An Application Study of the Improved PCA Method in the TE Process Fault Detection

摘要：

In this paper, a specific description of the principles and procedures about how to use PCA method is given, in the field of fault detection in industrial systems, based on the Tennessee-Eastman process. An improved PCA method is presented and a more precise model of the principal component is established. The simulation results show that the improved PCA has better performance, effectively reduce the missed alarm rate and enhance the sensitivity and robustness of faults detection systems. This article also summarized the cases about other deficiencies and improvement of PCA method, such as nonlinearity, adaptation and so on, which provides the corresponding solution ideas and improved programs of research, using PCA-based fault diagnosis method in variety of different industrial objects.

关键词： PCA Fault Detection TEP Data preprocessing

作者: GAO Qiang JIA Zefang

作者单位: Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin University of Technology Tianjin, China

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 706-709

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）