Author/Authors :
DING, S University of Duisburg-Essen - Institute for Automatic Control and Complex Systems (AKS), Germany , ZHANG, P University of Duisburg-Essen - Institute for Automatic Control and Complex Systems (AKS), Germany , DING, E University of Applied Sciences Gelsenkirchen - Department of Physical Engineering, Germany , YIN, S University of Duisburg-Essen - Institute for Automatic Control and Complex Systems (AKS), Germany , Naik, A University of Duisburg-Essen - Institute for Automatic Control and Complex Systems (AKS), Germany , DENG, P Central South University - School of Information Science and Engineering, China , GUI, W Central South University - School of Information Science and Engineering, China
Abstract :
In this paper, we briefly address the application of the standard principal component analysis (PCA) technique to fault detection and identification. Based on an analysis of the existing test statistic, we propose a new test statistic, which is similar to the Hawkin’s TH² statistic but without the numerical drawback.In comparison with the SPE index, the threshold setting associated with the new statistic is computationally simpler. Our further study is dedicated to the analysis of fault sensitivity. We consider the off-set and scaling faults, and evaluate the test statistic by viewing its sensitivity to the faults. Our final study focuses on identifying off-set and scaling faults. To this end, two algorithms are proposed. This paper also includes some critical remarks on the application of the PCA technique to fault diagnosis.
Keywords :
process monitoring , fault diagnosis , principal component analysis (PCA) , multivariate analysis
