计算辅助高性能增材制造铝合金开发的研究现状与展望

高建宝, 李志诚, 刘佳, 张金良, 宋波, 张利军

Current Situation and Prospect of Computationally Assisted Design in High-Performance Additive Manufactured Aluminum Alloys: A Review

GAO Jianbao, LI Zhicheng, LIU Jia, ZHANG Jinliang, SONG Bo, ZHANG Lijun

图11 基于物理信息的机器学习方法设计无裂纹3D打印件流程图[33]

Fig.11 A physics-informed machine learning towards crack-free printing[33]. Computed values of cooling rate and solidification morphology (indicated by the ratio of temperature gradient and solidification growth rate) at the trailing edge of the melt pool, the ratio of vulnerable and relaxation times, and solidification stress are used in a physics informed machine learning to accurately predict cracking during SLM of aluminum alloys. The combination of machine learning and mechanistic modeling gives a cracking susceptibility index, process maps for crack-free printing, the comparative influence of the important variables, and a decision tree to predict crack formation[33] (PBF-L—powder bed fusion- laser)