基于K-PSO稀疏表示的故障分类方法研究

摘要/Abstract

摘要： 针对现代复杂生产过程中不能准确识别、分类多种故障的问题,提出一种改进的稀疏表示故障分类方法。该方法依据信号的稀疏表示来判断故障所属类别。其具体实现过程首先是利用K-均值奇异值分解(K-SVD)算法构造过完备字典,使其包含原信息的主要特征,再通过粒子群(PSO)算法有效地搜索并寻找稀疏分解中产生的在过完备字典范围中的最匹配原子,最后利用以该匹配原子为基础的稀疏表示结果实现对多故障问题的分类识别。运用数值仿真验证了该算法的可行性和有效性。同时,针对柴油机燃油系统的故障分类,将该方法与基于BP神经网络和SVM的分类识别方法进行比较,实验表明该算法在故障分类上具有更好的效果。

关键词: 稀疏表示,K-均值奇异值分解算法,粒子群算法,故障分类

Abstract: In order to solve the problem of multiple faults which can not be identified and classified accurately in modern complex production process,an improved sparse representation fault classification method was proposed.This method is based on the sparse representation of the signal to determine the fault categories.First,the specific implementation process utilizes K-Means Singular Value De-composition(K-SVD) algorithm to constructe over complete dictionary with main features in the original message,and then uses the particle swarm optimization(PSO) algorithm to search and find the most matching atom which is generated in sparse decomposition in the range of over complete dictionary.Finally,the results based on the sparse representation realizes classification and identification about multiple faults problem.The validity and practicability of the proposed method is verified by numerical simulation.Meanwhile,the proposed method was compared with the methods based on the BP neural network and SVM classification through the fault classification of diesel engine fuel system.Experiments show that the algorithm has good effect on fault classification.

Key words: Sparse representation,K-SVD algorithm,Particle swarm optimization algorithm,Fault classification

傅蒙蒙,王培良. 基于K-PSO稀疏表示的故障分类方法研究[J]. 计算机科学, 2016, 43(12): 302-306. https://doi.org/10.11896/j.issn.1002-137X.2016.12.056

FU Meng-meng and WANG Pei-liang. Investigation on Fault Classification Method of K-PSO Sparse Representation[J]. Computer Science, 2016, 43(12): 302-306. https://doi.org/10.11896/j.issn.1002-137X.2016.12.056

参考文献

[1] Zhu Z B.Intergrating clustering analysis for fault detection and classification[D].Hangzhou:Zhejiang University,2012(in Chinese) 祝志博.融合聚类分析的故障检测和分类研究[D].杭州:浙江大学,2012
[2] Zhang M,Cheng W M,Liu J.Small fault detection and classification method for complex production process[J].Southwest Jiaotong University,2014,49(5):842-847(in Chinese) 张敏,程文明,刘娟.复杂生产过程的小故障检测与分类方法[J].西南交通大学学报,2014,9(5):842-847
[3] Yin J L,Zhu Y L,Yu G Q,et al.Fault diagnosis of transformers based on Gaussian process classifier[J].Transctions of China Electrotechical Society,2013,8(1):158-164(in Chinese) 尹金良,朱永利,俞国勤,等.基于高斯过程分类器的变压器故障诊断[J].电工技术学报,2013,8(1):158-164
[4] He J J,Zhang J X,Jia S Q,et al.A new Gaussian process classification algorithm[J].Control and Decision,2014,9(9):1587-1592(in Chinese) 贺建军,张俊星,贾思齐,等.一种新高斯过程分类算法[J].控制与决策,2014,9(9):1587-1592
[5] Li W H,Zhang S G.Fault classification based on improved evidence theory and multiple neural network fusion[J].Journal of Mechanical Engineering,2010,6(9):93-99(in Chinese) 李巍华,张盛刚.基于改进证据理论及多神经网络融合的故障分类[J].机械工程学报,2010,6(9):93-99
[6] Zhao L J,Yuan D C,Chai T Y.Identification of wastewater operational conditions based on multi-classification probabilistic extreme learning machine [J].CIESC Journal,2012,3(10):3173-3182(in Chinese) 赵立杰,袁德成,柴天佑.基于多分类概率极限学习机的污水处理过程操作工况识别[J].化工学报,2012,3(10):3173-3182
[7] Donoho D L.Compressed sensing [J].IEEE Transactions on Information Theory,2006,2(4):1289-1306
[8] Hu Z P,Song S F.Robust image recognition algorithm of maximum likelihood estimation sparse representation based on class-related neighbors subspace[J].Acta Automatica Sinica,2012,8(9),1420-1427(in Chinese) 胡正平,宋淑芬.基于类别相关近邻子空间的最大似然稀疏表示鲁棒图像识别算法[J].自动化学报,2012,8(9):1420-1427
[9] Dong J J,Mao Q R,Hu S L,et al.Sub-coding and Entire-coding Jointly Penalty Based Sparse Representation Dictionary Lear-ning[J].Computer Science,2014,41(10):122-127(in Chinese) 董俊健,毛启容,胡素黎,等.基于子编码和全编码联合惩罚的稀疏表示字典学习方法[J].计算机科学,2014,41(10):122-127
[10] Pei S Y,Tong L.A global sparse representation scheme based on PCA for fault identification of helicopter rotor computer engineering and applications[J].Electronic World,2014(5):94-95(in Chinese) 裴胜玉,童浪.最佳PCA稀疏表示方法及在直升机旋翼故障识别中的应用[J].电子世界,2014(5):94-95
[11] Zhu Q B,Yang B,Huang M.Bearing fault diagnosis based on a kernel-mapping sparse representation classification[J].Journal of Vibration and Shock,2013,2(11):30-34(in Chinese) 朱启兵,杨宝,黄敏.基于核映射稀疏表示分类的轴承故障诊断[J].振动与冲击,2013,2(11):30-34
[12] Olshausen B A,Field D J.Emergence of simple-cell recep-tive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609
[13] Zhou Y,Wang L.Fault signal extraction method based on sparse encoding and Tabu optimization algorithm[J].Computer Mea-surement & Control,2014,22(7):2164-2181(in Chinese) 周晏,王璐.基于稀疏编码和禁忌优化的故障信号抽取方法[J].计算机测量与控制,2014,2(7):2164-2181
[14] Candès E,Romberg J.Sparsity and incoherence in compres-sive sampling[J].Inverse Problems,2006,23(3):969-985
[15] Mallat S G,Zhang Z F.Matching Pursuits With Time-Frequency Dictionaries[J].IEEE Transactions on Signal Processing,1993,41(12):3397-3415
[16] Wang Z Y,Qin L L,Diao J L.Digital Modulation Recognition Based on Sparse Representation and K-SVD[J].Computer Scien-ce,2013,0(10):65-67(in Chinese) 王振宇,秦立龙,刁俊良.基于K-SVD和稀疏表示的数字调制模式识别[J].计算机科学,2013,40(10):65-67
[17] Ahsron M,Elad M,Bruekstein A.An K-SVD algorithm for de-signing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322
[18] Rubinstein R,Zibulevsky M,Elad M.Efficient Implementation of the K-SVD Algorithm using Batch Orthogonal Matching Pursuit[R].Technical Report CS,2009
[19] Pati Y C,Rezaiifar R,Krishnaprasad P S.Orthogonal matching pursuit:recursive function approximation with applications to wavelet decomposition[C]∥Proceedings of Asilomar Confe-rence on Signals,Systems and Computers.1993:40-44
[20] Kennedy J,Eberhart R.Particle swarm optimization[C]∥Proc.IEEE.Int’l.Conf.on Neural Networks,IV.Piscataway NJ:IEEE Service Center.1995:1942-1948
[21] Fu Y X,Zhao H,et al.MATLAB neural network application design[M].Beijing:Machinery Industry Press,2010(in Chinese) 傅荟璇,赵红,等.MATLAB神经网络应用设计[M].北京:机械工业出版社,2010

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed