Abstract: A composite control scheme is proposed using a fuzzy neural network structure to solve the problems of online model identification and online controller design in traditional adaptive control, achieving high-precision output tracking control for uncertain nonlinear systems. Simultaneously, a robust feedback controller is used to ensure the stability of the closed-loop system during the initial learning phase of the fuzzy neural network model. The scheme is applied to an electro-hydraulic position servo system, achieving satisfactory control results . Keywords: Electro-hydraulic position servo system; Fuzzy neural network; Robust control 1 Introduction An electro-hydraulic servo system is a complex nonlinear system with many uncertainties and nonlinear factors, such as the limiting characteristics of the servo valve's zero-bias hysteresis loop, the nonlinear gain of the servo amplifier circuit, and dead zone. These nonlinear factors have a significant impact on the system. Therefore, using a linearized system model often fails to achieve satisfactory control results. Designing a robust controller with good control performance and the ability to eliminate the effects of system uncertainties remains a major concern. This paper proposes a fuzzy neural network parallel self-learning robust tracking control structure and introduces a robust factor to eliminate the impact of uncertainties on the system and enhance the real-time performance of the control. For details, please click: Fuzzy Neural Network Control of Electro-hydraulic Position Servo System