SVM Based on ACROA and Its Applications to Rotating Machinery Fault Diagnosis

Abstract

Abstract:

Firstly, in view of SVM parameters optimization problem, combination to the advantage of ACROA, a new classification model, called ACROA_SVM was presented herein. Furthermore, the effectiveness and superiority of the ACROA_SVM model was identified via benchmark datasets, which was downed from the sit web of UCI. Lastly, combination to local mean decomposition and energy moment feature extraction, ACROA_SVM was served as approach of pattern recognition to identify rotating machinery fault types. The experimental results show ACROA_SVM method has higher precision, better generalization ability of fault diagnosis, and less time consumption, higher efficiency of fault diagnosis, which is conducive to realize online intelligent fault diagnosis.

Key words: support vector machine(SVM), artificial chemical reaction optimization algorithm(ACROA), rotating machinery, fault diagnosis

摘要：

针对支持向量机(SVM)的参数优化问题，结合人工化学反应优化算法的优点，提出了基于人工化学反应优化算法的支持向量机(ACROA_SVM)方法；然后利用标准数据验证了ACROA_SVM方法的有效性和优越性；最后,结合局部均值分解信号分析和能量矩特征提取，将ACROA_SVM方法应用于旋转机械故障诊断中。分析结果表明，ACROA_SVM方法不但具有较高的故障诊断精度和较好的泛化能力，而且时间消耗短，故障诊断效率高，有利于实现在线智能故障诊断。

关键词: 支持向量机, 人工化学反应优化算法, 旋转机械, 故障诊断

CLC Number:

Luo Songrong, Cheng Junsheng, Hunglinh A O. SVM Based on ACROA and Its Applications to Rotating Machinery Fault Diagnosis[J]. China Mechanical Engineering, 2015, 26(10): 1306-1312.

罗颂荣, 程军圣, Hunglinh A O. 基于人工化学反应优化的SVM及旋转机械故障诊断[J]. 中国机械工程, 2015, 26(10): 1306-1312.

References

[1]陈安华,周博,张会福,等.基于PCA与蚁群算法的机械故障聚类诊断方法[J].中国机械工程,2013,24(24):3333-3337.
[2]Yuan Shengfa, Chu Fulei. Fault Diagnosis Based on Support Vector Machines with Parameter Optimisation by Artificial Immunisation Algorithm[J]. Mechanical Systems and Signal Processing, 2007, 21 (3) : 1318-1330.
[3]Wang Huaqing, Chen Peng. Intelligent Diagnosis Method for Rolling Element Bearing Faults Using Possibility Theory and Neural Network[J]. Computers Industrial Engineering, 2011, 60(4) :511- 518.
[4]Wang C, Kang Yuan, Shen Pingchen, et al. Applications of Fault Diagnosis in Rotating Machinery by Using Time Series Analysis With Neural Network[J]. Expert Systems with Applications, 2010, 37 (2) : 1696-1702.
[5]Vapnik V, Chapelle O. Bounds on Error Expecta- tion for Support Vector Machines[J]. Neural Computation, 2000, 12(9) 2013-2036.
[6]Shi X H,Liang Y C, Lee H P, et al. An Improved GA and a Novel PSO-GA Based Hybrid Algorithm[J]. Information Processing Letters, 2005, 93(5): 255-261.
[7]Shelokar P S, Siarry P, Jayaraman V K, et al. Par- ticle Swarm and Ant Colony Algorithms Hybridized for Improved Continuous Optimization[J]. Applied Mathematics and Computation, 2007, 188(1): 129- 142.
[8]Xiao Jing, Li Liangping, A Hybrid Ant Colony Op- timization for Continuous Domains[J]. Expert Systems with Applications, 2011, 38 (9): 11072- 11077.
[9]An Senjian, Liu Wanquan, Venkatesh S. Fast Cross-validation Algorithms for least Squares Support Vector Machine and Kernel Ridge Regression [J]. Pattern Recognition, 2007, 40 (8) : 2154 - 2162.
[10]Diosan L, Rogozan A, Pecuchet J P. Improving Classification Performance of Support Vector Machine by Genetically Optimising Kernel Shape and Hyper-Parameters[J] Applied Intelligence, 2010, 36(2): 280-294.
[11]张弦,王宏力.基于粒子群优化的最小二乘支持向量机在时间序列预测中的应用[J].中国机械工程,2011,22(21):2572-2576.
[12]Alatas B. A Novel Chemistry Based Metaheuristic Optimization Method for Mining of Classification Rules[J]. Expert Systems with Applications, 2012, 39: 11080-11088.
[13]Alatas B. ACROA: Artificial Chemical Reaction Optimization Algorithm for Global Optimization [J]. Expert Systems with Applications, 2011, 32: 13170-13180.
[14]Lai Xingwu, Tse P W, Zhang Guicai, et al. Classification of Gear Faults Using Cumulants and the Radial Basis Function Network[J]. Mechanical Systems and Signal Processing, 2004, 18: 381- 389.
[15]Zhang Xiaoli, Chen Xuefeng, He Zhengjia. An ACO-based Algorithm for Parameter Optimization of Support Vector Machines[J]. Expert Systems with Applications, 2010, 37: 6618-6628.
[16]Jonathan S S. The Local Mean Decomposition and Its Application to EEG Perception Data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443-454.
[17]Peng Zhike, Peter W, Chu Fulei. A Comparison Study of Improved Hilbert-Huang Transform and Wavelet Transform: Application to Fault Diagnosis for Rolling Bearing[J]. Mechanical Systems and Signal Processing, 2005, 19(1): 974-988.