This article presents a neural algorithm based on Reinforcement Learning for optimising Linear Quadratic Regulator (LQR) creation. The proposed method allows designing such a target function that automatically leads to changes in the quality and resource matrix so that the target LQR regulator achieves the desired performance. The solution’s stability and optimality are the target controller’s responsibility. However, the neural mechanism allows obtaining, without expert knowledge, the appropriate Q and R matrices, which will lead to such a gain matrix that will realise the control that will lead to the desired quality. The presented algorithm was tested for the derived quadrant model of the suspension system. Its application improved user comfort by 67% compared to the passive solution and 14% compared to non-optimised LQR.

This paper focuses on the controller synthesis of the mathematical model developed for the nonlinear system. The considered system is an active wheeled vehicle suspension strut that incorporates an asymmetric electrohydraulic actuator with a single rod. The complexity of this model is heightened due to the asymmetry in piston areas and the nonlinear flow characteristics through the servo valve's throttling orifices, which contrasts with systems using symmetric double-rod actuators. The paper discusses simulation results aimed at linearizing the model. A key distinction from the linearization approach employed for symmetric actuators is the independent linearization of flow rates for each actuator chamber. The synthesis of the control law using the LQR method, after prior linearization of the nonlinear object model, is proposed. The developed controller was applied to operate a nonlinear model of the suspension strut. The paper proves that the controller synthesis conducted in this manner is effective in control systems exhibiting nonlinear characteristics. The performance of the nonlinear active suspension system was evaluated and compared with the experimental results of a passive commercial suspension setup in a laboratory setting.