Research On Optimization Of Nuclear Power Unit Output Based On Machine Learning Algorithm

As the capacity of nuclear power plants in China continues to increase,improving the economic efficiency of nuclear power plant unit has become a general demand.In order to solve the problem of insufficient output of a nuclear power plant in summer in China,a method for optimizing the output of nuclear power steam turbine based on LSTM and random forest algorithm is proposed.LSTM can achieve accurate prediction of seasonal time series.Random forest algorithm is not sensitive to outliers and has strong generalization ability,which is widely used in classification and regression problems.LSTM is used to establish a seawater temperature time series prediction model,and the random forest algorithm is used to establish a regression model of the relationship between the seawater temperature and electric power set value on the opening of the high-pressure regulating valve and heat power.The two models are combined to obtain the optimized curve of the electric power set value in the next 24 hours,and the unit operators can adjust the output of the unit according to the optimized curve.Through the historical data of the nuclear power plant,the effectiveness of the method is verified.Taking August 7,2019 as an example,if the unit operators set the unit output according to the electric power set value optimization curve,the unit output on that day will increase by 8.98 MW on average,which can generate approximately215000 kilowatt-hours of electricity.Based on the Flask framework,the nuclear power unit output optimization WEB application was developed and deployed on the nuclear power plant’s LAN through the method of Flask+Tornado+Nginx.Using the electric power set value optimization curve to set the unit output will effectively increase the unit output in summer and improve the unit economy under the condition that the unit operating parameters are not exceeded.