基于改进受限玻尔兹曼机的滚动轴承健康因子构建方法

doi:10.12305/j.issn.1001-506X.2023.09.39

摘要/Abstract

摘要：

针对传统方法构建的健康因子各类性能指标不高、信息冗余的问题, 提出一种基于改进受限玻尔兹曼机(restricted Boltzmann machine, RBM)的滚动轴承健康因子构建方法。首先, 提取滚动轴承振动监测信号时域、频域特征组成物理健康因子集。其次, 将RBM隐藏层节点数随时间变化斜率引入到正则化项中, 提取物理健康因子集中的趋势性特征。最后, 利用滚动轴承全寿命周期试验验证所提方法的有效性。实验结果表明，相对于主成分分析(principal component analysis, PCA)法、传统RBM虚拟健康因子构建方法, 基于改进RBM构建的虚拟健康因子单调性分别提高178.0%和33.3%, 趋势性分别提高126.8%和16%, 鲁棒性分别提高60%和6.02%。

关键词: 滚动轴承, 健康因子, 受限玻尔兹曼机, 正则化, 评估准则

Abstract:

Aiming at the problems of low performance indicators and information redundancy of health factors constructed by traditional methods, a method for constructing health factors of rolling bearings based on the improved restricted Boltzmann machine (RBM) is proposed. Firstly, the time-domain and frequency-domain features of rolling bearing vibration monitoring signals are extracted to form a physical health factor set. Secondly, the slope of the number of nodes in the hidden layer of the RBM with time is introduced into the regularization term to extract the trend characteristics of the physical health factor set. Finally, the effectiveness of the proposed method is verified through full life cycle testing of rolling bearings. The experimental results show that compared with the principal component analysis (PCA) method and the traditional RBM virtual health factor construction method, the monotonicity of the virtual health factor based on the improved RBM is increased by 178.0% and 33.3% respectively, the trend is increased by 126.8% and 16% respectively, and the robustness is improved by 60% and 6.02% respectively.

Key words: rolling bearing, health indicator, restricted Boltzmann machine (RBM), regularization, evaluation criterion

中图分类号:

TN911.72

孙世岩, 张钢, 梁伟阁, 佘博, 田福庆. 基于改进受限玻尔兹曼机的滚动轴承健康因子构建方法[J]. 系统工程与电子技术, 2023, 45(9): 2979-2985.

Shiyan SUN, Gang ZHANG, Weige LIANG, Bo SHE, Fuqing TIAN. Construction method of rolling bearing health indicator based on enhanced restricted Boltzmann machine[J]. Systems Engineering and Electronics, 2023, 45(9): 2979-2985.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 30

1	MARCIA L B , ELSA M P H , KAI G . More effective prognostics with elbow point detection and deep learning[J]. Mechanical Systems and Signal Processing, 2021, 146, 106987. doi: 10.1016/j.ymssp.2020.106987
2	MENG M , ZHU M . Deep-convolution-based LSTM network for remining useful life prediction[J]. IEEE Trans.on Industrial Informatics, 2021, 17 (3): 1658- 1667. doi: 10.1109/TII.2020.2991796
3	SHE D M , JIA M P . A BiGRU method for remaining useful life prediction of machinery[J]. Measurement, 2021, 167, 108277. doi: 10.1016/j.measurement.2020.108277
4	陆宁云, 陈闯, 姜斌, 等. 复杂系统维护策略最新研究进展: 从视情维护到预测性维护[J]. 自动化学报, 2021, 47 (1): 1- 17.
	LU N Y , CHEN C , JIANG B , et al. Latest progress on maintenance strategy of complex system: from condition-based maintenance to predictive maintenance[J]. Acta Automatica Sinca, 2021, 47 (1): 1- 17.
5	LIU Q M , DONG M , LYU W Y , et al. Manufacturing system maintenance based on dynamic programming model with prognostics information[J]. Journal of Intelligent Manufacturing, 2019, 30 (3): 1155- 1173. doi: 10.1007/s10845-017-1314-6
6	ZHU J , CHEN N , SHEN C Q . A new data-driven transferable remaining useful life prediction approach for bearing under diffe-rent working conditions[J]. Mechanical Systems and Signal Processing, 2020, 139, 106602. doi: 10.1016/j.ymssp.2019.106602
7	WANG B , LEI Y G , LI N P , et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Trans.on Reliability, 2020, 69 (1): 401- 412. doi: 10.1109/TR.2018.2882682
8	TIAN Q P , WANG H L . An ensemble learning and RUL prediction method based on bearings degradation indicator construction[J]. Applied Sciences, 2020, 10 (1): 346- 368. doi: 10.3390/app10010346
9	LOUKOPOULOS P , ZOLKIEWSKI G , BENNETT I , et al. Abrupt fault remaining useful life estimation using measurements from a reciprocating compressor valve failure[J]. Mechanical Systems and Signal Processing, 2019, 121 (2): 359- 372.
10	PARIS P C , ERDOGAN F . A critical analysis of crack propagation laws[J]. Journal of Fluids Engineering, 1963, 85, 528- 533.
11	WANG J J , GAO R X , YUAN Z , et al. A joint particle filter and expectation maximization approach to machine condition prognosis[J]. Journal of Intelligent Manufacturing, 2019, 30 (2): 605- 621. doi: 10.1007/s10845-016-1268-0
12	LEI Y G , LI N , GONTARZ S , et al. A model-based method for remaining useful life prediction of machinery[J]. IEEE Trans.on Reliability, 2016, 65 (3): 1314- 1326. doi: 10.1109/TR.2016.2570568
13	LIAO L X . Discovering prognostic features using genetic programming in remaining useful life prediction[J]. IEEE Trans.on Industrial Electronics, 2014, 61 (5): 2464- 2472. doi: 10.1109/TIE.2013.2270212
14	CHAN K S , ENRIGHT M P , MOODY J P , et al. Life prediction for turbopropulsion systems under dwell fatigue conditions[J]. Journal of Engineering for Gas Turbines and Power, 2012, 134 (12) doi: 10.1115/GT2012-69742
15	BARALDI P , MANGILI F , ZIO E . Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data[J]. Reliability Engineering and System Safety, 2013, 112, 94- 108. doi: 10.1016/j.ress.2012.12.004
16	BARALDI P , MANGILI F , ZIO E . A Kalman filter-based ensemble approach with application to turbine creep prognostics[J]. IEEE Trans.on Reliability, 2012, 61 (3): 966- 977.
17	彭志凌, 张毅, 丁明军, 等. 某供弹系统高速传动机构磨损机理分析与预测模型[J]. 中北大学学报(自然科学版), 2018, 39 (2): 155- 158. doi: 10.3969/j.issn.1673-3193.2018.02.008
	PENG Z L , ZHANG Y , DING M J , et al. Analysis and prediction model of wear mechanism for high speed transmission mechanism of a missile system[J]. Journal of North University of China(Natural Science Edition), 2018, 39 (2): 155- 158. doi: 10.3969/j.issn.1673-3193.2018.02.008
18	KATRIN S , PHILIPPE C C , REINALD B . Automatic selection of a representative trial from multiple measurements using Principle Component Analysis[J]. Journal of Biomechanics, 2012, 45 (3): 2306- 2309.
19	LI X Q , JIANG H K , XIONG X , et al. Rolling bearing health prognosis using a modified health index based hierarchical gated recurrent unit network[J]. Mechanism and Machine Theory, 2019, 133 (2): 229- 249.
20	孟文俊, 张四聪, 淡紫嫣, 等. 滚动轴承寿命动态预测新方法[J]. 振动、测试与诊断, 2019, 39 (3): 652- 658.
	MENG W J , ZHANG S C , DAN Z Y , et al. Method of dynamic life prediction of rolling bearing[J]. Journal of Vibration, Measurement & Diagnosis, 2019, 39 (3): 652- 658.
21	杨柯, 范世东. 基于长短期记忆网络时序数据趋势预测及应用[J]. 推进技术, 2021, (3): 675- 682.
	YANG K , FAN S D . Long short-term memory network based method and its application in time-series data trend prediction[J]. Journal Propulsion Technology, 2021, (3): 675- 682.
22	SINGH J , DARPE A K , SINGH H P , et al. Bearing damage assessment using Jensen-Renyi divergence based on EEMD[J]. Mechanical Systems and Signal Processing, 2017, 87 (2): 307- 339.
23	QIAN Y N , YAN R Q , GAO R X , et al. A multi-time scale approach to remaining useful life prediction in rolling bearing[J]. Mechanical Systems and Signal Processing, 2017, 83 (1): 549- 567.
24	SHAO H D , JIANG H K , LI X Q , et al. Rolling bearing fault detection using continuous deep belief network with locally linear embedding[J]. Computers in Industry, 2018, 96 (3): 27- 39.
25	ZHANG N , DING S F , ZHANG J , et al. An overview on restric-ted Boltzmann machines[J]. Neurocomputing, 2018, 275 (1): 1186- 1199.
26	LI C , SANCHEZ R V , ZURITA G , et al. Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis[J]. Neurocomputing, 2015, 168 (2): 119- 127.
27	LI C , SANCHEZ R V , ZURITA G , et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals[J]. Mechanical Systems and Signal Processing, 2016, 76 (2): 283- 293.
28	ZHANG L , GAO H L , WEN J , et al. A deep learning-based recognition method for degradation monitoring of ball screw with multi-sensor data fusion[J]. Microelectronics Reliability, 2017, 75, 215- 222.
29	NECTOX P, GOURIVEAU R, MEDJAHER K, et al. PRONOSTIA: an experimental platform for bearings accelerated degradation tests[C]//Proc. of the IEEE International Confe-rence on Prognostics and Health Management, 2012.
30	张钢, 田福庆, 佘博, 等. 一种基于特定频段信息熵和RBM的健康因子构建方法[J]. 振动与冲击, 2020, 39 (6): 147- 153.
	ZHANG G , TIAN F Q , SHE B , et al. Health indicator construction method based on the information entropy of a specific frequency band and the RBM[J]. Journal of Vibration and Shock, 2020, 39 (6): 147- 153.

[1]	刘鸣谦, 徐仲秋, 陈天成, 张冰尘, 吴一戎. 基于L₁ & TV正则化的低过采样Staggered SAR成像方法[J]. 系统工程与电子技术, 2023, 45(9): 2718-2726.
[2]	仇祝令, 查宇飞, 李振宇, 李禹铭, 张鹏, 朱川. 基于多模型蒸馏的时间正则化相关滤波跟踪算法[J]. 系统工程与电子技术, 2022, 44(8): 2448-2456.
[3]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[4]	王帅, 向建军, 彭芳, 唐书娟. 基于新最速下降法的目标跟踪算法[J]. 系统工程与电子技术, 2022, 44(5): 1512-1519.
[5]	刘歌, 芮国胜, 田文飚. 基于双重正则矩阵分解的缺失数据恢复[J]. 系统工程与电子技术, 2021, 43(5): 1191-1197.
[6]	赵迎新, 王长峰, 吴虹, 张铭, 黄英杰, 王乐耕, 刘之洋. 基于负熵最大化的压缩感知信道估计算法[J]. 系统工程与电子技术, 2021, 43(4): 1126-1132.
[7]	刘星, 熊厚情, 赵建印, 朱敏. 基于改进稀疏KELM的在线非平稳动态系统状态预测方法[J]. 系统工程与电子技术, 2020, 42(9): 2022-2032.
[8]	季策, 张晓梦. 基于MS-ROMP信号重构算法的欠定盲分离[J]. 系统工程与电子技术, 2020, 42(4): 756-763.
[9]	孙世岩, 张钢, 田福庆, 梁伟阁. 多输入混合深度学习网络的健康因子构建方法[J]. 系统工程与电子技术, 2020, 42(10): 2390-2398.
[10]	张钢, 田福庆, 梁伟阁, 佘博. 基于多尺度AlexNet网络的健康因子构建方法[J]. 系统工程与电子技术, 2020, 42(1): 245-252.
[11]	徐志林, 魏中浩, 吴辰阳, 张冰尘. 基于l1正则化的多通道滑动聚束SAR成像[J]. 系统工程与电子技术, 2019, 41(2): 304-310.
[12]	叶霞, 杨书杰. 改进混合正则化约束多帧湍流退化图像盲复原方法[J]. 系统工程与电子技术, 2018, 40(9): 2138-2142.
[13]	毕笃彦, 王世平, 刘坤, 何林远. 基于并行映射卷积网络的超分辨率重建算法[J]. 系统工程与电子技术, 2018, 40(8): 1873-1880.
[14]	纪元法, 朱亮亮, 孙希延, 严素清. 差分进化算法结合正则化解算病态方程[J]. 系统工程与电子技术, 2018, 40(7): 1573-1577.
[15]	徐志刚, 李文文, 袁飞祥, 朱红蕾, 许亚美. 基于稀疏表示和多成分字典学习的超分辨率重建[J]. 系统工程与电子技术, 2018, 40(3): 699-703.