PSO-optimised adaptive neuro-fuzzy system for magneto-rheological damper modelling

Abstract

This paper presents a novel method for the Non-Parametric Modelling of Magneto-Rheological (MR) Dampers using Adaptive Neuro-Fuzzy (NF) that incorporates a Particle Swarm Optimisation (PSO) method. In this approach, the adaptive NF method is using an adaptive Back-Propagation (BP) learning algorithm, which is used to update the weights in real-time. Initial values of the weights and biases are optimised using PSO in an off-line manner. The experimental data was presented in the time histories of the displacement, the velocity and the force parameters, measured for both constant and variable current settings and at a selected frequency applied to the damper. The model parameters were determined using a set of experimental measurements corresponding to different current constant values. It has been shown that the MR damper model's response via the proposed NF approach is in a good agreement with the MR damper test rig counterpart.