To improve the robustness and control accuracy of the controlled system, an adaptive control algorithm based on extreme learning machine is proposed for nonlinear systems with control saturation constraints and internal and external parameter perturbations. For nonlinear systems with control saturation constraints, the nonlinear control saturation constraints are transformed into conventional control inputs based on the designed auxiliary functions, which effectively reduces the difficulty of controller design. In order to improve the estimation accuracy and speed of the internal and external parameter perturbations, an adaptive control algorithm based on the Extreme Learning Machine (ELM) is constructed by approximating the synthesis term of the internal and external parameter perturbations. The global asymptotic stability of the closed-loop system is theoretically proved. Compared with the adaptive sliding mode controller, the simulation results show that the proposed controller has better performance in total control torque energy consumption and system output convergence trajectory.