Application of Fuzzy Control Based on Time Series Prediction Algorithm in Main Steam Temperature System

摘要

The stability of main steam temperature in thermal power plants is especially important for boiler operation. Conventional PID has poor control effect on large delay targets of main steam temperature system in thermal power plants. It is difficult to achieve satisfactory control results. In view of this situation, a PID-based fuzzy controller based on the time series prediction algorithm was designed. The time series algorithm can predict the main steam temperature at the next moment and calculate the input value of the PID fuzzy controller according to the predicted value. The fuzzy control that has the leading characteristic and the regulator advances to reduce the overshoot and adjustment time obviously. The BP neural network algorithm is used to correct the prediction results of the time series algorithm, which makes the algorithm more stable and safe. The simulation and experimental results show that the control effect is significantly better, indicating that this is an effective improvement method, which is obviously superior to the traditional PID control and PID-type fuzzy control.