Intelligent Compensation for the Set Values of PID Controllers to Improve Boiler Superheated Steam Temperature Control

Superheated steam temperature (SST) is a very important control parameter during the boiler operation. Because of the non-linearity, large-inertia and long-delay characteristics of the superheater system, cascade PID control scheme is widely adopted for water-spray desuperheating system control. Even so, when the unit load changes greatly and frequently in participating in peak load regulation under automatic generation control (AGC), with uncertain disturbances including changing coal quality, various furnace wind distribution, the cascade PID control with fixed parameters is often unable to achieve desired SST control effect. However, online tuning of PID parameters is time-consuming, laborious and difficult to realize in actual operation. Therefore, a dynamic optimization compensation strategy, which includes both feedforward compensation based on neural network SST prediction model and control error feedback compensation, is designed for the set values of PID controllers on the top level of the steam temperature control loop, on the premise of not changing the original steam temperature control logic and PID parameters. Control simulation experiments under different load changing conditions are carried out with the full-scope simulator of a 600-MW supercritical power unit. It is shown that, compared with the original control, the control quality of the SST is obviously improved with the intelligent set value optimization compensation scheme.