The belt conveyor is the main transport equipments in coal field, and its controllable drive system directly impacts on the running safety reliability and cost in coal production. Starting speed is unsmoothed in the traditional electrical drive system, which causes the belt off tracking or split and even safety accident. Therefore it is theory and practical significant to introduce a novel direct torque control (DTC) system of AC machine to the belt conveyor for solving the problem in coal mine. In allusion to the optimization of PID parameters in the speed regulators of the belt conveyor, the paper presents the improved genetic algorithm based on genetic algorithms and taboo search for the design of variable parameters of PID controller, and its ability of stronger climbing and faster finding the global optimum results are verified through the De Jong function. Compared with the traditional means, the rise time of the suggested system is faster, overshoot and regulating time is shorter, anti-disturbance is stronger, robust is better. So the optimization performance of control system is improved greatly.