An Approach to Automated Fault Diagnosis of Hydraulic Circuits Using Neural Networks

Fault diagnosis is one of the most important tasks assigned to intelligent supervisory control systems. Recently, artificial neural networks have been applied to this area more or less successfully with simple networks based on the Multi-Layer Perceptron (MLP). In this report, we will show a different approach to fault diagnosis through the use of dynamic radial basis function networks. We will show how the method created herein is more reliable than MLP methods that were not able to cope with certain categories of problems and finally, we will finish with a complete analysis of cost (space and time) as well as the weaknesses of this architecture. Résumé Le diagnostic d'erreur est une des plus importantes tâches affectée aux systèmes de contrôles intelligents. Récemment le domaine des réseaux neuronaux a été appliqué a ce domaine de recherche avec un succès plus ou moins reconnu grâce à des réseaux neuronaux élémentaires comme the Perceptron Multi-couches. Dans ce rapport, nous montre..