏青年科学家论坛石化专题论坛论文集,2018-07-24,宁夏,2018:323-325,329.MA Ting.Principle and application analysis of infrared thermal imager[C]//Proceedings of the 14th Ningxia Young Scientists Forum Petrochemical Symposium,July 24,2018,Ningxia,2018:323-325,329.(in Chinese)

    • [25] CHENG B,LYDON J,COOPER K,et al.Infrared thermal imaging for melt pool analysis in SLM:A feasibility investigation[J].Virtual and Physical Prototyping,2018,13(1):8-13.

    • [26] BARTLETT J L,HEIM F M,MURTY Y V,et al.In situ defect detection in selective laser melting via full-field infrared thermography[J].Additive Manufacturing,2018,24:595-605.

    • [27] CLIJSTERS S,CRAEGHS T,BULS S,et al.In situ quality control of the selective laser melting process using a high-speed,real-time melt pool monitoring system[J].The International Journal of Advanced Manufacturing Technology,2014,75(5):1089-1101.

    • [28] ZHANG K,LIU T,LIAO W,et al.Photodiode data collection and processing of molten pool of alumina parts produced through selective laser melting[J].Optik,2018,156:487-497.

    • [29] BARRIOBERO-VILA P,ARTZT K,STARK A,et al.Mapping the geometry of Ti-6Al-4V:From martensite decomposition to localized spheroidization during selective laser melting[J].Scripta Materialia,2020,182:48-52.

    • [30] ABOUELNOUR Y,GUPTA N.In-situ monitoring of sub-surface and internal defects in additive manufacturing:A review[J].Materials & Design,2022,222:111063.

    • [31] REN C G,LO Y L,TRAN H C,et al.Emissivity calibration method for pyrometer measurement of melting pool temperature in selective laser melting of stainless steel 316L[J].The International Journal of Advanced Manufacturing Technology,2019,105(1):637-649.

    • [32] GUTKNECHT K,HAFERKAMP L,CLOOTS M,et al.Determining process stability of laser powder bed fusion using pyrometry[J].Procedia Cirp,2020,95:127-132.

    • [33] LUONG M P.Fatigue limit evaluation of metals using an infrared thermographic technique[J].Mechanics of Materials,1998,28(1-4):155-163.

    • [34] 张勇.基于机器视觉的选区激光熔化成型质量监测的研究[D].厦门:厦门理工学院,2020.ZHANG Yong.Research on quality monitoring of selective laser melting molding based on machine vision[D].Xiamen:Xiamen University of Technology,2020.(in Chinese)

    • [35] 王晓玮.熔池图像高速采集与实时处理技术研究[D].成都:电子科技大学,2020.WANG Xiaowei.Research on high-speed acquisition and real-time processing technology of molten pool images[D].Chengdu:University of Electronic Science and Technology of China,2020.(in Chinese)

    • [36] 魏芬,吴怡,徐世武.基于机器学习与多光电二极管的可见光定位的实验研究[J/OL].激光与光电子学进展:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.WEI Fen,WU Yi,XU Shiwu.Experimental study on visible light localization based on machine learning and multiple photodiodes[J/OL].Laser and Optoelectronics:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.(in Chinese)

    • [37] MA P,HE X,WANG A.Design of online measurement system for molten pool morphology in selective laser melting(SLM)process[C]//2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture(AIAM),October 23-25,2021,Manchester,United Kingdom,IEEE,2021:198-204.

    • [38] 赵德陈,林峰.金属粉末床熔融工艺在线监测技术综述[J].中国机械工程,2018,29(17):2100-2110,2118.ZHAO Dechen,LIN Feng.Review of online monitoring technology of metal powder bed melting process[J].China Mechanical Engineering,2018,29(17):2100-2110,2118.(in Chinese)

    • [39] KANKO J A,SIBLEY A P,FRASER J M.In situ morphology-based defect detection of selective laser melting through inline coherent imaging[J].Journal of Materials Processing Technology,2016,231:488-500.

    • [40] MAZZOLENI L,CAPRIO L,PACHER M,et al.External illumination strategies for melt pool geometry monitoring in SLM [J].JOM,2019,71(3):928-937.

    • [41] LIU Y,ZHANG M,SHI W,et al.Study on performance optimization of 316L stainless steel parts by high-efficiency selective laser melting[J].Optics & Laser Technology,2021,138:106872.

    • [42] 朱锟鹏,王齐胜,林昕,等.基于熔池运动特征的选区激光熔融过程状态检测方法[J].计算机集成制造系统,2021,27(12):3403-3415.ZHU Kunpeng,WANG Qisheng,LIN Xin,et al.Selection laser melting process state detection method based on molten pool motion characteristics[J].Computer Integrated Manufacturing Systems,2021,27(12):3403-3415.(in Chinese)

    • [43] LI J,CAO L,XU J,et al.In situ porosity intelligent classification of selective laser melting based on coaxial monitoring and image processing[J].Measurement,2022,187:110232.

    • [44] LIN X,WANG Q,FUH J Y H,et al.Motion feature based melt pool monitoring for selective laser melting process[J].Journal of Materials Processing Technology,2022,303:117523.

    • [45] MODARESIALAM M,ROOZBAHANI H,ALIZADEH M,et al.In-situ monitoring and defect detection of selective laser melting process and impact of process parameters on the quality of fabricated SS 316L[J].IEEE Access,2022,10:46100-46113.

    • [46] LI J,ZHOU Q,CAO L,et al.A convolutional neural network-based multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Systems,2022,64:429-442.

    • [47] ANSARI M A,CRAMPTON A,GARRARD R,et al.A convolutional neural network(CNN)classification to identify the presence of pores in powder bed fusion images[J].The International Journal of Advanced Manufacturing Technology,2022,120(7):5133-5150.

    • [48] CHIEN C F,DAUZÈRE-PÉRÈS S,HUH W T,et al.Artificial intelligence in manufacturing and logistics systems:algorithms,applications,and case studies[J].International Journal of Production Research,2020,58(9):2730-2731.

    • [49] XING W,LYU T,CHU X,et al.Recognition and classification of single melt tracks using deep neural network:A fast and effective method to determine process windows in selective laser melting[J].Journal of Manufacturing Processes,2021,68:1746-1757.

    • [50] XING W,CHU X,LYU T,et al.Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process[J].Journal of Manufacturing Processes,2022,74:486-499.

    • [51] FANG Q,TAN Z,LI H,et al.In-situ capture of melt pool signature in selective laser melting using U-Net-based convolutional neural network[J].Journal of Manufacturing Processes,2021,68:347-355.

    • [52] YUAN B,GIERA B,GUSS G,et al.Semi-supervised convolutional neural networks for in-situ video monitoring of selective laser melting[C]//2019 IEEE Winter Conference on Applications of Computer Vision(WACV).January 7-11,2019,Waikoloa Village,HI,USA:IEEE,2019:744-753.

    • [53] RIEDER H,DILLHÖFER A,SPIES M,et al.Online monitoring of additive manufacturing processes using ultrasound[C]//Proceedings of the 11th European Conference on Non-destructive Testing.October 6-10,2014,Prague,Czech Republic 2014,1:2194-2201.

    • [54] WANG H,LI B,XUAN F Z.Acoustic emission for in situ process monitoring of selective laser melting additive manufacturing based on machine learning and improved variational modal decomposition[J].The International Journal of Advanced Manufacturing Technology,2022,122(5-6):2277-2292.

    • [55] LI J,ZHANG X,ZHOU Q,et al.A feature-level multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Processes,2022,84:913-926.

    • [56] FLEMING T G,NESTOR S G L,ALLEN T R,et al.Tracking and controlling the morphology evolution of 3D powder-bed fusion in situ using inline coherent imaging[J].Additive Manufacturing,2020,32:100978.

    • [57] VASILESKA E,DEMIR A G,COLOSIMO B M,et al.Layer-wise control of selective laser melting by means of inline melt pool area measurements[J].Journal of Laser Applications,2020,32(2):022057.

    • [58] 陈楠.基于温度场检测的激光选区熔化实时扫描策略研究[D].武汉:华中科技大学,2020.CHEN Nan.Research on real-time scanning strategy of laser selection melting based on temperature field detection[D].Wuhan:Huazhong University of Science and Technology,2020.(in Chinese)

    • [59] LIN X,ZHU K,FUH J Y H,et al.Metal-based additive manufacturing condition monitoring methods:from measurement to control[J].ISA Transactions,2022,120:147-166.

    • [60] PENG X,KONG L.Development of a multi-sensor system for defects detection in additive manufacturing[J].Optics Express,2022,30(17):30640-30665.

    • [61] HONARVAR F,VARVANI-FARAHANI A.A review of ultrasonic testing applications in additive manufacturing:Defect evaluation,material characterization,and process control[J].Ultrasonics,2020,108:106227.

    • [62] 吴世彪,窦文豪,杨永强,等.面向激光选区熔化金属增材制造的检测技术研究进展[J].精密成形工程,2019,11(4):37–50.WU Shibiao,DOU Wenhao,YANG Yongqiang,et al.Research progress on detection technology for additive manufacturing of melted metal for laser selection[J].Precision Forming Engineering,2019,11(4):37-50.(in Chinese)

    • [63] 曹龙超,周奇,韩远飞,等.激光选区熔化增材制造缺陷智能监测与过程控制综述[J].航空学报,2021,42(10):199-233.CAO Longchao,ZHOU Qi,HAN Yuanfei,et al.A review of intelligent monitoring and process control of defects in laser selective melting additive manufacturing[J].Chinese Journal of Aeronautics and Astronautics,2021,42(10):199-233.(in Chinese)

  • 参考文献

    • [1] PENG L M,SHAN Q C,WU Y J,et al.Additive manufacturing of magnesium alloys by selective laser melting technology:A review[J].Acta Metallurgica Sinca,2023,59(1):31-54.

    • [2] 王虎,彭云,赵琳,等.选区熔化3D打印TiAl基合金的研究现状及展望[J].表面技术,2021,50(1):173-186.WANG Hu,PENG Yun,ZHAO Lin,et al.Research status and prospect of selection melting 3D printing TiAl-based alloys[J].Surface Technology,2021,50(1):173-186.(in Chinese)

    • [3] KURZYNOWSKI T,PAWLAK A,SMOLINA I.The potential of SLM technology for processing magnesium alloys in aerospace industry[J].Archives of Civil and Mechanical Engineering,2020,20(1):1-13.

    • [4] JAFARI D,WITS W W.The utilization of selective laser melting technology on heat transfer devices for thermal energy conversion applications:A review[J].Renewable and Sustainable Energy Reviews,2018,91:420-442.

    • [5] 褚清坤,余春风,邓朝阳,等.TiC 含量对激光选区熔化 Inconel 625 合金微观组织及表面摩擦磨损性能的影响[J].中国表面工程,2021,34(1):76-84.CHU Qingkun,YU Chunfeng,DENG Chaoyang,et al.Effect of TiC content on microstructure and surface friction and wear properties of Inconel 625 alloy melted by laser selective area[J].China Surface Engineering,2021,34(1):76-84.(in Chinese)

    • [6] VOLPP J.Spattering effects during selective laser melting[J].Journal of Laser Applications,2020,32(2):022023.

    • [7] 刘小辉,刘允中.激光选区熔化成形高强铝合金晶粒细化抑制裂纹研究现状[J].材料工程,2022,50(8):1-16.LIU Xiaohui,LIU Yunzhong.Research status of crack suppression of grain refinement of high-strength aluminum alloy by laser selective melting[J].Journal of Materials Engineering,2022,50(8):1-16.(in Chinese)

    • [8] CHEN J,HOU W,WANG X.Microstructure,porosity and mechanical properties of selective laser melted AlSi10Mg[J].Chinese Journal of Aeronautics,2020,33(7):2043-2054.

    • [9] WU B,JI X,ZHOU J,et al.In situ monitoring methods for selective laser melting additive manufacturing process based on images—A review[J].China Foundry,2021,18(4):265-285.

    • [10] KWON O,KIM H G,HAM M J,et al.A deep neural network for classification of melt-pool images in metal additive manufacturing[J].Journal of Intelligent Manufacturing,2020,31(2):375-386.

    • [11] NANDI S K,KUMAR R,AGRAWAL A.Computationally inexpensive semi-analytical thermal model to predict melt-pool dimensions for a single-track in selective laser melting[J].Journal of Manufacturing Processes,2022,80:469-479.

    • [12] ITO K,KUSANO M,DEMURA M,et al.Detection and location of microdefects during selective laser melting by wireless acoustic emission measurement[J].Additive Manufacturing,2021,40:101915.

    • [13] 刘萌.3D 打印SLM技术在机械自动化加工中的应用研究[J].数字技术与应用,2015,33(4):107.LIU Meng.Application of 3D printing SLM technology in mechanical automation processing[J].Digital Technology and Application,2015,33(4):107.(in Chinese)

    • [14] YE D,HONG G S,ZHANG Y,et al.Defect detection in selective laser melting technology by acoustic signals with deep belief networks[J].The International Journal of Advanced Manufacturing Technology,2018,96(5):2791-2801.

    • [15] NAGARAJAN B,HU Z,SONG X,et al.Development of micro selective laser melting:The state of the art and future perspectives[J].Engineering,2019,5(4):702-720.

    • [16] 龙旭,贾啟普,李娇,等.选区激光熔化成形TC4钛合金力学性能及其工艺关联性[J].中国表面工程,2022,35(2):215-223.LONG Xu,JIA Qipu,LI Jiao,et al.Mechanical properties and process correlation of TC4 titanium alloy formed by selective laser melting[J].China Surface Engineering,2022,35(2):215-223.(in Chinese)

    • [17] 刘文浩,陈燕,王杰,等.SLM 成型零件型腔内表面电解辅助磁粒研磨加工研究[J].中国表面工程,2021,34(3):100-109.LIU Wenhao,CHEN Yan,WANG Jie,et al.Research on electrolytic-assisted magnetic particle grinding processing of inner surface of SLM molded parts[J].China Surface Engineering,2021,34(3):100-109.(in Chinese)

    • [18] 李忠利,杜东方,雷盛.镍基合金激光选区熔化成形的缺陷形成及其控制综述[J].锻压装备与制造技术,2022,57(5):97-100.LI Zhongli,DU Dongfang,LEI Sheng.Review of defect formation and control of laser selective melting and forming of nickel-based alloy[J].Forging Equipment and Manufacturing Technology,2022,57(5):97-100.(in Chinese)

    • [19] 伍方.选择性激光熔化纯钨材料的成形技术研究[D].上海:上海大学,2021.WU Fang.Research on forming technology of selective laser melting of pure tungsten materials[D].Shanghai:Shanghai University,2021.(in Chinese)

    • [20] 毕轩.不锈钢选区激光熔化熔池及微观组织演化研究 [D].大连:大连理工大学,2021.BI Xuan.Study on laser melting pool and microscopic tissue evolution in stainless steel selection[D].Dalian:Dalian University of Technology,2021.(in Chinese)

    • [21] YADAV P,RIGO O,ARVIEU C,et al.In situ monitoring systems of the SLM process:On the need to develop machine learning models for data processing[J].Crystals,2020,10(6):524-550.

    • [22] 李文龙,戈海龙,任远,等.图像处理技术在激光熔池温度检测的应用[J].激光技术,2018,42(5):599-604.LI Wenlong,GE Hailong,REN Yuan,et.al.Application of image processing technology in temperature detection of laser molten pool[J].Laser Technology,2018,42(5):599-604.(in Chinese)

    • [23] 王奉涛,杨守华,吕秉华,等.金属增材制造过程熔池动态监测研究综述[J/OL].计算机集成制造系统:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.WANG Fengtao,YANG Shouhua,LV Binghua,et al.Research review on dynamic monitoring of melt pool in metal additive manufacturing process[J/OL].Computer Integrated Manufacturing System:1-23[2022-07-11].http://kns.cnki.net/kcms/detail/11.5946.TP.20211102.1345.004.html.(in Chinese)

    • [24] 马婷.红外热成像仪原理与应用分析[C]//第十四届宁夏青年科学家论坛石化专题论坛论文集,2018-07-24,宁夏,2018:323-325,329.MA Ting.Principle and application analysis of infrared thermal imager[C]//Proceedings of the 14th Ningxia Young Scientists Forum Petrochemical Symposium,July 24,2018,Ningxia,2018:323-325,329.(in Chinese)

    • [25] CHENG B,LYDON J,COOPER K,et al.Infrared thermal imaging for melt pool analysis in SLM:A feasibility investigation[J].Virtual and Physical Prototyping,2018,13(1):8-13.

    • [26] BARTLETT J L,HEIM F M,MURTY Y V,et al.In situ defect detection in selective laser melting via full-field infrared thermography[J].Additive Manufacturing,2018,24:595-605.

    • [27] CLIJSTERS S,CRAEGHS T,BULS S,et al.In situ quality control of the selective laser melting process using a high-speed,real-time melt pool monitoring system[J].The International Journal of Advanced Manufacturing Technology,2014,75(5):1089-1101.

    • [28] ZHANG K,LIU T,LIAO W,et al.Photodiode data collection and processing of molten pool of alumina parts produced through selective laser melting[J].Optik,2018,156:487-497.

    • [29] BARRIOBERO-VILA P,ARTZT K,STARK A,et al.Mapping the geometry of Ti-6Al-4V:From martensite decomposition to localized spheroidization during selective laser melting[J].Scripta Materialia,2020,182:48-52.

    • [30] ABOUELNOUR Y,GUPTA N.In-situ monitoring of sub-surface and internal defects in additive manufacturing:A review[J].Materials & Design,2022,222:111063.

    • [31] REN C G,LO Y L,TRAN H C,et al.Emissivity calibration method for pyrometer measurement of melting pool temperature in selective laser melting of stainless steel 316L[J].The International Journal of Advanced Manufacturing Technology,2019,105(1):637-649.

    • [32] GUTKNECHT K,HAFERKAMP L,CLOOTS M,et al.Determining process stability of laser powder bed fusion using pyrometry[J].Procedia Cirp,2020,95:127-132.

    • [33] LUONG M P.Fatigue limit evaluation of metals using an infrared thermographic technique[J].Mechanics of Materials,1998,28(1-4):155-163.

    • [34] 张勇.基于机器视觉的选区激光熔化成型质量监测的研究[D].厦门:厦门理工学院,2020.ZHANG Yong.Research on quality monitoring of selective laser melting molding based on machine vision[D].Xiamen:Xiamen University of Technology,2020.(in Chinese)

    • [35] 王晓玮.熔池图像高速采集与实时处理技术研究[D].成都:电子科技大学,2020.WANG Xiaowei.Research on high-speed acquisition and real-time processing technology of molten pool images[D].Chengdu:University of Electronic Science and Technology of China,2020.(in Chinese)

    • [36] 魏芬,吴怡,徐世武.基于机器学习与多光电二极管的可见光定位的实验研究[J/OL].激光与光电子学进展:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.WEI Fen,WU Yi,XU Shiwu.Experimental study on visible light localization based on machine learning and multiple photodiodes[J/OL].Laser and Optoelectronics:1-17[2022-11-06].http://kns.cnki.net/kcms/detail/31.1690.TN.20220713.2225.771.html.(in Chinese)

    • [37] MA P,HE X,WANG A.Design of online measurement system for molten pool morphology in selective laser melting(SLM)process[C]//2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture(AIAM),October 23-25,2021,Manchester,United Kingdom,IEEE,2021:198-204.

    • [38] 赵德陈,林峰.金属粉末床熔融工艺在线监测技术综述[J].中国机械工程,2018,29(17):2100-2110,2118.ZHAO Dechen,LIN Feng.Review of online monitoring technology of metal powder bed melting process[J].China Mechanical Engineering,2018,29(17):2100-2110,2118.(in Chinese)

    • [39] KANKO J A,SIBLEY A P,FRASER J M.In situ morphology-based defect detection of selective laser melting through inline coherent imaging[J].Journal of Materials Processing Technology,2016,231:488-500.

    • [40] MAZZOLENI L,CAPRIO L,PACHER M,et al.External illumination strategies for melt pool geometry monitoring in SLM [J].JOM,2019,71(3):928-937.

    • [41] LIU Y,ZHANG M,SHI W,et al.Study on performance optimization of 316L stainless steel parts by high-efficiency selective laser melting[J].Optics & Laser Technology,2021,138:106872.

    • [42] 朱锟鹏,王齐胜,林昕,等.基于熔池运动特征的选区激光熔融过程状态检测方法[J].计算机集成制造系统,2021,27(12):3403-3415.ZHU Kunpeng,WANG Qisheng,LIN Xin,et al.Selection laser melting process state detection method based on molten pool motion characteristics[J].Computer Integrated Manufacturing Systems,2021,27(12):3403-3415.(in Chinese)

    • [43] LI J,CAO L,XU J,et al.In situ porosity intelligent classification of selective laser melting based on coaxial monitoring and image processing[J].Measurement,2022,187:110232.

    • [44] LIN X,WANG Q,FUH J Y H,et al.Motion feature based melt pool monitoring for selective laser melting process[J].Journal of Materials Processing Technology,2022,303:117523.

    • [45] MODARESIALAM M,ROOZBAHANI H,ALIZADEH M,et al.In-situ monitoring and defect detection of selective laser melting process and impact of process parameters on the quality of fabricated SS 316L[J].IEEE Access,2022,10:46100-46113.

    • [46] LI J,ZHOU Q,CAO L,et al.A convolutional neural network-based multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Systems,2022,64:429-442.

    • [47] ANSARI M A,CRAMPTON A,GARRARD R,et al.A convolutional neural network(CNN)classification to identify the presence of pores in powder bed fusion images[J].The International Journal of Advanced Manufacturing Technology,2022,120(7):5133-5150.

    • [48] CHIEN C F,DAUZÈRE-PÉRÈS S,HUH W T,et al.Artificial intelligence in manufacturing and logistics systems:algorithms,applications,and case studies[J].International Journal of Production Research,2020,58(9):2730-2731.

    • [49] XING W,LYU T,CHU X,et al.Recognition and classification of single melt tracks using deep neural network:A fast and effective method to determine process windows in selective laser melting[J].Journal of Manufacturing Processes,2021,68:1746-1757.

    • [50] XING W,CHU X,LYU T,et al.Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process[J].Journal of Manufacturing Processes,2022,74:486-499.

    • [51] FANG Q,TAN Z,LI H,et al.In-situ capture of melt pool signature in selective laser melting using U-Net-based convolutional neural network[J].Journal of Manufacturing Processes,2021,68:347-355.

    • [52] YUAN B,GIERA B,GUSS G,et al.Semi-supervised convolutional neural networks for in-situ video monitoring of selective laser melting[C]//2019 IEEE Winter Conference on Applications of Computer Vision(WACV).January 7-11,2019,Waikoloa Village,HI,USA:IEEE,2019:744-753.

    • [53] RIEDER H,DILLHÖFER A,SPIES M,et al.Online monitoring of additive manufacturing processes using ultrasound[C]//Proceedings of the 11th European Conference on Non-destructive Testing.October 6-10,2014,Prague,Czech Republic 2014,1:2194-2201.

    • [54] WANG H,LI B,XUAN F Z.Acoustic emission for in situ process monitoring of selective laser melting additive manufacturing based on machine learning and improved variational modal decomposition[J].The International Journal of Advanced Manufacturing Technology,2022,122(5-6):2277-2292.

    • [55] LI J,ZHANG X,ZHOU Q,et al.A feature-level multi-sensor fusion approach for in-situ quality monitoring of selective laser melting[J].Journal of Manufacturing Processes,2022,84:913-926.

    • [56] FLEMING T G,NESTOR S G L,ALLEN T R,et al.Tracking and controlling the morphology evolution of 3D powder-bed fusion in situ using inline coherent imaging[J].Additive Manufacturing,2020,32:100978.

    • [57] VASILESKA E,DEMIR A G,COLOSIMO B M,et al.Layer-wise control of selective laser melting by means of inline melt pool area measurements[J].Journal of Laser Applications,2020,32(2):022057.

    • [58] 陈楠.基于温度场检测的激光选区熔化实时扫描策略研究[D].武汉:华中科技大学,2020.CHEN Nan.Research on real-time scanning strategy of laser selection melting based on temperature field detection[D].Wuhan:Huazhong University of Science and Technology,2020.(in Chinese)

    • [59] LIN X,ZHU K,FUH J Y H,et al.Metal-based additive manufacturing condition monitoring methods:from measurement to control[J].ISA Transactions,2022,120:147-166.

    • [60] PENG X,KONG L.Development of a multi-sensor system for defects detection in additive manufacturing[J].Optics Express,2022,30(17):30640-30665.

    • [61] HONARVAR F,VARVANI-FARAHANI A.A review of ultrasonic testing applications in additive manufacturing:Defect evaluation,material characterization,and process control[J].Ultrasonics,2020,108:106227.

    • [62] 吴世彪,窦文豪,杨永强,等.面向激光选区熔化金属增材制造的检测技术研究进展[J].精密成形工程,2019,11(4):37–50.WU Shibiao,DOU Wenhao,YANG Yongqiang,et al.Research progress on detection technology for additive manufacturing of melted metal for laser selection[J].Precision Forming Engineering,2019,11(4):37-50.(in Chinese)

    • [63] 曹龙超,周奇,韩远飞,等.激光选区熔化增材制造缺陷智能监测与过程控制综述[J].航空学报,2021,42(10):199-233.CAO Longchao,ZHOU Qi,HAN Yuanfei,et al.A review of intelligent monitoring and process control of defects in laser selective melting additive manufacturing[J].Chinese Journal of Aeronautics and Astronautics,2021,42(10):199-233.(in Chinese)

  • 手机扫一扫看