Research on Operation Condition Monitoring Method of Intellectual Apparatus Based on Data Driven

被引：0
|
作者：
Gao X. [1 ]
Yang D. [1 ]
机构：
[1] College of Information Science and Engineering, Northeastern University, Shenyang
来源：
Yang, Dongsheng (yangdongsheng@ise.neu.edu.cn) | 2017年 / Shanghai Jiaotong University卷 / 51期
关键词：
Condition monitoring; Hidden semi-Markov model (HSMM); Intellectual apparatus; Kernel principal component analysis (KPCA); Multi-information fusion; Wavelet transform;
D O I：
10.16183/j.cnki.jsjtu.2017.09.013
中图分类号：
学科分类号：
摘要：
Alternating current (AC) contactor used frequently under full load is taken as a research object, and a method of apparatus operation condition monitoring based on data driven is proposed in this paper. First, historical operation data of AC contactor are collected by test platform and state characteristic parameters are gained. Combined with comprehensive assessment of wavelet transform and principal component analysis, data preprocessing such as denoising and removing outliers is used. Then, aimed at the disadvantage of high-dimensionality and redundancy, kernel principal component analysis (KPCA) is adopted to merge multi-information and kernel parameters are optimized based on test data. Finally, the fused information is input to hidden semi-Markov model (HSMM), and the operation condition monitoring and recognition of intellectual apparatus are realized. The practicability and validity of the method in apparatus condition monitoring is verified by test data from CJX2-8011 AC contactor. © 2017, Shanghai Jiao Tong University Press. All right reserved.
引用
收藏
页码：1104 / 1110
页数：6
相关论文
共 15 条
  • [1] Hammerschmidt M., Ncuhaus A.R., Rieder W.F., The effect of material transfer in relays diagnosed by force and/or voltage measurement, IEEE Transactions on Components and Packaging Technologies, 7, 1, pp. 12-18, (2004)
  • [2] Wang X., Rong M., Wu Y., Et al., Method of quick fault diagnosis and new knowledge obtainment for high voltage circuit breaker expert system, Proceedings of the CSEE, 27, 3, pp. 95-99, (2007)
  • [3] Li L., Ma D., Li Z., Performance assessment based on condition monitoring data of electrical contact of electrical products, Journal of Mechanical Engineering, 51, 18, pp. 198-203, (2015)
  • [4] Huang Y., Yu Z., Xie C., Et al., Study on the application of electric power big data technology in power system simulation, Proceedings of the CSEE, 35, 1, pp. 13-22, (2015)
  • [5] Yuan J., Li K., Wang Y., Et al., Study on online monitoring of electrical endurance of AC contactor, Low Voltage Apparatus, 17, pp. 7-10, (2011)
  • [6] Ye X., Ma Y., Meng H., Et al., Degradation failure model of electromagnetic relay, Proceedings of ICEC-ICREPEC, pp. 116-123, (2012)
  • [7] Cai T., Zhu J., Adaptive selection of optimal decomposition level in threshold de-noising algorithm based on wavelet, Control and Decision, 21, 2, pp. 217-220, (2006)
  • [8] Yang Z., Dong M., Equipment fault diagnosis using auto-regressive hidden Markov models, Journal of Shanghai Jiao Tong University, 42, 3, pp. 471-474, (2008)
  • [9] Smits G.F., Jordan E.M., Improved SVM regression using mixtures of kernels, Proceeding of the 2002 International Joint Conference on Neural Net Works, pp. 2785-2790, (2002)
  • [10] Zheng W., Zou C., Zhao L., An improved algorithm for kernel principal components analysis, Neural Processing Letters, 22, 1, pp. 49-56, (2005)
12