Harrou, Fouzi and Madakyaru, Muddu and Sun, Ying (2017) Improved nonlinear fault detection strategy based on the Hellingerdistance metric: Plug flow reactor monitoring. Energy and Buildings, 143. pp. 149-161. ISSN 0378-7788

PDF 2329.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

tFault detection has a vital role in the process industry to enhance productivity, efficiency, and safety,and to avoid expensive maintenance. This paper proposes an innovative multivariate fault detectionmethod that can be used for monitoring nonlinear processes. The proposed method merges advantagesof nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metricto identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantifythe dissimilarity between current NLPLS-based residual and reference probability distributions obtainedusing fault-free data. Furthermore, to enhance further the robustness of these methods to measurementnoise, and reduce the false alarms due to modeling errors, wavelet-based multiscale filtering of residualsis used before the application of the HD-based monitoring scheme. The performances of the developedNLPLS-HD fault detection technique is illustrated using simulated plug flow reactor data. The resultsshow that the proposed method provides favorable performance for detection of faults compared to theconventional NLPLS method.

Actions (login required)

View Item