Research on Optimization of Initial Pressure of Steam Turbine Based on Principal Component Analysis

To obtain the optimal main steam pressure of steam turbine under different operating conditions, a heat consumption prediction model based on principal component analysis (PCA) and genetic algorithm-support vector regression (GA-SVR) is established according to the historical operation data. In order to remove the principal components with low contribution rate, PCA is used to reduce the dimension of heat consumption factors. The genetic algorithm with global search ability is used to optimize the parameters of SVR prediction model of heat consumption. Based on the established PCA-GASVR prediction model of heat consumption, main steam pressure is optimized within the feasible range, and the optimized sliding pressure curve is compared with the original one. The results show that heat consumption of the unit decreases under each load after optimization and the operation of steam turbine under optimized sliding pressure curve can improve the unit economy under various operating conditions.