Neural fault diagnosis and fuzzy fault control for a complex linear dynamic system

Fault diagnosis has become an issue of primary importance in modern process automation as it provides the prerequisites for the task of fault detection. The ability to detect the faults is essential to improve reliability and security of a complex control system. In this paper, the authors describe a completed feasibility study demonstrating the merit of employing pattern recognition and an artificial neural network for fault diagnosis through a backpropagation learning algorithm and making use of fuzzy approximate reasoning for fault control via parameter changes in a dynamic system. As a test case, a complex magnetic levitation vehicle (MLV) system is studied. Analytical fault symptoms are obtained by system dynamics measurements and the classification is carried out through a multilayer feedforward network. The neural network is first taught the different fault situations through training patterns. After the network is trained, it achieves an overall classification accuracy of 99.78% for a disturbance-free MLV model and 91.4% for a model with track disturbance irregularities. Proper actions are performed based on fuzzy reasoning of knowledge base results in a normal process operation recovered