Modeling of Main Steam Temperature Using an Improved Fuzzy Genetic Algorithm

Main steam temperature is an important parameter in thermal power plants. In order to get a better control effect, an improved fuzzy genetic algorithm (FGA) modelling method is proposed in this paper. Different from traditional identification methods, the improved FGA is more suitable for modeling the dynamic process of the main steam temperature which has the characteristics of strong coupling and nonlinearity. Firstly, to solve the nonlinear problem, a fuzzy thought is introduced to partition the whole operating region into several local regions. Then an improved genetic algorithm (GA) which has better identification capability is proposed to build the linear model in each local region. The nonlinear dynamic process of studied system is elaborately approximated by the fuzzy combination of the local linear models. The simulation results show that the improved FGA can achieve satisfactory effects even in the case of strong coupling and nonlinearity, which provides theory foundation for other control methods.