基于改进KICA的故障检测方法在连续采煤机上的应用研究
|
摘要
连续采煤机是煤矿中的重要设备,如果连续采煤机因为发生故障而停机,会导致整个煤矿系统瘫痪。因此,对连续采煤机进行故障检测具有重要的现实意义。本文提出了一种基于改进的核独立元分析(Kernel Independent Component Analysis,简称KICA)的故障检测方法,并针对连续采煤机截割部减速器进行故障检测。
KICA结合了核主元分析(Kernel Principle Component Analysis,简称KPCA)和独立元分析(Independent Component Analysis,简称ICA)的优点,是在线故障检测的一种非线性方法。在KICA方法中,数据映射到特征空间后变得线性冗余；当引入核技巧时,输入空间线性相关的数据映射到特征空间会产生误差；另外,在KPCA训练过程中核矩阵大小是样本个数的平方,计算量较大。针对上述问题,本文提出了相似性分析的解决方法,对KICA进行了改进,即在使用KICA算法之前先在输入空间和特征空间对数据进行相似性分析,去除掉相似性较强的数据。此方法既降低了计算量,又减少了引入核技巧时带来的误差。
利用改进的KICA我们能够从连续采煤机的数据中提取具有代表性的特征数据,根据其提取的特征数据计算故障检测统计量,能够更好的反映当时连续采煤机采煤过程的运行状况。本文采用Hotelling T2和平方预测误差(SPE)统计量进行故障检测,由于数据从输入空间映射到特征空间时,原始的SPE统计量计算公式不再适用,因而针对改进的KICA建立了一种新的SPE统计量计算公式。
最后本文将此方法应用到了连续采煤机的截割部减速器故障检测当中,并通过Matlab进行了仿真研究,实验结果表明改进的KICA有效地捕获了变量中的非线性动态特征,并成功检测到故障的发生。
The continuous miner is an important equipment in the excavate coal industry. It may make the coal-mining system broken-down, if continuous miner stop running cause of fault.The importance of the continuous miner fault diagnosis is increasingly prominent. In this paper, the fault detection method based on improved kernel independent component analysis (KICA) is developed. The proposed approach is applied to cutting unit reducer of continuous miner for fault detection.
KICA is unsupervised and combines the advantages of KPCA and ICA to develop a nonlinear approach to detect fault online. Because the data mapped into feature space become linearly redundant, linear relation data introduce error while the kernel trick is used and the size of the kernel matrix are the square of the number of samples in the training process of KPCA, similarity analysis is developed to improve KICA algorithm, i.e., observation data is deal with using similarity analysis in input space and feature space before KICA algorithm. This method not only decreases the computation load, but also reduces the error while the kernel trick is used.
We can extract the dominant feature data from the data of continuous miner by the KICA method. The statistics, calculated based on the feature data, can be better to describe the mining status of the continuous miner. This paper makes use of the Hotelling T2 and SPE statistics for fault detection. The original formula for calculating the SPE statistics is not available any more, because the data is mapped from input space to feature space. To solve this problem, a new formula for KICA is established.
This method is applied to the fault detection of the reducer of continuous miner in this paper. The simulation result shows that the KICA method can capture the nonlinear dynamic features effectively, and detects the fault successfully.
KICA结合了核主元分析(Kernel Principle Component Analysis,简称KPCA)和独立元分析(Independent Component Analysis,简称ICA)的优点,是在线故障检测的一种非线性方法。在KICA方法中,数据映射到特征空间后变得线性冗余；当引入核技巧时,输入空间线性相关的数据映射到特征空间会产生误差；另外,在KPCA训练过程中核矩阵大小是样本个数的平方,计算量较大。针对上述问题,本文提出了相似性分析的解决方法,对KICA进行了改进,即在使用KICA算法之前先在输入空间和特征空间对数据进行相似性分析,去除掉相似性较强的数据。此方法既降低了计算量,又减少了引入核技巧时带来的误差。
利用改进的KICA我们能够从连续采煤机的数据中提取具有代表性的特征数据,根据其提取的特征数据计算故障检测统计量,能够更好的反映当时连续采煤机采煤过程的运行状况。本文采用Hotelling T2和平方预测误差(SPE)统计量进行故障检测,由于数据从输入空间映射到特征空间时,原始的SPE统计量计算公式不再适用,因而针对改进的KICA建立了一种新的SPE统计量计算公式。
最后本文将此方法应用到了连续采煤机的截割部减速器故障检测当中,并通过Matlab进行了仿真研究,实验结果表明改进的KICA有效地捕获了变量中的非线性动态特征,并成功检测到故障的发生。
The continuous miner is an important equipment in the excavate coal industry. It may make the coal-mining system broken-down, if continuous miner stop running cause of fault.The importance of the continuous miner fault diagnosis is increasingly prominent. In this paper, the fault detection method based on improved kernel independent component analysis (KICA) is developed. The proposed approach is applied to cutting unit reducer of continuous miner for fault detection.
KICA is unsupervised and combines the advantages of KPCA and ICA to develop a nonlinear approach to detect fault online. Because the data mapped into feature space become linearly redundant, linear relation data introduce error while the kernel trick is used and the size of the kernel matrix are the square of the number of samples in the training process of KPCA, similarity analysis is developed to improve KICA algorithm, i.e., observation data is deal with using similarity analysis in input space and feature space before KICA algorithm. This method not only decreases the computation load, but also reduces the error while the kernel trick is used.
We can extract the dominant feature data from the data of continuous miner by the KICA method. The statistics, calculated based on the feature data, can be better to describe the mining status of the continuous miner. This paper makes use of the Hotelling T2 and SPE statistics for fault detection. The original formula for calculating the SPE statistics is not available any more, because the data is mapped from input space to feature space. To solve this problem, a new formula for KICA is established.
This method is applied to the fault detection of the reducer of continuous miner in this paper. The simulation result shows that the KICA method can capture the nonlinear dynamic features effectively, and detects the fault successfully.
引文
1.胡敬东,连向东.我国煤炭科技发展现状及展望[J],煤炭科学技术,2005,30(1)：21-24.
2.黄绍服,何庆.浅析连续采煤机故障检测技术研究[J],中国检测技术,2004,30(3)：26-30.
3.叶铁丽等.采煤机在线故障诊断与预报专家系统[J],煤矿机械,2000,(7)：49-51.
4.刘建平.我国煤矿连续采煤机国产化发展现状与思考[J],采矿技术,2006,6(3)：437-453.
5.于伟信.复杂煤层模拟及连续采煤机截割机构参数优化[D],葫芦岛：辽宁工程技术大学,2006.
6.周东华,叶银忠.现代故障诊断于容错控制[M],清华大学出版社,2000,4-10.
7.王仲生.智能故障诊断与容错控制[M],西安：西北工业大学出版社,2005,6-11.
8.陈玉东,施颂椒,翁正新.动态系统的故障诊断方法综述[J],化工自动化及仪表,2001,28(3)：1-14.
9.潘玉松.基于主元分析的传感器故障检测与诊断[D],北京：华北电力大学,2006.
10. Kramer, M. A.. Nonlinear principal component analysis using autoassociative neural networks [J], AIChE Journal,1991,37:233-243.
11. Dong, D.,& McAvoy, T. J.. Nonlinear principal component analysis based on principal curves and neural networks [J], Computers and Chemical Engineering,1996,20,65-78.
12. Hiden, et al. Non-linear principal components analysis using genetic programming [J], Computers & Chemical Engineering,1999,23:413-425.
13. Tan, S., & Mavrovouniotis, M. L.. Reducing data dimensionality through optimizing neural networks inputs [J], AIChE Journal,1995,41:1471-1480.
14. J. C. Knirsch, P. MJuller, K.-R. RJatsch. Input space versus feature space in kernelbased methods [J], IEEE Transactions on Neural Networks,1999,10(5):1000-1016.
15. Sang Wook Choi, et al. Fault detection and identification of nonlinear processes based on Kernel PCA [J], Chemometrics and Intelligent Laboratory Systems,2005,75:55-67.
16.Ji-Hoon Cho, et al. Fault identification for process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2005,60:279-288.
17. B. Scholkopf, A. Smola, K.R. Muller, Nonlinear component analysis as a kernel eigenvalue problem [J], Neural Comput,1998,10(5):1299-1319.
18. S. Mika, B. Scholkopf, et al. KPCA and de-noising in feature spaces [J], Advances in Neural Information Processing Systems,1999,11:536-542.
19. Ming J. Zuo, Jing Lin, Xianfeng Fan. Feature separation using ICA for a one-dimensional time series and its application in fault detection [J], Journal of Sound and Vibration,2005, 287:614-624.
20.刘永欣.关于在煤矿机电设备中故障检测诊断技术的应用[J],采矿技术,2004,23(10)：89-90.
21.董爱华,刘丽红.故障检测诊断技术在煤矿机电设备中的应用[J],焦作工学院学报,2005,21(3)：189-192.
22.姜林先,李桂轲.采煤机故障分析与诊断[J],煤炭技术,1999,18(6)：1-2.
23.张寒松,贾瑞清,王廷军.采煤机的故障分析与诊断及其发展趋势[J],矿业,2004,13(2)：85-88.
24.吴莹锋.矿用挖掘机行走减速器故障诊断技术研究[D],长春：吉林大学,2007.
25.寿海飞.基于小波分析的齿轮故障诊断研究[D],杭州：浙江工业大学,2007.
26.王艳芳.齿轮箱故障特征提取技术研究[D],太原：中北大学,2007.
27.周辉.齿轮故障的特征提取与模式识别技术研究[D],郑州：郑州大学,2005.
28.王凡,杨树莲.BP神经网络在采煤机故障诊断中的应用[J],煤矿现代化,2006,(6)：36-37.
29.杨树莲,李文海等.小波和神经网络在采煤机故障诊断中的应用[J],煤炭科学技术,2006,34(9)：23-25.
30.朱孔伟.基于主元分析的电厂锅炉故障检测与诊断[D],南京：东南大学,2006.
31. Masayuki Tamura, Shinsuke Tsujita. A study on the number of principal components and sensitivity of fault detection using PCA [J], Computers & Chemical Engineering,2007, 30:1035-1046.
32.王静.飞控系统故障诊断技术研究及软件开发[D],西安：西北工业大学,2007.
33.高岩.化工过程故障诊断方法应用研究[D],无锡：江南大学,2005.
34. L.J. Cao, K.S. Chua, W.K. Chong, H.P. Lee, Q.M. Gu. A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine [J], Neurocompution,2003,55: 321-336.
35. Jong-Min Lee, S.Joe Qin, In-Beum Lee. Fault detection and diagnosis of multivariate process based on modified independent component analysis [J], AIChE Journal,2006,52: 3501-3514.
36. Jackson JE. A User's Guide to Principal Components [M], New York:John Wiley & Sons, 1991, Inc.
37. Jackson JE, Mudholkar GS. Control procedures for residuals associated with principal component analysis [J], Technometrics,1979,21(3):341-349.
38.王峻峰.基于主分量、独立分量分析的盲信号处理及应用研究[D],武汉：华中科技 大学,2005.
39.Achmad Widodo, Bo-Suk Yang, Tian Han. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors [J], Expert Systems with Applications,2007,32:299-312.
40.郭辉.基于ICA的工业过程监控研究[D],北京：北京化工大学,2006.
41.吴昌应.基于ICA的多元投影算法在过程监控中的应用研究[D],无锡：江南大学,2006.
42.郑春厚.独立分量分析算法及其应用研究[D],合肥：中国科学技术大学,2006.
43.Jong-Min Lee, ChangKyoo Yoo, In-Beum Lee. Statistical process monitoring with independent component analysis [J], Journal of Process Control,2004,14:467-485.
44.蒋星.基于独立分量分析特征提取的心电信号模式识别的研究[D],上海：上海交通大学,2007.
45. A. Hyvarinen. Fast and robust fixed-point algorithms for independent component analysis [J], IEEE Transactions on,1999,10:1129-1159.
46. Hyvarinen A, Oja E. Independent component analysis:algorithms and applications [J], Neural Networks,2000,13(4-5):411-430.
47. A. Hyvarinen. New approximations of differential entropy for independent component analysis and projection pursuit [J], Advances in Neural Information Processing Systems, 1998,10:273-279.
48. Ji-Hoon Cho, Jong-Min Lee, et al. Fault identi.cation for process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2005,60:279-288.
49.李巍华,廖广兰,史铁林.核函数主元分析及其在齿轮故障诊断中的应用[J],机械工程学报,2003,39(8)：65-70.
50. Jong-Min Lee, et al. Nonlinear process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2004,59:223-234.
51. ChangKyoo Yoo, In-Beum Lee. Nonlinear multivariate filtering and bioprocess monitoring for supervising nonlinear biological processes [J], Process Biochemistry,2006, 41:1854-1863.
52. Sang Wook Choi, In-Beum Lee. Nonlinear dynamic process monitoring based on dynamic kernel PCA [J], Chemical Engineering Science,2004,59:5897-5908.
53.郭辉,王玲,刘贺平.基于核主成分分析与最小二乘支持向量机结合处理时间序列预测问题[J],北京科技大学学报,2006,28(3)：303-306.
54.陈玉山,席斌.基于核独立成分分析和BP网络的人脸识别[J],计算机工程与应用,2007,43(26)：230-232.
55. Wenfei Wang, Jimin Liang, et al. Human Gait Recognition Based on Kernel Independent Component [J], Digital Image Computing Techniques and Application,2007,9:573-578.
56. ZHANG Xi, YAN Wei-wu, et al. Nonlinear Statistical Process Monitoring Based on Control Charts with Memory Effect and Kernel Independent Component Analysis [J], Journal of Shanghai Jiaotong University,2007,12(5):563-571.
57.Jian Yang, Xiumei Gao, David Zhang, Jing-yu Yang. Kernel ICA: An alternative formulation and its application to face recognition [J], Pattern Recognition,2005, 38:1784-1787.
2.黄绍服,何庆.浅析连续采煤机故障检测技术研究[J],中国检测技术,2004,30(3)：26-30.
3.叶铁丽等.采煤机在线故障诊断与预报专家系统[J],煤矿机械,2000,(7)：49-51.
4.刘建平.我国煤矿连续采煤机国产化发展现状与思考[J],采矿技术,2006,6(3)：437-453.
5.于伟信.复杂煤层模拟及连续采煤机截割机构参数优化[D],葫芦岛：辽宁工程技术大学,2006.
6.周东华,叶银忠.现代故障诊断于容错控制[M],清华大学出版社,2000,4-10.
7.王仲生.智能故障诊断与容错控制[M],西安：西北工业大学出版社,2005,6-11.
8.陈玉东,施颂椒,翁正新.动态系统的故障诊断方法综述[J],化工自动化及仪表,2001,28(3)：1-14.
9.潘玉松.基于主元分析的传感器故障检测与诊断[D],北京：华北电力大学,2006.
10. Kramer, M. A.. Nonlinear principal component analysis using autoassociative neural networks [J], AIChE Journal,1991,37:233-243.
11. Dong, D.,& McAvoy, T. J.. Nonlinear principal component analysis based on principal curves and neural networks [J], Computers and Chemical Engineering,1996,20,65-78.
12. Hiden, et al. Non-linear principal components analysis using genetic programming [J], Computers & Chemical Engineering,1999,23:413-425.
13. Tan, S., & Mavrovouniotis, M. L.. Reducing data dimensionality through optimizing neural networks inputs [J], AIChE Journal,1995,41:1471-1480.
14. J. C. Knirsch, P. MJuller, K.-R. RJatsch. Input space versus feature space in kernelbased methods [J], IEEE Transactions on Neural Networks,1999,10(5):1000-1016.
15. Sang Wook Choi, et al. Fault detection and identification of nonlinear processes based on Kernel PCA [J], Chemometrics and Intelligent Laboratory Systems,2005,75:55-67.
16.Ji-Hoon Cho, et al. Fault identification for process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2005,60:279-288.
17. B. Scholkopf, A. Smola, K.R. Muller, Nonlinear component analysis as a kernel eigenvalue problem [J], Neural Comput,1998,10(5):1299-1319.
18. S. Mika, B. Scholkopf, et al. KPCA and de-noising in feature spaces [J], Advances in Neural Information Processing Systems,1999,11:536-542.
19. Ming J. Zuo, Jing Lin, Xianfeng Fan. Feature separation using ICA for a one-dimensional time series and its application in fault detection [J], Journal of Sound and Vibration,2005, 287:614-624.
20.刘永欣.关于在煤矿机电设备中故障检测诊断技术的应用[J],采矿技术,2004,23(10)：89-90.
21.董爱华,刘丽红.故障检测诊断技术在煤矿机电设备中的应用[J],焦作工学院学报,2005,21(3)：189-192.
22.姜林先,李桂轲.采煤机故障分析与诊断[J],煤炭技术,1999,18(6)：1-2.
23.张寒松,贾瑞清,王廷军.采煤机的故障分析与诊断及其发展趋势[J],矿业,2004,13(2)：85-88.
24.吴莹锋.矿用挖掘机行走减速器故障诊断技术研究[D],长春：吉林大学,2007.
25.寿海飞.基于小波分析的齿轮故障诊断研究[D],杭州：浙江工业大学,2007.
26.王艳芳.齿轮箱故障特征提取技术研究[D],太原：中北大学,2007.
27.周辉.齿轮故障的特征提取与模式识别技术研究[D],郑州：郑州大学,2005.
28.王凡,杨树莲.BP神经网络在采煤机故障诊断中的应用[J],煤矿现代化,2006,(6)：36-37.
29.杨树莲,李文海等.小波和神经网络在采煤机故障诊断中的应用[J],煤炭科学技术,2006,34(9)：23-25.
30.朱孔伟.基于主元分析的电厂锅炉故障检测与诊断[D],南京：东南大学,2006.
31. Masayuki Tamura, Shinsuke Tsujita. A study on the number of principal components and sensitivity of fault detection using PCA [J], Computers & Chemical Engineering,2007, 30:1035-1046.
32.王静.飞控系统故障诊断技术研究及软件开发[D],西安：西北工业大学,2007.
33.高岩.化工过程故障诊断方法应用研究[D],无锡：江南大学,2005.
34. L.J. Cao, K.S. Chua, W.K. Chong, H.P. Lee, Q.M. Gu. A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine [J], Neurocompution,2003,55: 321-336.
35. Jong-Min Lee, S.Joe Qin, In-Beum Lee. Fault detection and diagnosis of multivariate process based on modified independent component analysis [J], AIChE Journal,2006,52: 3501-3514.
36. Jackson JE. A User's Guide to Principal Components [M], New York:John Wiley & Sons, 1991, Inc.
37. Jackson JE, Mudholkar GS. Control procedures for residuals associated with principal component analysis [J], Technometrics,1979,21(3):341-349.
38.王峻峰.基于主分量、独立分量分析的盲信号处理及应用研究[D],武汉：华中科技 大学,2005.
39.Achmad Widodo, Bo-Suk Yang, Tian Han. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors [J], Expert Systems with Applications,2007,32:299-312.
40.郭辉.基于ICA的工业过程监控研究[D],北京：北京化工大学,2006.
41.吴昌应.基于ICA的多元投影算法在过程监控中的应用研究[D],无锡：江南大学,2006.
42.郑春厚.独立分量分析算法及其应用研究[D],合肥：中国科学技术大学,2006.
43.Jong-Min Lee, ChangKyoo Yoo, In-Beum Lee. Statistical process monitoring with independent component analysis [J], Journal of Process Control,2004,14:467-485.
44.蒋星.基于独立分量分析特征提取的心电信号模式识别的研究[D],上海：上海交通大学,2007.
45. A. Hyvarinen. Fast and robust fixed-point algorithms for independent component analysis [J], IEEE Transactions on,1999,10:1129-1159.
46. Hyvarinen A, Oja E. Independent component analysis:algorithms and applications [J], Neural Networks,2000,13(4-5):411-430.
47. A. Hyvarinen. New approximations of differential entropy for independent component analysis and projection pursuit [J], Advances in Neural Information Processing Systems, 1998,10:273-279.
48. Ji-Hoon Cho, Jong-Min Lee, et al. Fault identi.cation for process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2005,60:279-288.
49.李巍华,廖广兰,史铁林.核函数主元分析及其在齿轮故障诊断中的应用[J],机械工程学报,2003,39(8)：65-70.
50. Jong-Min Lee, et al. Nonlinear process monitoring using kernel principal component analysis [J], Chemical Engineering Science,2004,59:223-234.
51. ChangKyoo Yoo, In-Beum Lee. Nonlinear multivariate filtering and bioprocess monitoring for supervising nonlinear biological processes [J], Process Biochemistry,2006, 41:1854-1863.
52. Sang Wook Choi, In-Beum Lee. Nonlinear dynamic process monitoring based on dynamic kernel PCA [J], Chemical Engineering Science,2004,59:5897-5908.
53.郭辉,王玲,刘贺平.基于核主成分分析与最小二乘支持向量机结合处理时间序列预测问题[J],北京科技大学学报,2006,28(3)：303-306.
54.陈玉山,席斌.基于核独立成分分析和BP网络的人脸识别[J],计算机工程与应用,2007,43(26)：230-232.
55. Wenfei Wang, Jimin Liang, et al. Human Gait Recognition Based on Kernel Independent Component [J], Digital Image Computing Techniques and Application,2007,9:573-578.
56. ZHANG Xi, YAN Wei-wu, et al. Nonlinear Statistical Process Monitoring Based on Control Charts with Memory Effect and Kernel Independent Component Analysis [J], Journal of Shanghai Jiaotong University,2007,12(5):563-571.
57.Jian Yang, Xiumei Gao, David Zhang, Jing-yu Yang. Kernel ICA: An alternative formulation and its application to face recognition [J], Pattern Recognition,2005, 38:1784-1787.