Soft computing technique for developing turbine cycle model of Chinshan Nuclear Power Plant Unit 2

Abstract The objective of this study is to develop a turbine cycle model using the adaptive neural-fuzzy inference system (ANFIS) to estimate the turbine-generator output for the Chinshan Nuclear Power Plant (NPP) owned by Taiwan Power Company. The plant operating data was verified using a linear regression model with a corresponding 95% confidence interval for the operating data. In this study, the key parameters were selected as inputs for the neuro-fuzzy based turbine cycle model. After training and validating with key parameters, including main steam to turbine pressure, condenser backpressure, feedwater flow rate, and final feedwater temperature, the proposed model was used to estimate the turbine-generator output. The effectiveness of the proposed ANFIS based turbine cycle model was demonstrated by using plant operating data obtained from the Chinshan NPP Unit 2. The results show that this neuro-fuzzy based turbine cycle model can be used to accurately estimate the turbine-generator output. In addition, a linear multiregression based turbine cycle model was also developed by using the same parameters in order to compare the performance of the ANFIS based turbine cycle model. The results show that the proposed neuro-fuzzy based turbine cycle model is capable of accurately estimating turbine-generator output and providing more reliable results than the multiregression based turbine cycle model, with regard to estimation accuracy and clearly defined trends. The results of this study also provide an alternative approach to evaluating the thermal performance of nuclear power plants.