Comparative Analysis of Adaptive NeuroFuzzy Control Techniques for Full Car Active Suspension System

Suspension system of a vehicle is used to minimize the effect of different road disturbances on ride comfort and to improve the vehicle control. The main objective of this work is to design an efficient active suspension control paradigm for full car model with 8 degrees of freedom using adaptive soft-computing techniques. The detailed mathematical model of the adaptive Mamdani fuzzy logic control and different adaptive neurofuzzy wavelet networks have been developed and successfully applied to a full car model. The parameters of the proposed controllers have been adjusted using online adaptation by minimizing the cost function. The robustness of the presented active controllers has been proved on the basis of different performance indices. Two road profiles have been used to check the performance of the proposed active suspension controllers as compared with passive, semi-active suspension, backstepping based fuzzy logic control, and linear quadratic regulated based suspension systems. The performance of the active suspension systems has been optimized in terms of displacement and acceleration of seat, heave, pitch, and roll.