Multiple Faults Fuzzy Detection Approach Improved by Particle Swarm Optimization

In this paper an on-line multiple faults detection approach is proposed and improved by the use of Particle Swarm Optimization (PSO) to optimally adjust the membership functions parameters. The residuals obtained by Analytical Redundancy Relations are used as inputs to our system. The Analytical Redundancy Relations are generated by the use of bond graph modelling. The results of the fuzzy detection module are presented as a colored causal graph. The causal graph represents the state of different variables from the green nominal state to the red faulty state. The proposed approaches are then tested through a simulation of the three-tank hydraulic system. A comparison between the results obtained by using PSO and those given by the use of Genetic Algorithms (GA) is finally made.