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

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 methods, none them meet all criteria implementing an efficient system (such intelligent solution, average effort, a reasonable cost, diagnosis, fewer false alarms, etc.). In addition, these techniques require either correct, robust, representative model or relevant data experts’ knowledge continuous updates. paper, we propose Machine Learning-based approach diagnostic system. It multi-class classifier predicts plant state: normal faulty what fault has arisen case failing behavior.