Localized Fisher discriminant analysis based complex chemical process monitoring

• Published in: AIChE journal Vol. 57; no. 7; pp. 1817 - 1828
• Main Author: Yu, Jie
• Format: Journal Article
• Language: English
• Published: Hoboken Wiley Subscription Services, Inc., A Wiley Company 01.07.2011; Wiley; American Institute of Chemical Engineers
• Subjects: Algorithms; Applied sciences; Chemical engineering; chemical process monitoring; Classification; Clusters; Construction; Discriminant analysis; Exact sciences and technology; fault detection and classification; Faults; Gaussian mixture model; localized Fisher discriminant analysis; Mathematical models; Monitoring; Monitoring methods; Monitoring systems; Normal distribution; Preserves; Principal components analysis; Safety; stationarity testing; Tennessee Eastman process; USA, Tennessee; chemical process monitoring; localized Fisher discriminant analysis; Sensitivity analysis; Independent component analysis; Extract; stationarity testing; Algorithm; Modeling; Steady state; Gaussian mixture model; fault detection and classification; Surveillance; Tennessee Eastman process; Failure detection; Partial least squares; Principal component analysis
• DOI: 10.1002/aic.12392
• ISSN: 0001-1541

Complex chemical process is often corrupted with various types of faults and the fault‐free training data may not be available to build the normal operation model. Therefore, the supervised monitoring methods such as principal component analysis (PCA), partial least squares (PLS), and independent component analysis (ICA) are not applicable in such situations. On the other hand, the traditional unsupervised algorithms like Fisher discriminant analysis (FDA) may not take into account the multimodality within the abnormal data and thus their capability of fault detection and classification can be significantly degraded. In this study, a novel localized Fisher discriminant analysis (LFDA) based process monitoring approach is proposed to monitor the processes containing multiple types of steady‐state or dynamic faults. The stationary testing and Gaussian mixture model are integrated with LFDA to remove any nonstationarity and isolate the normal and multiple faulty clusters during the preprocessing steps. Then the localized between‐class and within‐class scatter mattress are computed for the generalized eigenvalue decomposition to extract the localized Fisher discriminant directions that can not only separate the normal and faulty data with maximized margin but also preserve the multimodality within the multiple faulty clusters. In this way, different types of process faults can be well classified using the discriminant function index. The proposed LFDA monitoring approach is applied to the Tennessee Eastman process and compared with the traditional FDA method. The monitoring results in three different test scenarios demonstrate the superiority of the LFDA approach in detecting and classifying multiple types of faults with high accuracy and sensitivity. © 2010 American Institute of Chemical Engineers AIChE J, 2011