Abstract— In this paper, Particle Swarm Optimization (PSO) technique is applied to tune the Adaptive Neuro Fuzzy Controller (ANFIS) for vehicle suspension system. LQR controller is used to obtain the training data set for the vehicle suspension system. Subtractive clustering technique is used to formulate ANFIS which approximates the actuator output force as a function of system states. PSO algorithm search for optimal radii for subtractive clustering based ANFIS. Training is done off line and the cost function is based on the minimization of the error between actual and approximated output. Simulation results show that the PSO-ANFIS based vehicle suspension system exhibits an improved ride comfort and good road holding ability.

Index Terms— Vehicle suspension, Quarter car model, ANFIS, FLC, ride comfort.

Cite: Rajeswari Kothandaraman and Lakshmi Ponnusamy, "PSO tuned Adaptive Neuro-fuzzy Controller for Vehicle Suspension Systems," Journal of Advances in Information Technology, Vol. 3, No. 1, pp. 57-63, February, 2012.doi:10.4304/jait.3.1.57-63