[1]李栋,龚兰兰,刘树林,等.基于生物免疫机理的连续学习故障诊断方法[J].常州大学学报(自然科学版),2022,34(06):54-62.[doi:10.3969/j.issn.2095-0411.2022.06.007]
　LI Dong,GONG Lanlan,LIU Shulin,et al.Fault Diagnosis Method with Continual Learning Capacity Based on the Biological Immune Mechanism[J].Journal of Changzhou University(Natural Science Edition),2022,34(06):54-62.[doi:10.3969/j.issn.2095-0411.2022.06.007]
点击复制

基于生物免疫机理的连续学习故障诊断方法()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第34卷
期数:
2022年06期
页码:
54-62
栏目:
计算机与信息工程
出版日期:
2022-11-28

文章信息/Info

Title:
Fault Diagnosis Method with Continual Learning Capacity Based on the Biological Immune Mechanism
文章编号:
2095-0411(2022)06-0054-09
作者:
李栋1; 龚兰兰1; 刘树林2; 孙欣2; 雷勇3
(1.常州大学石油工程学院,江苏常州213164;2.上海大学机电工程与自动化学院,上海200444;3.渤海船舶重工有限责任公司,辽宁葫芦岛125004)
Author(s):
LI Dong1;  GONG Lanlan1;  LIU Shulin2;  SUN Xin2;  LEI Yong3
(1.School of Petroleum Engineering, Changzhou University, Changzhou 213164, China; 2.School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China; 3.Bohai Shipbuilding Heavy Industry Co., Ltd., Huludao 125004, China)
关键词:
故障诊断;  生物免疫机理;  连续学习;  机器学习
Keywords:
fault diagnosis;  biological immune mechanism;  continual learning;  machine learning
分类号:
TP 306
DOI:
10.3969/j.issn.2095-0411.2022.06.007
文献标志码:
A
摘要:
智能故障诊断方法是保障机械设备安全可靠运行的重要手段,然而,现有智能故障诊断方法缺乏连续学习能力,诊断时无法有效识别未参与训练的故障类型。在生物免疫系统智能机理的启发下,提出一种连续学习故障诊断方法。此方法使用k近邻策略优化诊断过程提升运行速度; 通过不断对诊断数据的学习,实时培养和更新记忆细胞; 利用新类型记忆细胞阈值识别未参与训练的故障类型,并培养新类型记忆细胞; 利用新记忆细胞阈值更新已知类型记忆细胞,用于提升故障诊断性能。在一定条件下,此方法退化为普通的监督学习故障诊断方法。利用20个标准数据集和凯斯西储大学轴承故障数据集对此方法进行了评估,实验结果表明此故障诊断方法具有良好的故障诊断性能。
Abstract:
Intelligent fault diagnosis methods play a significant role to ensure the safe and reliable operation of mechanical equipment. However, they cannot effectively classify the unseen samples in the testing stage, for they lack continual learning ability. A continual learning fault diagnosis method CLFDMD was proposed, inspired by the intelligent mechanisms of the biological immune system. It used k nearest neighbor rule to optimize the testing process for improving the running speed. It cultivated and updated memory cells by continual learning testing data during the testing stage. The new types of memory cells were cultivated after they recognized the unseen types of data with the help of their threshold. The memory cells of known types were updated by threshold of new memory cells to improve the fault diagnosis performance. It degenerates into a standard supervised learning fault diagnosis method at certain conditions. To assess the performance and possible advantages of CLFDMD, the experiments on twenty well-known datasets from the UCI repository and the ball bearing test dataset from Case Western Reserve University Bearing Data Center were performed. Results showed that it had better fault diagnosis performance.

参考文献/References:

[1] LEI Y G, YANG B, JIANG X W, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap[J]. Mechanical Systems and Signal Processing, 2020, 138: 106587.
[2] LIU R N, YANG B Y, ZIO E, et al. Artificial intelligence for fault diagnosis of rotating machinery: a review[J]. Mechanical Systems and Signal Processing, 2018, 108: 33-47.
[3] 雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
[4] 王国彪, 何正嘉, 陈雪峰, 等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报, 2013, 49(1): 63-72.
[5] LI X, YANG Y, HU N Q, et al. Discriminative manifold random vector functional link neural network for rolling bearing fault diagnosis[J]. Knowledge-Based Systems, 2021, 211: 106507.
[6] 李巍华, 翁胜龙, 张绍辉. 一种萤火虫神经网络及在轴承故障诊断中的应用[J]. 机械工程学报, 2015, 51(7): 99-106.
[7] WANG B, KE H W, MA X D, et al. Fault diagnosis method for engine control system based on probabilistic neural network and support vector machine[J]. Applied Sciences, 2019, 9(19): 4122.
[8] LI X, YANG Y, PAN H Y, et al. A novel deep stacking least squares support vector machine for rolling bearing fault diagnosis[J]. Computers in Industry, 2019, 110: 36-47.
[9] LEI Y G, ZUO M J. Gear crack level identification based on weighted K nearest neighbor classification algorithm[J]. Mechanical Systems and Signal Processing, 2009, 23(5): 1535-1547.
[10] XING S B, LEI Y G, WANG S H, et al. Distribution-invariant deep belief network for intelligent fault diagnosis of machines under new working conditions[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2617-2625.
[11] 王毅, 戴国洪, 王克胜. 深度学习技术在预测维修中的应用综述[J]. 常州大学学报(自然科学版), 2019, 31(3): 1-22.
[12] YANG B, LEI Y G, JIA F, et al. A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines[J]. IEEE Transactions on Industrial Electronics, 2020, 67(11): 9747-9757.
[13] YANG B, LEI Y G, JIA F, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings[J]. Mechanical Systems and Signal Processing, 2019, 122: 692-706.
[14] CHAI Z, ZHAO C H. Multiclass oblique random forests with dual-incremental learning capacity[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(12): 5192-5203.
[15] YU W K, ZHAO C H. Broad convolutional neural network based industrial process fault diagnosis with incremental learning capability[J]. IEEE Transactions on Industrial Electronics, 2020, 67(6): 5081-5091.
[16] LI D, LIU S L, GAO F R, et al. Continual learning classification method with constant-sized memory cells based on the artificial immune system[J]. Knowledge-Based Systems, 2021, 213: 106673.
[17] LI D, LIU S L, GAO F R, et al. Continual learning classification method with new labeled data based on the artificial immune system[J]. Applied Soft Computing, 2020, 94: 106423.
[18] 李栋, 刘树林, 孙欣. 针对不连续时变样本空间的连续学习故障诊断方法[J]. 机械工程学报, 2021, 57(1): 157-167.
[19] KOTSIANTIS S B, ZAHARAKIS I D, PINTELAS P E. Machine learning: a review of classification and combining techniques[J]. Artificial Intelligence Review, 2006, 26(3): 159-190.
[20] DONG L, LIU S L, ZHANG H L. A method of anomaly detection and fault diagnosis with online adaptive learning under small training samples[J]. Pattern Recognition, 2017, 64: 374-385.
(责任编辑:谭晓荷)

相似文献/References:

[1]袁兆辉,吴泽龙,颜惠庚.液压胀管机的压力测控及故障诊断[J].常州大学学报(自然科学版),2002,(03):30.
　YUAN Zhao -hui,WU Zhe -long,YAN Hui -gen.The Pressure Test and Control and Diagnosis of Faults of the Machine for Hydraulic Expanding of Tube to Tube[J].Journal of Changzhou University(Natural Science Edition),2002,(06):30.
[2]王洪元,史国栋,符彦惟,等.数据挖掘技术在故障诊断中的应用[J].常州大学学报(自然科学版),2001,(04):42.
　WANG Hong -yuan,SHI Gou -dong,FU Yan -wei,et al.Data Mining Technique and its Application in Fault Diagnosi s[J].Journal of Changzhou University(Natural Science Edition),2001,(06):42.

备注/Memo

备注/Memo:
收稿日期: 2022-01-26。
基金项目: 国家自然科学基金资助项目(52075310)。
作者简介: 李栋(1981—), 男, 山西长治人, 博士, 副教授。E-mail: lidong@cczu.edu.cn
更新日期/Last Update: 1900-01-01