电功率设定值优化曲线

AbstractIn order to solve the problem of insufficient output of a nuclear power plant insummer in China,a method for optimizing the output of nuclear power steam turbinebased on LSTM and random forest algorithm is proposed.LSTM can achieveaccurate prediction of seasonal time series.Random forest algorithm is not sensitiveto outliers and has strong generalization ability,which is widely used in classificationand regression problems.LSTM is used to establish a seawater temperature timeseries prediction model,and the random forest algorithm is used to establish aregression model of the relationship between the seawater temperature and electricpower 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 setvalue in the next 24 hours,and the unit operator can adjust the output of the unitaccording to the optimized curve.Through the historical data of the nuclear powerplant,the effectiveness of the method is verified.Based on the Flask framework,thenuclear power unit output optimization WEB application was developed and deployedon 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 willeffectively increase the unit output in summer and improve the unit economy underthe condition that the unit operating parameters are not exceeded.Key words:nuclear power steam turbine;insufficient output;LSTM;time series;random forest;WEB application