Multiple Local PCA Models for Fault Diagnosis With Application to the Tennessee Eastman Process
In the present work, the multiplicity of fault characteristics during process evolvement is proposed and utilized to improve fault diagnosis performance. It is based on the following recognition that the underlying fault characteristics in general do not stay constant but will present changes with the fault process evolvement. It is called the multiplicity of fault behaviors along time direction, revealing different fault variable correlations in different time periods. To analyze the multiplicity of fault characteristics, a fault division algorithm is developed to separate the fault process into multiple local time periods so that the fault characteristics can be deemed similar within ea ch local time period. Then a representative fault decomposition model is built in each local time period to reveal the relationships between the fault and normal operation cases. The proposed method gives an interesting insight into the fault evolvement behaviors and a more accurate from-fault-to-normal reconstruction result can be expected for fault diagnosis. The feasibility and performance of the proposed fault diagnosis method are illustrated with the Tennessee Eastman process.
Principal component analysis (PCA) multiplicity of fault characteristics fault process division fault reconstruction fault diagnosis.
Chunhui Zhao Youxian Sun Furong Gao
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering
国内会议
厦门
英文
1-7
2012-08-01（万方平台首次上网日期，不代表论文的发表时间）