Data based approach for online diagnosis of Discrete Event System
Résumé
In this paper, we are interested in the online diagnosis of Automated Production Systems with sensors and actuators delivering discrete binary signals (TOR), which are part of Discrete Event Systems. We offer an intelligent diagnostic solution to replace traditional solutions, that are often non-industrializable, by a new data-based method learned from the simulation of the plant behaviors and using recurrent neural networks (RNN) with short-term and long-term memory (Long short-term memory, LSTM).