激光选区熔化增材制造缺陷智能监测与过程控制综述
曹龙超1,2, 周奇1, 韩远飞3, 宋波2, 聂振国4, 熊异5, 夏凉6
1. 华中科技大学 航空航天学院, 武汉 430074;
2. 华中科技大学 材料科学与工程学院 材料成形与模具技术国家重点实验室, 武汉 430074;
3. 上海交通大学 材料科学与工程学院 金属基复合材料国家重点实验室, 上海 200240;
4. 清华大学 机械工程系, 北京 100084;
5. 南方科技大学 系统设计与智能制造学院, 深圳 518005;
6. 华中科技大学 机械科学与工程学院 数字制造装备与技术国家重点实验, 武汉 430074
CAO Longchao1,2, ZHOU Qi1, HAN Yuanfei3, SONG Bo2, NIE Zhenguo4, XIONG Yi5, XIA Liang6
1. School of Aerospace Engineering, Huazhong University of Science & Technology, Wuhan 430074, China;
2. State Key Laboratory of Materials Processing and Die and Mould Technology, School of Materials Science and Engineering, Huazhong University of Science & Technology, Wuhan 430074, China;
3. State Key Laboratory of Metal Matrix Composites, School of Mechanical Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China;
4. Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China;
5. School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518005, China;
6. State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
关键词: 激光选区熔化(SLM), 增材制造, 过程监测, 机器学习, 质量控制
Abstract: Selective Laser Melting (SLM) is considered to be one of the most promising additive manufacturing technologies and has been applied in aerospace, medical equipment and other fields. However, how to ensure the reliability of component quality and the repeatability of manufacturing is the largest challenge faced by SLM, which has been regarded as the biggest barrier to the development and industrial application of SLM and other metal additive manufacturing technologies. The main reason is that the defects generated during the SLM process are difficult to control. Therefore, process monitoring and real-time feedback control of SLM is an important research direction to solve this problem, which has become one of the research hotspots in academia and industry. Based on a literature survey in this field in the past ten years, the common metallurgical defects and their generation mechanisms in metal laser additive manufacturing are reviewed, and the signals generated during the metal additive manufacturing process and their monitoring methods, such as acoustic signal, optical signal, and thermal Signal, are described in detail. Signal data processing methods are summarized, including traditional statistical processing methods and emerging intelligent monitoring methods based on machine learning. Then, the quality control methods of metal additive manufacturing processes, including non-closed loop control and closed-loop control, are reviewed. Directions worthy of future research of SLM intelligent monitoring and control are also discussed.
Key words: Selective Laser Melting(SLM), additive manufacturing, process monitoring, machine learning, quality control