A Multiagent-Based Methodology for Known and Novel Faults Diagnosis in Industrial Processes

Abstract

This article proposes a multiagent-based methodology for the real-time fault diagnosis in industrial processes. This articles aims to build a decision support tool that helps process operators identify and better manage abnormal situations. The supervised and semisupervised machine learning methods are widely used to develop such tools. Despite their accuracy in classifying faults, supervised methods have a major limitation: they cannot diagnose novel faults. The semisupervised methods can detect and isolate novel faults but cannot disclose their root causes. The proposed methodology combines both supervised and semisupervised methods in a parallel-serial structure, exploiting their respective strengths. Moreover, it provides the process expert with the meaningful explanations of the detected novel faults or otherwise. Two case studies are used in this article to demonstrate the effectiveness of the proposed methodology. The first case is the Tennessee Eastman process benchmark. The second one uses the real data collected from a heat recovery system in a thermomechanical pulp mill.