Gearbox fault diagnosis and application based on wavelet packet and centroid particle swarm optimization

PDF(1092 KB)

Journal of Vibration and Shock ›› 2016, Vol. 35 ›› Issue (11) : 191-195.

QianLin1, KangMin1,2

Author information +

History +

Abstract

For a large amount of state information in gearbox vibration signal is difficult to be effectively extracted, the wavelet packet decomposition was used to reduce noise and extract energy feature of the original vibration signal. Pattern recognition of fault was carried out with BP neural network. Considering the BP neural network of slow convergence speed and easily getting into local optimal value, improved centroid particle swarm algorithm (ICPSO) was proposed to optimize the weights and bias of BP neural network. In ICPSO, by introducing the design of center in population and the best individual mass, the dynamically change of inertia weight into speed adjustment formula to build ICPSO. ICPSO was compared with basic particle swarm algorithm and genetic algorithm in gearbox fault diagnosis test. The results show that ICPSO can effectively improve the classification efficiency and accuracy.

Key words

Wavelet packet decomposition / Centroid particle swarm optimization / Vibration signal / Neural Network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

QianLin1, KangMin1,2. Gearbox fault diagnosis and application based on wavelet packet and centroid particle swarm optimization[J]. Journal of Vibration and Shock, 2016, 35(11): 191-195

References

[1] MALLAT S. A Wavelet Tour of Signal Processing[M]. Washington: Academic Press, 1999.
[2]纪震,廖惠连,吴青华.粒子群算法及应用[M].北京：科学出版社，2009.
JI Zhen, LIAO Huilian, WU Qinghua. Particle Swarm Algorithm and Application [M].Beijing: Science Press, 2009.
[3] A. Djebala, N. Ouelaa, C. Benchaabane, et al. Application of the Wavelet Multi-resolution Analysis and Hilbert transform for the prediction of gear tooth defects [J]. Meccanica, 2012, 47:1601–1612.
[4] ZHANG Zhen-you, WANG Yi, WANG Kesheng. Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network [J]. Journal of Intelligent Manufacturing, 2013, 24:1213–1227.
[5]周祥鑫, 王小敏, 杨扬,等. 基于小波阈值的高速道岔振动信号降噪[J]. 振动与冲击, 2014, 33(23): 200—206.
ZHOU Xiangxin, WANG Xiao-min, YANG Yang, et al. De-Noising of High-speed Turnout Vibration Signal based on Wavelet Threshold. Journal of Vibration and Shock, 2014, 33(23): 200-206.
[6] HUANG Wentao, NIU Peilu, LU Xiao-jun. Spur Bevel Gearbox Fault Diagnosis Using Wavelet Packet Transform for Feature Extraction [J]. Practical Applications of Intelligent Systems, 2014: 155-165.
[7] 罗毅，甄立敬. 基于小波包与倒频谱分析的风电机组齿轮箱齿轮裂纹诊断方法[J]. 振动与冲击, 2015, 34(3): 210—214.
LUO Yi, ZHEN Lijing. Diagnosis Method of Turbine Gearbox Crack Based on Wavelet Packet and Cepstrum Analysis [J].Journal of Vibration and Shock, 2015, 34(3): 210-214.
[8]李萌.旋转机械轴承故障的特征提取与模式识别方法研究[D]. 吉林:吉林大学, 2008.
LI Meng. Research on the Method of Feature Extraction and Pattern Recognition for Bearings Fault of Rotating Machinery[D]. Jilin: Jilin University, 2008.
[9]魏秀业,潘宏侠. 粒子群优化及智能故障诊断[M]. 北京:国防工业出版社, 2010.
WEI Xiuye, PAN Hongxia. Particle Swarm Optimization and Intelligent Fault Diagnosis[M]. Beijing: National Defense Industry Press, 2010.
[10]汪永生,李均利. 质心粒子群优化算法[J]. 计算机工程与应用,2011,03:34-37.
WANG Yongsheng, LI Junli.Centroid particle swarm optimization algorithm.Computer Engineering and Applications, 2011,47(3):34-37.
[11] HUANG Qian, JIANG Dongxiang, HONG Liang-you, et al. Application of Wavelet Neural Networks on Vibration Fault Diagnosis for Wind Turbine Gearbox [J].Advances in Neural Networks, 2008: 313-320.
[12]龙泉, 刘永前, 杨勇平.基于粒子群优化BP神经网络的风电机组齿轮箱故障诊断方法[J].太阳能学报, 2012, 33(1): 120—124.
LONG Quan, LIU Yongqian, YANG Yong-ping. Wind Turbine Gearbox Fault Diagnosis Method based on Particle Swarm Optimizing BP Neural Network [J].ACTA ENERGIAE SOLARIS SINICA, 2012, 33(1):120-124.
[13] (美)Martin T. Hagan等著.神经网络设计[M]. 戴葵等译.北京:机械工业出版社,2002.
Martin T. Hagan. Neural Network Design[M].DAI Kui, Beijing: Mechanical Industry Press, 2002.
[14]陈寿文.基于质心与自适应指数惯性权重改进的粒子群算法[J].计算机应用, 2015, 35(3): 675—679.
CHEN Shouwen. Improved Particle Swarm Optimization Algorithm based on Centroid and Self-adaptive exponential inertia weight. Journal of Computer Applications, 2015,35(3):675-679.