An energy graph eigendecomposition approach to fault detection and isolation applied to a gas-to-liquids process

Abstract

Fault detection and isolation (FDI), which make up a large part of a process monitoring protocol, is a refined scheme which aims to detect and isolate anomalies that occur within an industrial plant. For the past 50+ years, much work has been done on developing FDI schemes for a vast array of different applications. In recent years, novel energy-based FDI techniques were proposed, as energy is seen as a unifying parameter of different domains. Additionally, the proposed energy-based approaches attempt to capture causal (or structural) information of the considered physical system. Keeping with this theme, this study will determine, after some alterations, the applicability and performance of some of the previously proposed energy-based approaches, especially compared to one another, when applied to a single, larger-scale gas-to-liquid (GTL) process. The approaches covered in this study include one qualitative eigendecomposition approach, one quantitative eigendecomposition approach, and a graph matching approach utilising a distance parameter (DC-value). Even though the quantitative eigendecomposition approach revealed improved detection sensitivity over the DC-value approach for faulty conditions, both techniques revealed a detection accuracy of 89%. The DC-value approach could correctly isolate 71% of the fault cases while the quantitative and qualitative eigendecomposition approaches could respectively only match 37.69% and 11% correctly. Even though the eigendecomposition approaches could not outperform the DC-value approach, the resolution benefit of 6 parameters that it offers warrants further research.