Biogeography-based Optimized Adaptive Neuro-Fuzzy Control of a Nonlinear Active Suspension System

This paper presents an optimum network structure based on a BBO tuned adaptive neuro-fuzzy inference system (ANFIS) to control active suspension (ASS). The unsupervised learning via Biogeography-Based Optimization (BBO) algorithm is used train the ANFIS network. optimal proportional-integral-derivative controller LQR method generate training data set. base Fuzzy c-means (FCM) clustering applied approximate relationships between vehicle body (sprung mass) vertical input velocity and actuator output force. optimize fuzzy c means parameters. numerical simulation results showed that proposed optimized BBO-FCMANFIS has better performance as compared with LQR-PID under uncertainties in both of reducing energy consumption suppression vibration sprung mass acceleration, 43% 9.5% reduction, respectively.