基于假设检验和支持向量机的旋转机械故障诊断方法

摘要/Abstract

摘要： 针对旋转机械故障诊断中存在的早期非平稳微弱故障信号特征提取困难、故障诊断不准确等问题，提出了一种基于自适应假设检验滤波和支持向量机（SVM）的故障诊断方法。该方法采用统计学假设检验原理来评估参考信号(噪声信号)和原始信号(故障信号)在频域上的相似性，删除具有高相似性的频域成分；通过粒子群优化算法获得最佳的显著性水平α；定义评估因子Ipq来评价假设检验滤波的效果。最后通过SVM来逐次诊断轴系构造异常。验证结果表明该方法能够有效地诊断出传动轴不对中和不平衡的故障类型。

关键词: 特征提取, 假设检验, 显著性水平；支持向量机

Abstract: A fault diagnosis method was proposed based on adaptive statistic test filter (STF) and SVM for condition diagnosis of rotating machinery to extract weak fault features and identify fault types. STF was based on the statistic of the hypothesis testing in the frequency domain to evaluate similarity among reference signals (noise signal) and original signals, and remove the components of high similarity. The optimal level of significance α was obtained by using particle swarm optimization(PSO). To evaluate the performances of the STF, evaluation factor Ip qwas also defined. Finally, a sequential diagnosis method, using sequential inference and SVM was also proposed, by which the conditions of rolling bearings might be identified sequentially. Practical examples of fault diagnosis for structural faults often occurring in the shafts, such as unbalance, misalignment states were shown to verify that the method is effective.

Key words: feature extraction, hypothesis testing, level of significance, support vector machine(SVM)

中图分类号:

TH133.2
O21

赵宇, 李可, 宿磊, 陈鹏. 基于假设检验和支持向量机的旋转机械故障诊断方法[J]. 中国机械工程.

ZHAO Yu, LI Ke, SU Lei, CHEN Peng. Fault Diagnosis Method Based on Hypothesis Testing and SVM for Condition Diagnosis of Rotating Machinery[J]. China Mechanical Engineering.

参考文献

[1]LI K, CHEN P, WANG S M. An Intelligent Diagnosis Method for Rotating Machinery Using Least Squares Mapping and a Fuzzy Neural Network[J]. Sensors,2012,5:5919-5939.
[2]PUSEY H C. Machinery Condition Monitoring[J]. Journal of Sound and Vibration,2000,34(5):6-7.
[3]LIN J, QU L. Feature Extraction Based on Morlet Wavelet and Its Application for Mechanical Fault Diagnosis[J]. Journal of Sound and Vibration,2000,234(1):135-148.
[4]LIU B, LING S F. On the Selection of Informative Wavelets for Machinery Diagnosis[J]. Mechanical Systems and Signal Processing,1999,13(1):145-162.
[5]赵志宏. 基于振动信号的机械故障特征提取与诊断研究[D]. 北京：北京交通大学,2012.
ZHAO Zhihong. Research on Vibration Signal Based Machinery Fault Feature Extraction and Diagnosis[D]. Beijing: Beijing Jiaotong University,2012.
[6]曾海东, 韩峰, 刘瑶琳. 傅里叶分析的发展与现状[J]. 现代电子技术,2014,37(3):144-147.
ZENG Haidong, HAN Feng, LIU Yaolin. Development and Current Situation of Fourier Analysis[J]. Modern Electronics Technique,2014,37(3):144-147.
[7]杨旭霞, 张毅, 张鹏. 基于FFT分析振动信号的机械故障诊断[J]. 山西电子技术,2015(2):6-7.
YANG Xuxia, ZHANG Yi, ZHANG Peng. The Mechanical Fault Diagnosis of Vibration Signal Based on FFT Analysis[J]. Shanxi Electronic Technology，2015(2):6-7.
[8]余建青, 臧观建, 谢世坤,等. 旋转机械故障诊断中的信号处理技术综述[J]. 机床与液压, 2011,39(24):107-110.
YU Jianqin, ZANG Guanjian, XIE Shikun, et al. The Summary of Signal Processing Technology in Fault Diagnosis for Rotating Machinery[J]. Machine Tool＆Hydraulics,2011,39(24):107-110.
[9]WATSON S J, XIANG B J, YANG Wenxian, et al. Condition Monitoring of the Power Output of Wind Turbine Generators Using Wavelets[J]. IEEE Transactions on Energy Conversion,2010,25:715-721.
[10]RAFIEE J, RAFIEE M A, TSE P W. Application of Mother Wavelet Functions for Automatic Gear and Bearing Fault Diagnosis[J]. Expert Systems with Applications,2010,37(6):4568-4579.
[11]廖庆斌, 李舜酩. 一种旋转机械振动信号特征提取的新方法[J]. 中国机械工程，2006，17(16)：1675-1679.
LIAO Qingbin, LI Shunmin. A Method for Feature Extraction of Rotating Machinery Vibration Signals[J]．China Mechanical Engineering,2006,17(16):1675-1679.
[12]LI K, CHEN P, WANG H Q. Intelligent Diagnosis Method for Rotating Machinery Using Wavelet Transform and Ant Colony Optimization[J]. IEEE Sensors,2012,12(7):2474-2484.
[13]HUANG Q, JIANG D X, HONG L Y, et al. Application of Wavelet Neural Networks on Vibration Fault Diagnosis for Wind Turbine Gearbox[J]. Lecture Notes in Computer Science,2008,5264:313-320
[14]JACK L B, NANDI A K. Fault Detection Using Support Vector Machines and Artificial Neural Networks, Augmented by Genetic Algorithms[J]. Mechanical Systems and Signal Processing,2002,16:373-390.
[15]YANG B S, HAN T, AN J L. ART-KOHONEN Neural Network for Fault Diagnosis of Rotating Machinery[J]. Mechanical Systems and Signal Processing,2004,18:645-65.
[16]XUE Hongtao, WANG Huaqing, CHEN Peng, et al. Automatic Diagnosis Method for Structural Fault of Rotating Machinery Based on Distinctive Frequency Components and Support Vector Machines under Varied Operating Conditions[J]. Neurocomputing,2013,116:326-335.