In order to improve the control quality of main steam temperature system of thermal power plants

nonlinear PID(NPID) controllers are generally selected. However

there is no systematic method for parameter setting of the NPID controllers. The immune genetics algorithm improved by information entropy(GAIE) is proposed in this study. The GAIE algorithm adds information entropy to the immune genetic algorithm to improve the problem of easy to fall into local optimality and slow optimization of immune genetic algorithm. The collected actual operation data of the power plant is used to identify the main steam temperature system. Then the GAIE algorithm is used to optimize the NPID controller for control based on the transfer function of the identified system. The results of validation and simulation of actual data show that

the output of the GAIE algorithm identification model fits the actual output of the site better

the average precision is 40.18% higher than that of the immune genetic algorithm model

and the optimization speed of model parameters is improved by 86.67%. The control effect of the GAIE algorithm is obviously superior to the conventional PID controller.