| 1,326 | 0 | 35 |
| 下载次数 | 被引频次 | 阅读次数 |
激光增材制造技术可以快速制造出形状结构复杂且尺寸精度高的零件，被广泛应用于汽车、航空航天和医疗器械等领域。在激光增材制造过程中，为了得到性能更佳的合金和适用于不同材料的工艺参数，需要进行大量的反复试验，耗时且成本较高。机器学习通过输入试验数据和采用特定的算法，建立起能泛化的模型并通过自我更新和优化来不断提高结果的准确性，可以有效预测增材制造材料的成分、性能和缺陷，在高性能辅助材料开发方面具有广阔的发展前景。从上述三方面总结了近年来机器学习在激光增材制造中的应用实例，并提出了其未来发展的趋势及应用方向。
Abstract：Laser additive manufacturing technology can quickly manufacture parts with complex shapes and structures, and high dimensional accuracy, are widely used in fields such as automotive, aerospace, and medical devices. In the process of laser additive manufacturing, a large number of trial and error are required to obtain both the alloys with better performance and the process parameters suitable for different materials, which are time-consuming and costly. By inputting experimental data and using specific algorithms the machine learning establishes a model which can be generalized and continuously increase the accuracy of results through self-updating and optimization, effectively predict the composition, performance, and defects of additive manufacturing materials, and has broad development prospects in the aspect of development of high-performance auxiliary materials. The application examples of the machine learning in the laser additive manufacturing in recent years were summarized from the above three aspects, and finally its future development trends and application directions were proposed.
[1] 戴功旺.3D打印颠覆传统制造是噱头还是未来[J].中国战略新兴产业，2018(41):70- 72.
[2] 孙暄，胡斌，熊智慧，等.航空航天领域用增材制造金属材料的研究进展[J].上海金属，2024,46(3):1- 12.
[3] 秋大闯，李多生，叶寅，等.SLM成形镍基高温合金及其数值模拟的研究进展[J].材料保护，2019,50(3):3049- 3058.
[4] 王天元，黄帅，周标，等.航空装备激光增材制造技术发展及路线图[J].航空材料学报，2023,43(1):1- 17.
[5] 龚小弟，王智，于宁，等.用于选择性激光烧结的聚合物粉末材料研究进展[J].材料保护，2019,50(10):10027- 10039.
[6] Fuel Oil News Group.ASTM international adds certification capabilities[J].Fuel Oil News,2010,75(1):10- 12.
[7] 顾波.增材制造技术国内外应用与发展趋势[J].金属加工(热加工),2022(3):1- 16.
[8] 编辑部.3D打印又有零的突破我国“增材制造”首项国标发布[J].粉末冶金工业，2022,32(1):110.
[9] AKBARI P,OGOKE F,KAO N Y,et al.MeltpoolNet:melt pool characteristic prediction in metal additive manufacturing using machine learning[J].Additive Manufacturing,2022,55:102817.
[10] WANG X D,CHEN B.Origin of Fresnel problem of two dimensional materials[J].Scientific Reports,2019,9:17825.
[11] TANG Z Q,PENG X,LI K,et al.Towards efficient U- nets:a coupled and quantized approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,42(8):2038- 2050.
[12] LAIADI O,OUAMANE A,BENAKCHA A,et al.A weighted exponential discriminant analysis through side- information for face and kinship verification using statistical binarized image features[J].International Journal of Machine Learning and Cybernetics,2020,12:171- 185.
[13] BIANCO M J,GERSTOFT P,TRAER J,et al.Machine learning in acoustics:theory and applications[J].Acoustical Society of America,2019,146(5):3590- 3628.
[14] 苏金龙，陈乐群，谭超林，等.基于机器学习的增材制造过程优化与新材料研发进展[J].中国激光，2022,49(14):11- 22.
[15] MAHESH B.Machine learning algorithms:a review[J].International Journal of Science and Research,2020,9(1):381- 386.
[16] PREATONI E,NODARI S,LOPOMO N F.Supervised machine learning applied to wearable sensor data can accurately classify functional fitness exercises within a continuous workout[J].Frontiers in Bioengineering and Biotechnology,2020,8:664.
[17] KASIHMUDDIN M S M,JAMALUDIN S Z M,MANSOR M A,et al.Supervised learning perspective in logic mining[J].Mathematics,2022,10(6):10060915.
[18] 袁源，郭进利.基于复杂网络上监督学习方法的研究综述[J].运筹与管理，2022,31(12):234- 239.
[19] 李永国，徐彩银，汤璇，等.半监督学习方法研究综述[J].世界科技研究与发展，2023,45(1):26- 40.
[20] VILORIA A,ZELAYA N A L,VARELA N.Unsupervised learning algorithms applied to grouping problems[J].Procedia Computer Science,2020,175:677- 682.
[21] SHAKYA A K,PILLAI G,CHAKRABARTY S.Reinforcement learning algorithms:a brief survey[J].Expert Systems with Applications,2023,231:120459.
[22] RAZA A,DEEN M K,JAAFREH R,et al.Incorporation of machine learning in additive manufacturing:a review[J].International Journal of Advanced Manufacturing Technology,2022,122:1143- 1166.
[23] MENG L B,WILLIAMS B,JAROSINSKI W,et al.Machine learning in additive manufacturing:a review[J].JOM,2020,72(6):2363- 2377.
[24] HES R,GIOROLI G.A distributed unsupervised learning algorithm and its suitability to physical based observation[J].International Journal of Parallel,Emergent and Distributed Systems,2022,37(4):443- 455.
[25] ZHOU Y,GAN G Y,YI J H,et al.Research status of the rare and precious metals’ materials genome initiative[J].Journal of Micromechanics and Molecular Physics,2020,5(2):2040002.
[26] MEREDITH D.Materials genome initiative:advances and initiatives[J].JOM,2014,66(3):334- 335.
[27] MIAO J C,ZHANG L H,LI Z Y,et al.Material database for the mechanical design of components made of powder metallurgy material[C]//International Conference on Gears.Munich:VDI Wissensforum GmbH,2023.
[28] YAMAZAKI M.Development and challenge of materials database:a case study of NIMS materials database[C]// The Second Asia Materials Science Database Symposium.Sanya:University of Science and Technology Beijing,2010.
[29] 文成.基于机器学习的高熵合金成分设计与性能优化[D].北京：北京科技大学，2022
[30] DECOST B L,JAIN H,ROLLETT A D,et al.Computer vision and machine learning for autonomous characterization of AM powder feedstocks[J].The Minerals,Metals & Materials Society,2016,69(3):456- 465.
[31] DECOST B L,HOLM E A.A computer vision approach for automated analysis and classification of microstructural image data[J].Computational Materials Science,2015,110:126- 133.
[32] MARTIN J H,YAHATA B D,HUNDLEY J M,et al.3D printing of high- strength aluminium alloys[J].Nature Letters,2017,549:365- 369.
[33] 乐夏唯.基于机器学习的倾斜基板激光增材制造工艺优化研究[D].徐州：中国矿业大学，2022.
[34] LUO C Q,ZHU S P,KESHTEGAR B,et al.An enhanced uniform simulation approach coupled with SVR for efficient structural reliability analysis[J].Reliability Engineering and System Safety,2023,237:109337.
[35] SAFARI M,RABIEE A H,JOUDAKI J.Developing a support vector regression (SVR) model for prediction of main and lateral bending angles in laser tube bending process[J].Materials,2023,16(8):32- 51.
[36] ZHANG G J,LIU C Y,MIN K,et al.A GAN- BPNN- based surface roughness measurement method for robotic grinding[J].Machines,2022,10(11):10- 26.
[37] SONG Y Q,ZHANG C J,JIN X,et al.Spatial prediction of PM2.5 concentration using hyper- parameter optimization XGBoost model in China[J].Environmental Technology & Innovation,2023,32:103272.
[38] BARNWAL A,CHO H,HOCKING T.Survival regression with accelerated failure time model in XGBoost[J].Journal of Computational and Graphical Statistics,2022,31(4):1292- 1302.
[39] 张治洲.基于深度学习的3D打印金属材料力学性能预测方法研究[D].广州：暨南大学，2019.
[40] JIN L,WAN X T.Image recognition algorithm based on improved AlexNet and shared parameter transfer learning[J].Academic Journal of Computing & Information Science,2022,5(12):6- 14.
[41] PRANOTO H,HERYADI Y,WARNARS H L H S,et al.Enhanced IPCGAN-Alexnet model for new face image generating on age target[J].Journal of King Saud University:Computer and Information Sciences,2022,34(9):7236- 7246.
[42] ZHU F Z,LI J C,ZHU B,et al.UAV remote sensing image stitching via improved VGG16 Siamese feature extraction network[J].Expert Systems with Applications,2023,229:120525.
[43] DUBAY A K,JAIN V.Automatic facial recognition using VGG16 based transfer learning model[J].Journal of Information and Optimization Sciences,2020,41(7):1589- 1596.
[44] BARRIONUEVO G O,RAMOS- GREZ J A,WALCZAK M,et al.Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting[J].International Journal of Advanced Manufacturing Technology,2021,113:419- 433.
[45] PARK H S,NGUYEN D S,HONG T L,et al.Machine learning- based optimization of process parameters in selective laser melting for biomedical applications[J].Journal of Intelligent Manufacturing,2022,33:1843- 1858.
[46] SOMMACAL S,MATSCHINSKI A,HOLMES J,et al.Detailed void characterisation by X- ray computed tomography of material extrusion 3D printed carbon fibre/PEEK[J].Composite Structures,2023,308:116635.
[47] LAWRENCE T J,CARR S J,MANNING A J,et al.A novel 3D volumetric method for directly quantifying porosity and pore space morphology in flocculated suspended sediments[J].MethodsX,2023,10:101975.
[48] HUANG H,SHAN Z D,LIU J H,et al.A unified trans- scale mechanical properties prediction method of 3D composites with void defects[J].Composite Structures,2023,306:116572.
[49] YANG L X,ZOU Z H,KOU Z D,et al.High temperature stress and its influence on surface rumpling in NiCoCrAlY bond coat[J].Acta Materialia,2017,139:122- 137.
[50] CHIKOSHA S,TSHABALALA L C,BISSETT H,et al.Spheroidisation of stainless steel powder for additive manufacturing[J].Metals,2021,11(7):11071081.
[51] STAUB A,BRUNNER L,SPIERINGS A B,et al.A machine- learning-based approach to critical geometrical feature identification and segmentation in additive manufacturing[J].Technologies,2022,10(5):10050102.
[52] LI R,JIN M Z,PAQUIT V C.Geometrical defect detection for additive manufacturing with machine learning models[J].Materials & Design,2021,206:109726.
[53] KHANZADEH M,CHOWDHURY S,TSCHOPP M A,et al.In- situ monitoring of melt pool images for porosity prediction in directed energy deposition processes[J].IISE Transactions,2019,51(5):437- 455.
[54] PENG T,KELLENS K,TANG R Z,et al.Sustainability of additive manufacturing:an overview on its energy demand and environmental impact[J].Additive Manufacturing,2018,21:694- 704.
[55] NASIRI S,KHOSRAVANI M R.Machine learning in predicting mechanical behavior of additively manufactured parts[J].Journal of Materials Research and Technology,2021,14:1137- 1153.
[56] KONONENKO D Y,NIKONOVA V,SELEZNEV M,et al.An in situ crack detection approach in additive manufacturing based on acoustic emission and machine learning[J].Additive Manufacturing Letters,2023,5:100- 130.
[57] 穆亚航，张雪，陈梓名，等.基于热力学计算与机器学习的增材制造镍基高温合金裂纹敏感性预测模型[J].金属学报，2023,59(8):1075- 1086.
[58] ZHAN Z X,LI H.Machine learning based fatigue life prediction with effects of additive manufacturing process parameters for printed SS 316L[J].International Journal of Fatigue,2021,142:105941.
[59] 肖斌，吴雨沁，刘轶.基于第一性原理计算的镍基单晶高温合金掺杂的机器学习研究[J].上海金属，2020,42(3):97- 104,110.
基本信息:
DOI：10.19947/j.issn.1001-7208.2024.02.04
中图分类号:TG665;TP181
引用信息:
[1]李翔,张亮,李京伟.机器学习的发展现状及其在激光增材制造中的应用[J].上海金属,2025,47(04):1-12.DOI:10.19947/j.issn.1001-7208.2024.02.04.
基金信息:
国家自然科学基金(52111540265)