A New Fuzzy-NARMA L2 Controller Design for Active Suspension System

Abstract

This paper is concerned with the design of a newcontroller for active suspension system. The model isconsidered as a quarter-car. The presented controller dependson the fuzzy technique and NARMA-L2 linearizationalgorithm. The compensation system that added by the fuzzyrules improves the performance of the controller, while theneural network produces the required control signal. The newcontroller can achieve an improvement of the ride comfortwith a reasonable value of power consumption. Themathematical analysis of the mechanical power used by themodel is focused on the average and the RMS of the powersupplied to the system, regardless of the frequency content ofthe vibration signal. The simulation results which are verifiedby a practical examples of road profiles, demonstrate theefficacy of the proposed controller.