Advanced data-driven fault detection in gas-to-liquid plants

Abstract

Fault detection is a critical part of process monitoring, where the objective is to flag unexpected operating behavior quickly and accurately. In this paper, a novel extension of the Generalized Likelihood Ratio charts is proposed, denoted as the Maximum Multivariate GLR charts. Linear and nonlinear data-driven models, namely principal component analysis and its kernel extension and neural networks, are combined with different statistical charts towards the detection of multiple fault types in three distinct case studies: synthetic, Tennessee Eastman process, and Gas-to-Liquid process. The results show that the MMGLR charts have a better detection accuracy than conventional charts, and that neural networks are more robust modeling techniques than PCA and KPCA for the sake of fault detection.