In view of the complex characteristics of the main steam temperature loop in thermal power plants, such as large inertia, large delay, nonlinearity and time-varying, and the difficulty of PID self-tuning, a parallel two-degree-of-freedom PID control method based on improved genetic algorithm (GA) is proposed. The parameters of the parallel two-degree-of-freedom PID controller are optimized by using the improved genetic algorithm, and it is used in the main steam temperature control system. The simulation results show that compared with other methods, the proposed method has better control effect, fast response, short adjustment time, small overshoot and good robustness, which can meet the field control requirements of main steam temperature control system in thermal power plant.