At present, electromechanical actuator is very popular in the industrial field because of environmental protection, energy saving and high efficiency. At the same time, it also puts forward higher requirements for its reliability. In this paper, a fault tolerant nonsingular terminal sliding mode control method for electromechanical system based on support vector machine (SVM) is proposed. SVM is designed to estimate the possible faults in the system by off-line learning from large sample data with gradient descent method. The estimation is used to compensate the possible fault with feedforward cancellation technique in the proposed controller. An observer is designed to estimate the system states to make fault detection and reconstruct the controller when something is wrong in electromechanical system. A nonsingular terminal sliding mode surface is designed, and Lyapunov theorem is used to derive a parameter adaptation law for handling the parametric uncertainty and a nonsingular terminal sliding mode control law. It is guaranteed the proposed controller can achieve bounded stability. Extensive comparative simulation and experimental results illustrate the effectiveness and advancement of the proposed controller compared with several other main-stream controllers.