基于模糊信息粒化与小波支持向量机的滚动轴承性能退化趋势预测

摘要/Abstract

摘要： 针对滚动轴承的性能退化指标及其波动范围难以有效预测的问题，提出了一种基于模糊信息粒化与小波支持向量机的滚动轴承性能退化趋势预测方法。首先以一定的时间间隔采集滚动轴承运行过程中的振动信号序列，提取各个振动信号序列的特征指标，对特征指标序列进行模糊信息粒化，进而提取各个粒化窗口的有效分量信息；随后通过构建小波支持向量机对各个指标分量分别建立预测模型，实现对滚动轴承性能退化指标的退化趋势及波动范围的预测。实验结果表明，该预测方法可以有效跟踪滚动轴承性能衰退指标的变化趋势，并对其指标的波动范围进行有效预测。

关键词: 模糊信息粒化, 小波支持向量机, 滚动轴承, 退化趋势预测

Abstract: Aiming at the problems where the performance degradation index and its fluctuation ranges of the roller bearings were difficult to forecast effectively, a method was proposed herein based on fuzzy information granulation and WSVM for roller bearing performance degradation trend prediction. Firstly, the vibration signal sequences of rolling bearings in the operation process were acquired at a certain time interval, then, those feature indexes were extracted from those vibration signals. In order to acquire the effective component information, the process of the fuzzy information granulation for those feature indexes might be performed. Subsequently, a prediction model was established for each feature index by constructing the WSVM, and the degradation trend and the fluctuation ranges of the performance feature indexes of the rolling bearings were predicted. The experimental results show that the proposed method can track the change tendency of the rolling bearing performance effectively, and the degradation trend and the fluctuation ranges of the performance feature indexes may be predicted effectively.

Key words: fuzzy information granulation, wavelet support vector machine（WSVM）, rolling bearing, degradation trend prediction

中图分类号:

TH132

陈法法, 杨勇, 陈保家, 陈从平. 基于模糊信息粒化与小波支持向量机的滚动轴承性能退化趋势预测[J]. 中国机械工程.

Chen Fafa, Yang Yong, Chen Baojia, Chen Congping. Degradation Trend Prediction of Rolling Bearings Based on Fuzzy Information Granulation and Wavelet Support Vector Machine[J]. China Mechanical Engineering.

参考文献

[1]Chen Hua, Zhang Qing, Xu Guanghua,et al. Performance Reliability Estimation Method Based on Adaptive Failure Threshold[J]. Mechanical Systems and Signal Processing, 2013, 36(2): 505-519.

[2]杨帆，汤宝平，尹爱军. 小波包能谱构建综合评估函数的轴承退化评估[J]. 中国机械工程,2015，26(17): 2355-2368.

Yang Fan, Tang Baoping, Yin Aijun.Early Performance Degradation Assessment of Rolling Bearing Based on Comprehensive Evaluation Function Constructing Wavelet Packet Energy Spectrum[J]. China Mechanical Engineering, 2015，26(17): 2355-2368.

[3]Tan Xiaohui, Bi Weihua, Hou Xiaoliang, et al. Reliability Analysis Using Radial Basis Function Networks and Support Vector Machines[J]. Computers and Geotechnics, 2011, 38(2):178-186.

[4]王冰, 李洪儒, 许葆华. 基于多尺度形态分解谱嫡的电机轴承预测特征提取及退化状态评估[J]. 振动与冲击, 2013, 32(22):124-128.

Wang Bing, Li Hongru, Xu Baohua. Motor Bearing Forecast Feature Extracting and Degradation Status Identification Based on Multi-scale Morphological Decomposition Spectral Entropy[J]. Journal of Vibration and Shock, 2013, 32(22):124-128.

[5]申中杰, 陈雪峰, 何正嘉, 等. 基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测[J]. 机械工程学报, 2013,49(2) :183-189.

Shen Zhongjie, Chen Xuefeng, He Zhengjia, et al. Remaining Life Predictions of Rolling Bearing Based on Relative Features and Multivariable Support Vector Machine[J]. Journal of Mechanical Engineering, 2013,49(2) :183-189.

[6]霍军周,王亚杰,欧阳湘宇,等.基于BP神经网络的TBM主轴承载荷谱预测[J].哈尔滨工程大学学报,2015,36(7):1-6.

Huo Junzhou, Wang Yajie, Ouyang Xiangyu, et al. Load Spectrum Prediction Based on BP Neural Network of Main Drive Bearing of Tunnel Boring Machine[J]. Journal of Harbin Engineering University, 2015, 36(7):1-6.

[7]徐东, 徐永成, 陈循, 等. 基于EMD的灰色模型的疲劳剩余寿命预测方法研究[J]. 振动工程学报, 2011,24(1) :104-110.

Xu Dong, Xu Yongcheng, Chen Xun, et al. Residual Fatigue Life Prediction Based on Grey Model and EMD[J]. Journal of Vibration Engineering, 2011, 24(1):104-110.

[8]Chen Fafa, Tang Baoping, Chen Runxiang. A Novel Fault Diagnosis Model for Gearbox Based on Wavelet Support Vector Machine with Immune Genetic Algorithm[J]. Measurement, 2013, 46: 220-232.

[9]Duygu C, Esin D. An Automatic Diabetes Diagnosis System Based on LDA-wavelet Support Vector Machine Classifier [J]. Expert Systems with Applications, 2011, 38(7): 8311-8315.

[10]Li Cong, Duan Haibin. Information Granulation-based Fuzzy RBFNN for Image Fusion Based on Chaotic Brain Storm Optimization[J]. Optik, 2015, 126:1400-1406.

[11]Lin Yaojin, Li Jinjin, Lin Peirong, et al. Feature Selection Via Neighborhood Multi-granulation Fusion[J]. Knowledge-based Systems, 2014, 67(5):162-168.

[12]Wang Weina, Witold P, Liu Xiaodong. Time Series Long-term Forecasting Model Based on Information Granules and Fuzzy Clustering[J]. Engineering Applications of Artificial Intelligence, 2015, 41(5):17-24.

[13]Wu Qi. The Forecasting Model Based on Wavelet V-support Vector Machine[J]. Expert Systems with Applications, 2009, 36(4):604-7610.

[14]Chen Fafa, Tang Baoping, Song Tao. Multi-fault Diagnosis Study on Roller Bearing Based on Multi-kernel Support Vector Machine with Chaotic Particle Swarm Optimization[J]. Measurement, 2014, 47(1): 576-590.

[15]Zhu Keheng, Song Xigeng, Xue Dongxin. A Roller Bearing Fault Diagnosis Method Based on Hierarchical Entropy and Support Vector Machine with Particle Swarm Optimization Algorithm [J]. Measurement, 2014, 47(1): 669-675.