基于自组织神经网络的滚动轴承状态评估方法

摘要/Abstract

摘要： 针对单一特征在进行故障诊断时准确率不高的问题，提出了一种基于自组织神经网络（SOM）的滚动轴承状态评估方法。该方法首先从原始振动信号中提取出多特征数据，运用主成分分析（PCA）方法对多特征数据进行预处理，采用SOM进行网络训练，构建多特征数据的融合模型，输出竞争神经元层的权值矢量；然后，计算每一个样本到竞争神经元层权值矢量的最小欧氏距离，输出最终的融合指标；最后，通过比较待检测样本与正常样本的最小欧氏距离的差异来判断轴承的状态。将该方法应用于滚动轴承状态评估，试验结果表明：融合指标比单一指标对早期故障更加敏感、更加稳健；同时，融合指标能够定量地描述轴承状态的劣化过程。

关键词: 自组织神经网络, 主成分分析, 特征融合, 最小匹配距离, 滚动轴承, 故障识别

Abstract: Aiming at the problems that single feature fault diagnosis accuracy was not too high, a rolling bearing condition assessment method was proposed based on SOM herein. Firstly, the multi-dimensional features were extracted from the original vibration signals and preprocessed by PCA, a fusion model was established by training SOM network and weight vectors of competitive neuron were obtained. Secondly, the fusion index, which was the minimum Euclidean distance between every sample values to the competitive neuron weighting vector, was achieved. Finally, the conditions of rolling bearings were classified by comparing the minimum Euclidean distances among the detected samples and the normal samples. The proposed method herein was applied to condition assessment of the rolling bearings, and the test results show that the fusion index is more sensitive and robust than that of original single feature during the stages of early faults; meanwhile, the fusion index may reflect the states of rolling bearings more accurately.

Key words: self-organization mapping(SOM), principal component analysis(PCA), feature fusion, minimum matching distance, rolling bearing, fault identification

中图分类号:

V263.6

张全德, 陈果, 林桐, 欧阳文理, 滕春禹, 王洪伟. 基于自组织神经网络的滚动轴承状态评估方法[J]. 中国机械工程.

ZHANG Quande, CHEN Guo, LIN Tong, OUYANG Wenli, TENG Chunyu, WANG Hongwei. Condition Assessment for Rolling Bearings Based on SOM[J]. China Mechanical Engineering.

参考文献

[1]陈果, 李爱. 航空器检测与诊断技术导论[M]. 北京: 航空工业出版社, 2012：1-6.
CHEN Guo, LI Ai. Introduction to Aircraft Detection and Diagnosis Technology[M]. Beijing: Aviation Industry Press, 2012：1-6.
[2]罗慧, 王友仁, 崔江,等. 电力电子电路多源特征层融合故障诊断方法[J]. 电机与控制学报, 2010, 14(4):92-96.
LUO Hui, WANG Youren, CUI Jiang， et al. Intelligent Fault Diagnosis for Power Electronic Circuits Based on Multi-source Feature-level Fusion[J]. Electric Machines and Control,2010,14(4):92-96.
[3]古莹奎, 杨子茜, 朱繁泷. 基于主成分分析的齿轮箱故障特征融合分析[J]. 中国机械工程, 2015, 26(11):1532-1537.
GU Yingkui, YANG Ziqian, ZHU Fanlong. Gearbox Fault Feature Fusion Based on Principal Component Analysis[J]. China Mechanical Engineering, 2015, 26(11):1532-1537.
[4]李凌均, 张周锁, 何正嘉. 基于支持向量数据描述的机械故障诊断研究[J]. 西安交通大学学报, 2003, 37(9):910-913.
LI Lingjun, ZHANG Zhousuo, HE Zhengjia.Research of Mechanical System Fault Diagnosis Based on Support Vector Data Description[J]. Journal of Xi'an Jiaotong University, 2003, 37(9):910-913.
[5]蒋全胜, 贾民平, 胡建中,等. 基于拉普拉斯特征映射的故障模式识别方法[J]. 系统仿真学报, 2008,20(20):5710-5713.
JIANG Quansheng, JIA Mingping, HU Jianzhong, et al. Method of Fault Pattern Recognition Based on Laplacian Eigenmaps[J]. Journal of System Simulation, 2008,20(20):5710-5713.
[6]张伟, 周维佳, 刘晓源. 基于扩展LLE方法的非线性系统故障诊断研究[J]. 电子学报, 2015, 43(9):1810-1815.
ZHANG Wei, ZHOU Weijia, LIU Xiaoyuan.An Improved LLE-based Approach to Fault Diagnosis of Nonlinear System[J]. Acta Electronica Sinica, 2015, 43(9):1810-1815.
[7]刘志川, 唐力伟, 曹立军,等. 基于Isomap和IGA-SVM的齿轮箱故障诊断研究[J]. 机械强度,2016，38(1):38-43.
LIU Zhichuan,TANG Liwei, CAO Lijun. Research on Gearbox Fault Diagnosis Based on ISOMAP and IGA-SVM[J]. Journal of Mechanical Strength, 2016，38(1):38-43.
[8]袁宪锋, 宋沐民, 周风余,等. 多PCA模型及SVM-DS融合决策的服务机器人故障诊断[J]. 振动、测试与诊断, 2015(3):434-440.
YUAN Xianfeng, SONG Mumin, ZHOU Fengyu. Experimental and Analytical Study of Dynamic Response of Structure Controlled by Active-passive Hybrid Tune Mass Damper[J]. Journal of Vibration Measurement & Diagnosis, 2015(3):434-440.
[9]ZHANG Q, HUA C, XU G. A Mixture Weibull Proportional Hazard Model for Mechanical System Failure Prediction Utilising Lifetime and Monitoring Data[J]. Mechanical Systems & Signal Processing, 2014, 43(1/2):103-112.
[10]YU J. Bearing Performance Degradation Assessment Using Locality Preserving Projections and Gaussian Mixture Models[J]. Mechanical Systems and Signal Processing, 2011, 25(7): 2573-2588.
[11]PAN Y, CHEN J, LI X. Bearing Performance Degradation Assessment Based on Lifting Wavelet Packet Decomposition and Fuzzy C-means[J]. Mechanical Systems and Signal Processing, 2010, 24(2): 559-566.
[12]汪瑾, 陈果, 王洪伟,等. 基于后验概率 SVM的航空发动机滚动轴承状态评估[J]. 轴承, 2015(5):55-59.
WANG Jin, CHEN Guo, WANG Hongwei, et al. Condition Assessment for Aero-engine Rolling Bearing Based on Posterior Probability SVM[J]. Bearing, 2015(5):55-59.
[13]CHAUDHARY V, BHATIA R S, AHLAWAT A K. A Novel Self-organizing Map (SOM) Learning Algorithm with Nearest and Farthest Neurons[J]. Alexandria Engineering Journal, 2014, 53(4):827-831.
[14]KURDTHONGMEE W. A Low Latency Minimum Distance Searching Unit of the SOM Based Hardware Quantizer [J]. Microprocessors & Microsystems, 2015, 39(2): 135-143.

[15]高隽. 人工神经网络原理及仿真实例[M]. 北京: 机械工业出版社, 2007:168-173.
GAO Juan. Artificial Neural Network Principle and Simulation[M]. Beijing: Mechanical Industry Press, 2007:168-173.
[16]杨淑莹. 模式识别与智能计算[M]. 北京: 电子工业出版社, 2011:170-176.
YANG Shuying. Pattern Recognition and Intelligent Computing[M]. Beijing: Publishing House of Electronics Industry, 2011:170-176.
[17]CHEN G, HAO T F, WANG H F, et al. Sensitivity Analysis and Experimental Research on Ball Bearing Early Fault Diagnosis Based on Testing Signal from Casing[J]. Journal of Dynamic Systems Measurement & Control, 2014, 136(6):061009.