Heat Rate Prediction Model Used in the Thermal Power Plants Based on the Support Vector Regression and Genetic Algorithm

摘要

Heat rate is a key parameter in the thermal power plants. The heat rate not only affects the efficiency of the economics of thermal system, but also the operating of the engineer. Based on heat rate characteristic, a calculation model of steam turbine heat rate is given by using support vector regression (SVR) with SVR model's parameters optimized by genetic algorithm (GA). Data of a 300MW unit is validated by the proposed method. The results show that the SVR model has high prediction accuracy and very strong stability. SVR is an effective method about operating performance of steam turbine and lays the theoretical foundation on the thermal economic performance diagnosis.