Research on active disturbance rejection control of hydro-pneumatic suspension of engineering vehicle based on BP neural network

To enhance the ride comfort of the active hydro-pneumatic suspension and ensure system stability during an engineering vehicle’s operation, this study focuses on a dual-chamber hydro-pneumatic spring. It derives the relationship between the nonlinearity of the damping force and stiffness characteristics of the hydro-pneumatic spring and the vehicle body displacement. A control strategy is proposed to optimize the active disturbance rejection controller (ADRC) using a BP neural network. The neural network’s self-learning capability is employed for dynamic tuning of the ADRC parameters, thereby dampening body vibrations and achieving a stable condition. A two-degree-of-freedom dynamics model for a hydro-pneumatic suspension, along with a road input model, is constructed using MATLAB/Simulink. An optimized ADRC, leveraging a BP neural network, is integrated into the hydro-pneumatic suspension system. The vertical acceleration of the vehicle body and the dynamic load of the tire are adopted as evaluation indices. Through simulation analysis, the performance of the optimized algorithm is compared with that of an active suspension system controlled by both passive control and ADRC control. It is demonstrated that this optimization algorithm effectively reduces the vehicle body’s vertical acceleration and the tire’s dynamic load, thereby validating the efficacy of the control strategy.