Machine learning-based approach for online fault Diagnosis of Discrete Event System

TL;DR

This paper presents a machine learning-based method for online fault diagnosis in discrete event systems, aiming to improve efficiency, reduce false alarms, and operate without extensive system modeling or expert input.

Contribution

It introduces a multi-class classifier approach for real-time fault detection and identification in automated production systems modeled as discrete event systems.

Findings

Effective in predicting system states as normal or faulty

Capable of identifying specific faults in real-time

Reduces reliance on detailed system models or expert knowledge

Abstract

The problem considered in this paper is the online diagnosis of Automated Production Systems with sensors and actuators delivering discrete binary signals that can be modeled as Discrete Event Systems. Even though there are numerous diagnosis methods, none of them can meet all the criteria of implementing an efficient diagnosis system (such as an intelligent solution, an average effort, a reasonable cost, an online diagnosis, fewer false alarms, etc.). In addition, these techniques require either a correct, robust, and representative model of the system or relevant data or experts' knowledge that require continuous updates. In this paper, we propose a Machine Learning-based approach of a diagnostic system. It is considered as a multi-class classifier that predicts the plant state: normal or faulty and what fault that has arisen in the case of failing behavior.