一种改进基尼指数加权的轴承健康指标构建方法

doi:10.3969/j.issn.1004-132X.2023.15.006

中国机械工程 ›› 2023, Vol. 34 ›› Issue (15): 1813-1819，1855.DOI: 10.3969/j.issn.1004-132X.2023.15.006

一种改进基尼指数加权的轴承健康指标构建方法

钱门贵1;陈涛1;于耀翔1;郭亮1;高宏力1;李威霖2,3

1.西南交通大学机械工程学院，成都，610031
2.浙江方圆检测集团股份有限公司，杭州，310018
3.浙江省市场监管新能源汽车驱动系统重点实验室，杭州，310014

出版日期:2023-08-10 发布日期:2023-08-14
通讯作者: 郭亮（通信作者），男，1988年生，副教授。研究方向为轨道交通设备智能维护与健康管理、健康指标构建、智能故障诊断与预测、边云协作系统、智能维护机器人等。发表论文50余篇，获专利20余项。E-mail:guolaing@.swjtu.edu.com。
作者简介:钱门贵，男，1998年生，硕士研究生。研究方向为机械信号分析与处理、机械健康监测与智能维护。
基金资助:
国家自然科学基金(51905452,51775452)；中央引导地方科技发展资金(2020ZYD012)；浙江省市场监督管理局雏鹰计划培育项目(CY2022111)；四川省科技项目(2021YFG0068)

A Method for Constructing Bearing HIs with IGI Weighting

QIAN Mengui1;CHEN Tao1;YU Yaoxiang1;GUO Liang1;GAO Hongli1;LI Weilin2,3

1.School of Mechanical Engineering,Southwest Jiaotong University,Chengdu,610031
2.Zhejiang Fangyuan Test Group Co.,Ltd.,Hangzhou,310018
3.Key Laboratory of New Energy Automotive Drive Systems for Zhejiang Market Regulation,
Hangzhou,310014

Online:2023-08-10 Published:2023-08-14

摘要/Abstract

摘要： 在轴承的状态监测中，构建一个可以准确描述轴承退化趋势且能及时识别早期退化点(EDP) 的健康指标(HI) 至关重要。目前大多学者提出的健康指标能较好地描述轴承的退化趋势，但不能准确识别早期退化点。提出了一种改进基尼指数(IGI) 加权的轴承健康指标构建方法。利用集成经验模态分解(EEMD) 对原始信号进行分解，根据各分量的故障特征能量比(FCER)，对其进行加权重构得到重构信号；计算重构信号的IGI；将IGI作为重构信号的FCER进行加权计算，得到最终的指标IGI-FCER-HI。通过两个实验验证了所提方法的有效性，并与其他健康指标进行了对比。结果表明，所提方法构建的指标不仅具有良好的单调性和趋势性，而且能准确监测轴承的早期退化点。

关键词: 滚动轴承, 早期退化点, 健康指标, 集成经验模态分解, 加权重构的集成经验模态分解, 故障特征能量比, 改进的基尼指数

Abstract: In the bearings condition monitoring, it was important to construct a HI that might accurately describe bearings degradation trends and identify EDP. At present, most of HIs proposed might describe the degradation trends of bearings well, but could not accurately identify the EDP. A method for constructing bearing HIs was proposed with IGI weighting. The original signals were decomposed by using EEMD, and the reconstructed signals were weighted according to the FCER of each components. The IGI of the reconstructed signals was calculated.The IGI was weighted as the FCER of the reconstructed signals to obtain the final IGI-FCER-HI. The effectiveness of the method was verified by two experiments. The results show that the IGI-FCER-HI has well monotonicity and trend, may identify EDPs of bearings accurately.

Key words: rolling bearing, early degradation point(EDP), health indicator(HI), ensemble empirical mode decomposition(EEMD), weighted reconstructed EEMD, failure characteristic energy ratio(FCER), improved Gini index(IGI)

中图分类号:

TH133

钱门贵, 陈涛, 于耀翔, 郭亮, 高宏力, 李威霖, . 一种改进基尼指数加权的轴承健康指标构建方法[J]. 中国机械工程, 2023, 34(15): 1813-1819，1855.

QIAN Mengui, CHEN Tao, YU Yaoxiang, GUO Liang, GAO Hongli, LI Weilin, . A Method for Constructing Bearing HIs with IGI Weighting[J]. China Mechanical Engineering, 2023, 34(15): 1813-1819，1855.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2023.15.006

http://www.cmemo.org.cn/CN/Y2023/V34/I15/1813

参考文献

［1］QIU H, LEE J, LIN J, et al. Wavelet Filter-based Weak Signature Detection Method and Its Application on Rolling Element Bearing Prognostics［J］. Journal of Sound and Vibration, 2006, 289(4/5):1066-1090.
［2］WANG D, TSUI K L, MIAO Q. Prognostics and Health Management:a Review of Vibration Based Bearing and Gear Health Indicators［J］. IEEE Access, 2017, 6:665-676.
［3］GUO L, LI N, JIA F, et al. A Recurrent Neural Network Based Health Indicator for Remaining Useful Life Prediction of Bearings［J］. Neurocomputing, 2017, 240:98-109.
［4］LEI Y, LI N, GUO L, et al. Machinery Health Prognostics:a Systematic Review from Data Acquisition to RUL Prediction［J］. Mechanical Systems and Signal Processing, 2018, 104:799-834.
［5］张淑清,李威,张立国,等.基于多元经验模态分解互近似熵及GG聚类的轴承故障诊断［J］. 中国机械工程, 2016, 27(24):3362-3367.
ZHANG Shuqing, LI Wei, ZHANG Liguo,et al. Bearing Fault Diagnosis Based on Multi-EMD, cApEn and GG Clustering Algorithm［J］. China Mechanical Engineering, 2016, 27(24):3362-3367.
［6］ZHAO M, LIN J. Health Assessment of Rotating Machinery Using a Rotary Encoder［J］. IEEE Transactions on Industrial Electronics, 2017, 65(3):2548-2556.
［7］GUO L, LEI Y, LI N, et al. Machinery Health Indicator Construction Based on Convolutional Neural Networks Considering Trend Burr［J］. Neurocomputing, 2018, 292:142-150.
［8］GUO L, LEI Y, LI N, et al. Machinery Health Indicator Construction Based on Convolutional Neural Networks Considering Trend Burr［J］. Neurocomputing, 2018, 292:142-150.
［9］何强, 唐向红, 李传江，等. 负载不平衡下小样本数据的轴承故障诊断［J］.中国机械工程, 2021, 32(10):1164-1171.
HE Qiang, TANG Xianghong, LI Chuanjiang， et al. Bearing Fault Diagnosis Method Based on Small Sample Data under Unbalanced Loads［J］. China Mechanical Engineering, 2021, 32(10):1164-1171.
［10］LI N, LEI Y, LIN J, et al. An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings［J］. IEEE Transactions on Industrial Electronics, 2015, 62(12):7762-7773.
［11］HUANG Z, XU Z, KE X, et al. Remaining Useful Life Prediction for an Adaptive Skew-Wiener Process Model［J］. Mechanical Systems and Signal Processing, 2017, 87:294-306.
［12］CUI H, QIAO Y, YIN Y, et al. An Investigation of Rolling Bearing Early Diagnosis Based on High-frequency Characteristics and Self-adaptive Wavelet De-noising［J］. Neurocomputing, 2016, 216:649-656.
［13］REN L, CUI J, SUN Y, et al. Multi-bearing Remaining Useful Life Collaborative Prediction:a Deep Learning Approach［J］. Journal of Manufacturing Systems, 2017, 43:248-256.
［14］顾晓辉，杨绍普，刘永强，等. 一种改进的峭度图方法及其在复杂干扰下轴承故障诊断中的应用［J］. 振动与冲击, 2017, 36(23):187-193.
GU Xiaohui, YANG Shaopu, LIU Yongqiang， et al. An Improved Kurtogram Method and Its Application in Fault Diagnosis of Rolling Element Bearings under Complex Interferences［J］. Journal of Vibration and Shock, 2017, 36(23):187-193.
［15］ZHAO M, JIA X. A Novel Strategy for Signal Denoising Using Reweighted SVD and Its Applications to Weak Fault Feature Enhancement of Rotating Machinery［J］. Mechanical Systems and Signal Processing, 2017, 94:129-147.
［16］YAN T, WANG D, XIA T, et al. A Generic Framework for Degradation Modeling Based on Fusion of Spectrum Amplitudes［J］. IEEE Transactions on Automation Science and Engineering, 2022,19(1):308-319.
［17］DUONG B P, KHAN S A, SHON D, et al. A Reliable Health Indicator for Fault Prognosis of Bearings［J］. Sensors, 2018, 18(11):3740.
［18］刘兴教，赵学智，李伟光，等. 基于峭度原则的EEMD-MCKD的柔性薄壁轴承故障特征提取［J］. 振动与冲击, 2021, 40(1):157-164.
LIU Xingjiao, ZHAO Xuezhi, LI Weiguang, et al. EEMD-MCKD Fault Feature Extraction Method for Flexible Thin-wall Bearing Based on Kurtosis Principle［J］. Journal of Vibration and Shock, 2021, 40(1):157-164.
［19］NOMAN K, HE Q, PENG Z, et al. A Scale Independent Flexible Bearing Health Monitoring Index Based on Time Frequency Manifold Energy & Entropy［J］. Measurement Science and Technology, 2020, 31(11):114003.
［20］LIM C, KIM S, SEO Y H, et al. Feature Extraction for Bearing Prognostics Using Weighted Correlation of Fault Frequencies over Cycles［J］. Structural Health Monitoring, 2020, 19(6):1808-1820.
［21］MIAO Y, ZHAO M, LIN J. Improvement of Kurtosis-guided-grams via Gini Index for Bearing Fault Feature Identification［J］. Measurement Science and Technology, 2017, 28(12):125001.
［22］HOU B, WANG D, WANG Y, et al. Adaptive Weighted Signal Preprocessing Technique for Machine Health Monitoring［J］. IEEE Transactions on Instrumentation and Measurement, 2020, 70:1-11.
［23］HOU B, WANG D, YAN T, et al. A Comparison of Machine Health Indicators Based on the Impulsiveness of Vibration Signals［J］. Acoustics Australia, 2021, 49(2):199-206.
［24］LEI Y, HE Z, ZI Y. Application of the EEMD Method to Rotor Fault Diagnosis of Rotating Machinery［J］. Mechanical Systems and Signal Processing, 2009, 23(4):1327-1338.
［25］WANG B, LEI Y, LI N, et al. A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings［J］. IEEE Transactions on Reliability, 2018, 69(1):401-412.

[1]	胡超, 刘佐民. 基于材料匹配性的球轴承Heathcote黏-滑模型研究 [J]. J4, 201016, 21(16): 1969-1973.
[2]	秦国浩, 张楷, 丁昆, 黄锋飞, 郑庆, 丁国富, . 动态宽卷积残差网络的轴承故障诊断方法[J]. 中国机械工程, 2023, 34(18): 2212-2221.
[3]	董绍江, 周存芳, 陈里里, 徐向阳. 基于判别性特征提取和双重域对齐的轴承跨域故障诊断[J]. 中国机械工程, 2023, 34(15): 1856-1863.
[4]	郑近德, 陈焱, 童靳于, 潘海洋. 精细广义复合多元多尺度反向散布熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2023, 34(11): 1315-1325.
[5]	张龙, 张号, 王朝兵, 王晓博, 文培田, 赵丽娟. 显式动力学驱动的轴承变工况故障诊断方法[J]. 中国机械工程, 2023, 34(08): 982-992.
[6]	董绍江, 朱朋, 朱孙科, 刘兰徽, 邢镔, 胡小林. 基于仿真数据驱动和领域自适应的滚动轴承故障诊断方法[J]. 中国机械工程, 2023, 34(06): 694-702.
[7]	李可, 燕晗, 顾杰斐, 宿磊, 苏文胜, 薛志钢. 基于shapelets时间序列的多源迁移学习滚动轴承故障诊断方法[J]. 中国机械工程, 2022, 33(24): 2990-2996,3006.
[8]	王东峰, 袁巨龙, 王燕霜, 程勇杰, 吕冰海. 轴承沟道表面完整性研究进展[J]. 中国机械工程, 2022, 33(18): 2143-2160.
[9]	杨光友, 刘浪, 习晨博. 自适应辅助分类器生成式对抗网络样本生成模型及轴承故障诊断[J]. 中国机械工程, 2022, 33(13): 1613-1621.
[10]	赵志宏, 李乐豪, 杨绍普, 李晴. 一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程, 2022, 33(10): 1234-1243.
[11]	郭家昕, 程军圣, 杨宇, . 改进多线性主成分分析网络及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2022, 33(02): 187-193,201.
[12]	童靳于, 罗金, 郑近德. 基于增强深度自编码网络的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(21): 2617-2624.
[13]	郭俊超, 甄冬, 孟召宗, 师占群, 谷丰收. 基于WAEEMD和MSB的滚动轴承故障特征提取[J]. 中国机械工程, 2021, 32(15): 1793-1800.
[14]	郑近德, 王兴龙, 潘海洋, 童靳于, 刘庆运. 基于自适应自相关谱峭度图的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(07): 778-785，792.
[15]	丁嘉鑫;王振亚;姚立纲;蔡永武. 广义复合多尺度加权排列熵与参数优化支持向量机的滚动轴承故障诊断[J]. 中国机械工程, 2021, 32(02): 147-155.

一种改进基尼指数加权的轴承健康指标构建方法

A Method for Constructing Bearing HIs with IGI Weighting

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics