Multi-Step Ahead Fault Prediction Method Based on PCA and EMD

摘要：

In recent years, fault prediction method, which means forecast process fault in an early time based on the current condition of the system, has attracted more and more attention by companies and scientists. However, it still has many problems in this area, especially for its application in industrial process. In the present work, a multi-step ahead fault prediction method combining principle component analysis, empirical mode decomposition and extreme learning machine are developed to realize early prediction of fault. The application of the presented method is illustrated with respect to simulated data collected from the Tennessee Eastman process. The experimental results demonstrate the effectiveness of the proposed method.

关键词： fault prediction principle component analysis (PCA) empirical mode decomposition (EMD) extreme learning machine (ELM) fault diagnosis signal processing

作者: Shu Wang Zhen Zhao Fuli Wang Yuqing Chang

作者单位: Key Laboratory of Integrated Automation of Process Industry, Ministry of Education, Northeastern Uni School of Information & Control Engineering, Liaoning University of Petroleum & Chemical Technology,

会议类型: 国际会议

会议名称: 2011 China Control and Decision Conference(2011中国控制与决策会议 CCDC)

会议地点: 四川绵阳

会议语种:英文

页码: 2879-2883

在线出版日期: 2011-05-23（万方平台首次上网日期，不代表论文的发表时间）