基于致密度和显微组织的IN625合金激光粉末床熔融工艺优化

doi:10.13251/j.issn.0254-6051.2024.03.014

摘要/Abstract

摘要： 基于高斯过程回归(GPR)模型,对激光粉末床熔融(LPBF)增材工艺制备的IN625合金的致密度、晶粒取向和晶粒长径比的观测数据进行了机器学习,确定了具有特定组织特征的致密IN625合金的LPBF工艺窗口,并探讨了激光功率(P)-扫描速度(v)工艺组合以及激光能量密度对合金致密度和显微组织的影响。结果发现,获得高致密(≥99%)合金的激光能量密度需≥55 J/mm³,适宜的P-v工艺窗口呈梨形,高激光功率(P)下可选择的扫描速度(v)范围较宽。LPBF合金的柱状晶具有<001>//BD的择优取向,其取向强度及长径比随着激光能量密度的提高而增加,但超过一定值后会有所下降。经交叉验证表明,GPR预测的以致密度和组织特征为目标的LPBF优化工艺窗口是可靠的,该方法可拓展应用到其它合金基于多目标的激光增材工艺优化设计中。

关键词: 激光粉末床熔融, 高斯过程回归, 相对致密度, 显微组织

Abstract: A machine-learning approach based on gaussian process regression (GPR) was proposed to optimize the processing window of laser power (P) and scanning speed (v) in the IN625 alloy fabricated by laser powder bed fusion (LPBF) using the experimental data of relative density, crystallography orientation and shape aspect ratio of columnar grains. The effect of laser power-scanning speed combinations and laser energy density (ED) on the relative density and microstructure of the LPBF specimens was investigated as well. The results show that the applied laser ED≥55 J/mm³ is prerequisite for fully dense LPBF specimens with relative density ≥99%. The optimized L-PBF processing window for manufacturing fully dense IN625 alloy is pear-shaped, and the selectable scanning speed range can be wide in the case of high laser power. The LPBF specimens possess the columnar grains with the preferred orientation <001> parallel to build direction (BD). The preferred orientation intensity and the shape aspect ratio of the columnar grains tend to increase with the laser ED but marginally decrease after a high ED value. The leave-one-out cross validation reveals that the GPR model predicting the optimized LPBF process window based on relative density and microstructure features is reliable and can be readily applied to multi-objective optimization of laser additive manufacturing process in other metals and alloys.

Key words: laser powder bed fusion, gaussian process regression, relative density, microstructure

中图分类号:

TG146.1

杜文祥, 曹李策, 申发磊, 潘来涛, 王泽龙, 孙业东, 方晓英. 基于致密度和显微组织的IN625合金激光粉末床熔融工艺优化[J]. 金属热处理, 2024, 49(3): 83-90.

Du Wenxiang, Cao Lice, Shen Falei, Pan Laitao, Wang Zelong, Sun Yedong, Fang Xiaoying. Process optimization of laser powder bed fusion for IN625 alloy based on densification and microstructure[J]. Heat Treatment of Metals, 2024, 49(3): 83-90.

参考文献

[1]Khairallah S A, Martin A A, Lee J R I, et al. Controlling interdependent meso-nanosecond dynamics and defect generation in metal 3D printing[J]. Science, 2020, 368(6491): 660-665.
[2]Schneider J, Lund B, Fullen M. Effect of heat treatment variations on the mechanical properties of Inconel 718 selective laser melted specimens[J]. Additive Manufacturing, 2018, 21: 248-254.
[3]Acharya R, Sharon A J, Staroselsky A. Prediction of microstructure in laser powder bed fusion process[J]. Acta Materialia, 2017, 124: 360-371.
[4]Kranz J, Herzog D, Emmelmann C. Design guidelines for laser additive manufacturing of lightweight structures in TiAl6V4[J]. Journal of Laser Applications, 2014, 27(S1): 14001.
[5]Awad A, Fina F, Goyanes A, et al. Advances in powder bed fusion 3D printing in drug delivery and healthcare[J]. Advanced Drug Delivery Reviews, 2021, 174: 406-424.
[6]Yang T, Dacian T, Paul R, et al. Influences of processing parameters on surface roughness of Hastelloy X produced by selective laser melting[J]. Additive Manufacturing, 2017, 13: 103-112.
[7]Shen X F, Cheng Z Y, Wang C G, et al. Effect of heat treatments on the microstructure and mechanical properties of Al-Mg-Sc-Zr alloy fabricated by selective laser melting[J]. Optics and Laser Technology, 2021, 143: 107312.
[8]ZhangJ L, Song B, Wei Q S, et al. A review of selective laser melting of aluminum alloys: Processing, microstructure, property and developing trends[J]. Journal of Materials Science & Technology, 2018, 35(2): 270-284.
[9]Vukkum V B, Gupta R K. Review on corrosion performance of laser powder-bed fusion printed 316L stainless steel: Effect of processing parameters, manufacturing defects, post-processing, feedstock, and microstructure[J]. Materials & Design, 2022, 221: 110874.
[10]Koutiri I, Pessard E, Peyre P, et al. Influence of SLM process parameters on the surface finish, porosity rate and fatigue behavior of as-built Inconel 625 parts[J]. Journal of Materials Processing Technology, 2017, 255: 536-546.
[11]Brennan M C, Keist J S, Palmer T A. Defects in metal additive manufacturing processes[J]. Journal Materials Engineering Performance, 2021, 30: 4808-4818.
[12]Gokcekaya O, Ishimoto T, Hibino S, et al. Unique crystallographic texture formation in Inconel 718 by laser powder bed fusion and its effect on mechanical anisotropy[J]. Acta Materialia, 2021, 212: 116876.
[13]Galina K, Jan H, Joachim G, et al. Correlation between porosity and processing parameters in TiAl6V4 produced by selective laser melting[J]. Materials & Design, 2016, 105: 160-170.
[14]Ross C, Zhao C, Niranjan P, et al. Keyhole threshold and morphology in laser melting revealed by ultrahigh-speed X-ray imaging[J]. Science, 2019, 363(6429): 849-852.
[15]Mugwagwa L, Dimitrov D, Matope S, et al. Influence of process parameters on residual stress related distortions in selective laser melting[J]. Procedia Manufacturing, 2018, 21: 92-99.
[16]Zhang S, Xu S B, Pan Y F, et al. Mechanism study of the effect of selective laser melting energy density on the microstructure and properties of formed renewable porous bone scaffolds[J]. Metals, 2022, 12(10): 1712-1712.
[17]Shi W T, Li J H, Liu Y D, et al. Experimental study on mechanism of influence of laser energy density on surface quality of Ti-6Al-4V alloy in selective laser melting[J]. Journal of Central South University, 2022, 29(10): 3447-3462.
[18]Marial, Miguel G M, Kurt B, et al. Microstructure evolution of 316L produced by HP-SLM (high power selective laser melting)[J]. Additive Manufacturing, 2018, 23: 402-410.
[19]Önder S, Saklakoglu N. Selective laser melting of Ti6Al4V alloy: Effects of process parameters at constant energy density on mechanical properties, residual stress, microstructure and relative density[J]. Materials Testing, 2023, 65(2): 162-173.
[20]Johnso N S, Vulimiri P S, To A C, et al. Invited review: Machine learning for materials developments in metals additive manufacturing[J]. Additive Manufacturing, 2020, 36: 101641.
[21]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): 3-14.
Su Jinlong, Chen Lequn, Tan Chaolin, et al. Progress in machine-learning-assisted process optimization and novel material development in additive manufacturing[J]. Chinese Journal of Lasers, 2022, 49(14): 3-14.
[22]Tapia G, Elwany A H, Sang H. Prediction of porosity in metal-based additive manufacturing using spatial gaussian process models[J]. Additive Manufacturing, 2016, 12: 282-290.
[23]Chandrika K, Fan Y J. Regression with small data sets: A case study using code surrogates in additive manufacturing[J]. Knowledge and Information System, 2018, 57(2): 475-493.
[24]Liu Q, Wu H H, Paul M J, et al. Machine-learning assisted laser powder bed fusion process optimization for AlSi10Mg: New microstructure description indices and fracture mechanisms[J]. Acta Mater, 2020, 201: 316-328.
[25]He P D, Liu Q, Krizic J J, et al. Machine-learning assisted additive manufacturing of a TiCN reinforced AlSi10Mg composite with tailorable mechanical properties[J]. Materials Letters, 2022, 307: 131018.
[26]孙业东, 姜夕义, 李昊卿, 等. 基于机器学习的Ti-6Al-4V合金激光粉末床熔融工艺优化[J]. 中国有色金属学报, 2022, 32(10): 3085-3095.
Sun Yedong, Jiang Xiyi, Li Haoqing, et al. Optimization of selective laser powder bed fusion process for Ti-6Al-4V alloy based on machine-learning[J]. The Chinese Journal of Nonferrous Metals, 2022, 32(10): 3085-3095.
[27]Sam C, Manisha B, Jan P, et al. Prediction of lack of fusion porosity in selective laser melting based on melt pool monitoring data[J]. Additive Manufacturing, 2018, 25: 347-356.
[28]Masoumeh A, Thomas R. Online quality inspection using Bayesian classification in powder-bed additive manufacturing from high-resolution visual camera images[J]. Journal of Intelligent Manufacturing, 2019, 30(6): 2505-2523.
[29]Chen Z, Lu Y X, Luo F, et al. Effect of laser scanning speed on the microstructure and mechanical properties of laser-powder-bed-fused k418 nickel-based alloy[J]. Materials, 2022, 15(9): 3045-3045.
[30]Gaur R, Bhanupratap R, Ghyar R, et al. Parameter optimization for printing Ti6Al4V-alloy patient-customized orthopaedic implants by laser powder bed fusion using physio-mechanical properties and biological evaluations[J]. Indian Journal of Orthopaedics, 2022, 56(5): 797-804.
[31]Liu K, Gu D D, Guo M, et al. Effects of processing parameters on densification behavior, microstructure evolution and mechanical properties of W-Ti alloy fabricated by laser powder bed fusion[J]. Materials Science & Engineering A, 2022, 829.
[32]Li B, Zhang W, Xuan F Z. Machine-learning prediction of selective laser melting additively manufactured part density by feature-dimension-ascended Bayesian network model for process optimisation[J]. The International Journal of Advanced Manufacturing Technology, 2022, 121(5-6): 4023-4038.
[33]Jessica G, Dominik B, Thorsten S, et al. Advanced microstructure classification by data mining methods[J]. Computational Materials Science, 2018, 148: 324-335.
[34]Azimi S M, Britz D, Engstler M, et al. Advanced steel microstructural classification by deep learning methods[J]. Scientific Reports, 2018, 8(1): 2128.
[35]Kang J, Hu X H, Wright S I, et al. On the calculation of volume fraction of texture components in aa5754 sheet materials[J]. Metallurgical and Materials Transactions, 2008(8): 2007-2013.
[36]Liu Q, Wu H K, Paul M J, et al. Machine-learning assisted laser powder bed fusion process optimization for AlSi10Mg: New microstructure description indices and fracture mechanisms[J]. Acta Mater, 2020, 201: 316-328.