|
|
基于MBPLS的液压潜液泵故障检测方法
|
Abstract:
本文提出了一种基于MBPLS故障检测方法，与其他的PLS不同的是，本方法重在结合设备的工作工况，从系统级、部件级进行剖析，深层次挖掘设备运行数据之间的关联关系，结合PLS算法优势，实现更优的设备故障检测。在本文中，先通过研究设备各作业工况下相关变量关系，再对各变量进行分组，从系统角度和局部角度分别展开数据分析，可以提高故障检测效率。仿真结果表明，基于设备工况进行分块的MBPLS故障检测方法包含了更多的负载信息并且提高了诊断性能。
In this paper, a PLS fault detection method based on working condition classification is proposed. Different from other PLS, this method focuses on the working condition of the equipment, analyzes from the system level and component level, deeply excavates the correlation between the operating data of the equipment, and combines the advantages of PLS algorithm to achieve better equipment fault detection. In this paper, the fault detection efficiency can be improved by first studying the relationship between the relevant variables under each operating condition of the equipment, and then grouping each variable to carry out data analysis from the system perspective and local perspective. The simulation results show that the MBPLS fault detection method based on equipment working conditions contains more load information and improves the diagnostic performance.
| [1] | Downs, J.J. and Vogel, E.F. (1993) A Plant-Wide Industrial Process Control Problem. Computers & Chemical Engineering, 17, 245-255. https://doi.org/10.1016/0098-1354(93)80018-i |
| [2] | 李尔国, 俞金, 等. PCA在过程故障检测与诊断中的应用[J]. 华东理工大学学报, 2001, 19(1): 1-8. |
| [3] | 陈国金, 梁军, 钱积新. 独立元分析方法(ICA)及其在化工过程监控和故障诊断中的应用[J]. 化工学报, 2003, 54(10): 1474-1477. |
| [4] | 宋凯, 王海清, 李平. PLS质量监控及其在(Tennessee Eastman)过程中的应用[J]. 浙江大学学报, 2005, 39(5): 658-662. |
| [5] | Cheng, Y., Zhuang, Y. and Yang, J. (1992) Optimal Fisher Discriminant Analysis Using the Rank Decomposition. Pattern Recognition, 25, 101-111. https://doi.org/10.1016/0031-3203(92)90010-g |
| [6] | Plovoso, M.J. and Kosanovich, K.A. (1994) Applications of Multivariate Statistical Methods to Process Monitoring and Controller Design. International Journal of Control, 59, 743-765. https://doi.org/10.1080/00207179408923103 |
| [7] | Zhao, L.-J., Chai, T.-Y. and Wang, G. (2003) A Nonlinear Modeling and Online Monitoring Method for the Batch Process Using Glmultiple Local PCA. Proceedings of the 2003 International Conference on Machine Learning and Cybernetics, Xi’an, 5 November 2003, 1190-1194. https://doi.org/10.1109/ICMLC.2003.1259666 |
| [8] | 张立君, 刘爱伦. 基于改进主元分析方法的化工过程的故障检测[J]. 工业控制计算机, 2006, 19(1): 21-25. |
| [9] | 杨莉. 基于主元分析的多变量统计的故障辨识技术[J]. 信息与电子工程, 2004, 2(4): 256-258. |
| [10] | 冯俊婷, 王桂增, 徐铁. 基于在主元分析的核电站主冷却剂泵故障诊断[J]. 原子能科学技术, 2003, 37(5): 395-399. |
| [11] | 王惠文. 偏最小二乘回归方法及其应用[M]. 北京: 国防工业出版社, 1999. |
| [12] | 孔祥玉, 罗家宇, 张琪. 基于正交信号修正与高效偏最小二乘的质量相关故障检测方法[J]. 控制与决策, 2020, 35(5): 146-153. |
