To address the problem that the parameters of the self-disturbance rejection control with piston displacement feedback are hardly adjustable and easily fall into local optimum, an improved genetic algorithm is proposed to optimize the parameters of the self-disturbance suppression controller in the electro-hydraulic servo position control system. The method first establishes the second-order closed-loop state space equations based on the valve-controlled electro-hydraulic cylinder mechanism model. The self-disturbance suppression controller is improved by introducing parameter perturbations and external disturbances, and an extended state observer is established by using a combination of linear and nonlinear fast-tracking differentiators as well as an improved sliding mode control law. In the process of optimizing the parameters of the self-disturbance rejection controller, the dynamic characteristics of the controller and the input constraints of the system are taken as the optimization objectives. The simulation experiment results indicate that the proposed method can effectively improve the control accuracy, stability, and anti-interference performance of the displacement feedback-based active disturbance suppression controller. The study provides a reference for further improving the control performance of electro-hydraulic servo systems.