基于双树复小波和自适应权重和时间因子的粒子群优化支持向量机的轴承故障诊断

摘要/Abstract

摘要： 提出了一种基于双树复小波和具有自适应权重和时间因子的粒子群算法优化支持向量机的轴承故障诊断方法。首先对机械振动信号进行DTCWT变换，提取能量熵作为特征向量。然后采用AWTFPSO算法优化SVM，实现轴承故障诊断。不同方法的对比实验及分析结果表明，该方法速度快、准确率高。

关键词: 双树复小波, 支持向量机, 粒子群算法, 自适应权重和时间因子, 故障诊断

Abstract: Based on DTCWT and SVM improved by AWTFPSO, a new method of bearing fault diagnosis was proposed. The mechanical vibration signals were first processed by DTCWT and the energy entropy was extracted as the feature vector. Then, SVM optimized by AWTFPSO was introduced to bearing fault diagnosis. Comparions of different methods show that the proposed method has advantages of high speed and accuracy.

Key words: dual-tree complex wavelet transform(DTCWT), support vector machines(SVM), particle swarm optimization(PSO), adaptive weighting and time factor(AWTF), fault diagnosis

中图分类号:

TN911.6

张淑清, 胡永涛, 姜安琦, 吴迪, 陆超, 姜万录. 基于双树复小波和自适应权重和时间因子的粒子群优化支持向量机的轴承故障诊断[J]. 中国机械工程.

ZHANG Shuqing, HU Yongtao, JIANG Anqi, WU Di, LU Chao, JIANG Wanlu. Bearing Fault Diagnosis Based on DTCWT and AWTFPSO-optimized SVM[J]. China Mechanical Engineering.

参考文献

[1]唐先广, 郭瑜, 丁彦春, 等. 基于短时傅里叶变换和独立分量分析的滚动轴承包络分析[J]. 机械强度, 2012, 34(1)：1-5.
TANG Guangxian, GUO Yu, DING Yanchun, et al. Application of Rolling Element Bearing Envelope Analysis Based on Short Time Fourier Transition and Independent Components Analysis[J]. Journal of Mechanical Strength, 2012, 34(1):1-5.
[2]杨绍普, 赵志宏. 改进的小波相邻系数降噪方法及其在机械故障诊断中的应用[J].机械工程学报, 2013, 49(17)：137-141.
YANG Shaopu, ZHAO Zhihong. Improved Wavelet Denoising Using Neighboring Coefficients and Its Applitcation to Machinery Fault Diagnosis[J]. Journal of Mechanical Engineering,2013, 49(17):137-141.
[3]张云强, 张培林, 吴定海, 等. 基于最优广义 S 变换和脉冲耦合神经网络的轴承故障诊断[J]. 振动与冲击, 2015, 34(9)：26-31.
ZHANG Yunqiang, ZHANG Peilin, WU Dinghai, et al. Bearing Fault Diagnosis Based on Optimal Generalized S Transform and Pulse Coupled Neural Network[J]. Journal of Vibration and Shock, 2015, 34(9):26-31.
[4]Bin G F, Gao J J, Li X J, et al. Early Fault Diagnosis of Rotating Machinery Based on Wavelet Packets—Empirical Mode Decomposition Feature Extraction and Neural Network[J]. Mechanical Systems and Signal Processing, 2012, 27(2):696-711.
[5]郑近德, 程军圣, 杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(19)： 2641-2646.
ZHENG Jinde, CHENG Junsheng, YANG Yu.Multi-scale Permutation Entropy and Its Applications to Rolling Bearing Fault Diagnosis[J]. China Mechanical Engineering, 2013, 24(19): 2641-2646.
[6]秦大力, 于德介. 基于本体的机械故障诊断贝叶斯网络[J]. 中国机械工程, 2013, 24(9): 1195-1209.
QIN Dali, YU Dejie.Ontology-based Diagnostic Bayesian Networks for Mechanical Fault Diagnosis[J]. China Mechanical Engineering, 2013, 24(9): 1195-1209.

[7]DEMIREL H, ANBARJAFARI G. Image Resolution Enhancement by Using Discrete and Stationary Wavelet Decomposition[J]. Image Processing, IEEE Transactions on, 2011, 20(5):1458-1460.
[8]艾树峰. 基于双树复小波变换的轴承故障诊断研究[J]. 中国机械工程, 2011, 22(20)：2446-2451.
AI Shufeng. Research on Bearing Fault Diagnosis Based on Dual-tree Complex Wavelet Transform[J]. China Mechanical Engineering, 2011, 22(20): 2446-2451.
[9]胥永刚, 孟志鹏, 陆明, 等. 双树复小波和奇异差分谱在滚动轴承故障诊断中的应用[J]. 振动工程学报, 2013, 26(6)：965-973.
XU Yonggang, MENG Zhipeng, LU Ming, et al. Application of Dual-tree Complex Wavelet Transform and Singular Value Difference Spectrum in the Rolling Bearing Fault Diagnosis[J]. Journal of Vibration Engineering, 2013, 26(6):965-973.
[10]王国彪, 何正嘉, 陈雪峰, 等. 机械故障诊断基础研究 “何去何从”[J]. 机械工程学报, 2013, 49(1)：63-72.
WANG Guobiao, HE Zhengjia, CHEN Xuefeng, et al. Basic Research on Machinery Fault Diagnosis-What is the Prescription[J]. Journal of Mechanical Engineering, 2013, 49(1):63-72.
[11]李鑫滨, 陈云强, 张淑清. 基于改进 ABC 算法优化的 LSSVM 多分类器组机械故障诊断模型[J]. 中国机械工程, 2013, 24(16): 2157-2164.
LI Xinbin, CHEN Yunqiang, ZHANG Shuqing.Mechanical Fault Diagnosis Model Based on Improved ABC Algorithm Optimized Multiple LSSVM Classifier Group[J]. China Mechanical Engineering, 2013, 24(16): 2157-2164.
[12]TIAN J, HU Q, MA X, et al. An Improved KPCA/GA-SVM Classification Model for Plant Leaf Disease Recognition[J].Journal of Computational Information Systems, 2012, 8(18)：7737-7745.
[13]HARISH N, LOKESH A, MANDAL S, et al. Parameter Optimization Using GA in SVM to Predict Damage Level of Non-reshaped Berm Breakwater[J]. The International Journal of Ocean and Climate Systems, 2014, 5(2)：79-88.
[14]SUBASI A. Classification of EMG Signals Using PSO Optimized SVM for Diagnosis of Neuromuscular Disorders[J]. Computers in Biology and Medicine, 2013, 43(5)：576-586.
[15]XUE Z, DU P, SU H. Harmonic Analysis for Hyperspectral Image Classification Integrated with PSO Optimized SVM[J]. Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, 2014, 7(6)：2131-2146.
[16]匡芳君, 徐蔚鸿, 张思扬. 基于改进混沌粒子群的混合核 SVM 参数优化及应用[J]. 计算机应用研究, 2014, 31(3)：671-674.
KUANG Fangjun, XU Weihong, ZHANG Siyang. Parameter Optimization and Application of SVM with Mixtures Kernels Based on Improved Chaotic Particle Swarm Optimization[J]. Application Research of Computers, 2014, 31(3):671-674.
[17]SHAKIBA R, SALEHI M E. PSO-based Path Planning Algorithm for Humanoid Robots Considering Safety[J]. Journal of Computer & Robotics, 2014, 5(1)：47-54.
[18]马国庆, 李瑞峰, 刘丽. 学习因子和时间因子随权重调整的粒子群算法[J]. 计算机应用研究, 2014, 31(11)：3291-3294.
MA Guoqing, LI Ruifeng,LIU Li. Particle Swarm Optimization Algorithm of Learning Factors and Time Factor Adjusting to Weights[J]. Application Research of Computers, 2014, 31(11)：3291-3294.
[19]DANENAS P, GARSVA G. Selection of Support Vector Machines Based Classifiers for Credit Risk Domain[J]. Expert Systems with Applications,2015, 42(6): 3194-3204.
[20]田中大, 高宪文, 石彤，等. 用于混沌时间序列预测的组合核函数最小二乘支持向量机[J].物理学报, 2014, 63(16)：66-76.
TIAN Zhongda, GAO Xianwen, SHI Tong,et al. Combination Kernel Function Least Squares Support Vector Machine for Chaotic Time Series Prediction[J]. Acta Physica Sinica, 2014,63(16): 66-76.
[21]HSUC W, LIN C J. A Comparison of Methods for Multiclass Support Vector Machines[J]. Neural Networks, IEEE Transactions on, 2002, 13(2): 415-425.