Plastic profiles are mainly processed by plastic extruders. In order to better solve the problems of hysteresis, high overshoot and low anti-interference ability of the extruder temperature system. First, the process flow and working principle of the extruder are analyzed, and the extruder temperature control system is developed on this basis. The step response curve identification method is used to obtain the system model parameters and establish the mathematical model of the temperature control system. On the basis of previous research on Fuzzy PID control, for the problem of empirical priority of Fuzzy control, a control method based on the improved particle swarm algorithm iteratively solves the key parameters in the Fuzzy PID variational domain algorithm is proposed, and the improved particle swarm Fuzzy PID controller is designed, and the control model is constructed, and the writing and debugging of the control algorithm is completed. Finally, step and interference simulation experiments are designed to simulate and analyze the temperature control effect of traditional PID, Fuzzy PID and improved particle swarm Fuzzy PID on the temperature control system. The results show that: the improved particle swarm Fuzzy PID significantly reduces the maximum overshooting amount, greatly shortens the restoration of steady state time, and at the same time meets the requirements of the system to control the process overshooting amount, has a strong resistance to dryness, and is able to better adapt to the changes in the system control output, which meets the system's demand for temperature control accuracy, stability and rapidity.Keyword:Plastics extrusion machine, Temperature accuracy, Particle swarm optimization, Stability control.