Page 127 - 无损检测2024年第八期
P. 127
述
综
综 述
DOI:10.11973/wsjc202408015
机器学习在金属磁记忆检测中的应用与展望
王慧鹏 ,李海航 ,石家龙 ,董丽虹 ,王海斗 3
1
1
2
1,2
(1. 江西理工大学 机电工程学院,赣州 341000;2. 陆军装甲兵学院 再制造技术国家重点实验室,北京 100072;
3. 陆军装甲兵学院 机械产品再制造国家工程研究中心,北京 100072)
摘 要:金属磁记忆检测技术(MMMT)能够检测以应力集中为代表的早期损伤,在铁磁性构
件损伤检测领域具有广阔的应用前景。由于金属磁记忆检测信号十分微弱并且具有较强的非线性,
在实际检测时容易出现漏检或误检。机器学习方法对信号数据集特征分析具有良好的自学习和自
适应性能力,较适合金属磁记忆检测信号的分析与处理。对机器学习技术在金属磁记忆检测中的
应用进行了综述,讨论了金属磁记忆信号传统特征提取方法的特点,分析了机器学习在金属磁记忆
检测中的特征提取、定量识别及剩余寿命预测等方面的研究现状,指出了机器学习在金属磁记忆检
测领域的难点问题,并对其发展方向进行了展望。
关键词:金属磁记忆检测;机器学习;特征提取;定量识别;寿命预测
中图分类号:TG115.28 文献标志码:A 文章编号:1000-6656(2024)08-0089-07
Application and prospects of machine learning on metal magnetic memory testing
WANG Huipeng , LI Haihang , SHI Jialong 1, 2 , DONG Lihong , WANG Haidou 3
1
2
1
(1. School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China;
2. National Key Laboratory for Remanufacturing, Army Academy of Armored Forces, Beijing 100072, China;
3. National Engineering Research Center for Remanufacturing, Army Academy of Armored Forces, Beijing 100072, China)
Abstract: Metal magnetic memory testing (MMMT) can detect early damage represented by stress concentration,
and has broad application prospects in the field of damage detection of ferromagnetic components. However, the MMMT
signals are very weak and nonlinear, and it is prone to have no warning or false warning applied the MMMT is applied in
engineering application. The machine learning method is suitable for data processing and analysis in MMMT for its good
self-learning ability and adaptability for characteristic patterns finding. This paper focused on the application of machine
learning methods in metal magnetic memory testing. The traditional feature extraction methods of MMMT signals were
discussed, and the research status of machine learning methods in feature extraction, quantitative recognition and residual
life prediction of metal magnetic memory testing was analyzed. The difficulties and future development direction of machine
learning methods in the field of metal magnetic memory testing were discussed.
Key words: metal magnetic memory testing; machine learning; feature extraction; quantitative identification; life
prediction
机械设备的大部分重要金属零部件均由铁磁性 交变荷载作用,极易出现疲劳失效,而导致机械设备
材料制造而成,这些部件在运行过程中频繁地承受 发生不可逆损坏 。为确保人员安全与设备稳定运
[1]
行,非常有必要对铁磁性材料进行疲劳损伤检测。
收稿日期:2023-11-22
疲劳损伤是指疲劳载荷作用下,材料微观结构
基金项目:国家自然科学基金(52065026)
作者简介:王慧鹏(1983—),男,博士,副教授,硕士生导师,主要 变化,产生微观裂纹和孔洞等缺陷,进而引发材料损
从事无损检测技术、无损评价等方面的研究工作
伤累积和结构性能衰退的过程,包含疲劳裂纹的萌
通信作者:董丽虹(1972—),女,博士,副研究员,博士生导师,主
要从事无损检测与再制造寿命预测工作 lihong.dong@126.com 生、扩展,直到构件的破坏阶段。铁磁性构件的疲劳
89
2024 年 第 46 卷 第 8 期
无损检测

