Enhancement of travelling comfort using PID based adaptive neuro fuzzy inference system for half car model

In this paper, pioneering Adaptive Neuro Fuzzy Inference System (ANFIS) which is trained with well known traditional Proportional, Integral and Derivative (PID) controller data for Half Car (HC) model is proposed to improve the travelling comfort. The travelling performance is generally assessed at the design stage in automobile industries by simulating the vehicle response to various road excitations. In this work, the disturbance from the road is assumed to be a jerk which represents a sudden shock. Initially a PID controller is designed and tuned to give better response. Secondly the PID tuning parameters are optimized using popular stochastic global optimization technique - Genetic Algorithm (GA) by considering the body acceleration as the Performance Index (PI). At last, an ANFIS which inherits the features of Neural Network (NN) and Fuzzy Logic (FL) is used for control purpose. The modelling of system and simulation with and without controllers are carried out in MATLAB/ Simulink environment. A comparison is made among the responses obtained and it shows that, the system with PID based ANFIS gives significant reduction of the Sprung mass Displacement (SD) and thus improves the travelling comfort.