Research on Semi-active Air Suspensions of Heavy Trucks Based on a Combination of Machine Learning and Optimal Fuzzy Control

A combination of machine learning (ML) and optimal fuzzy control (OFC) is proposed for the semi-active air suspensions of heavy trucks to further improve ride comfort and road friendliness. To obtain the study aim, a vehicle dynamics model with 10 degrees-of-freedom (10-DOF) is established in the MATLAB/Simulink environment to simulate and calculate the objective functions of the root-mean-square (RMS) acceleration responses of the vertical driver's seat and pitching cab angle and the dynamic load coefficient (DLC) on the wheel axles under various working conditions. Based on the OFC with its control rules optimized by the genetic algorithm (GA) and the data map of the random road surfaces, an ML method of the Adaptive Network-based Fuzzy Inference System (ANFIS) in MATLAB is developed and applied to control the semi-active air suspensions. The research results indicate that the semi-active air suspensions controlled by both the OFC and ML are superior to the exemplar vehicle with a passive air suspension under all the vehicle operating conditions investigated. Particularly, the ML method has an obvious effect on controlling the semi-active air suspensions. The results of the RMS acceleration responses of the vertical driver's seat and pitching cab angle and the DLC on the second wheel axle with ML are greatly reduced by 23.4%, 12.0%, and 10.0% in comparison with the OFC. Therefore, the semi-active air suspensions with the use of ML can further improve the ride comfort and road friendliness of heavy trucks.