Energy Consumption Analysis And Diagnosis Of Large Ultra Supercritical Condensing Steam Turbine Units

The research on energy consumption analysis and diagnosis of large ultra-supercritical condensing steam turbines is of great significance for mastering the operating characteristics of steam turbine systems and improving the economics of the generating units.In this paper,a 1000 MW ultra-supercritical condensing steam turbine unit is taken as the research object,and the data mining method is applied to analyze and diagnose the heat dissipation characteristics of the steam turbine unit.The main research contents of the thesis include:Firstly,a dynamic working condition library and a steady state working condition library of heat consumption characteristic parameters are established.For the dynamic working condition library,the K-means algorithm is used to explore the relationship between heat consumption rate and load and ambient temperature.The heat dissipation characteristics of steam turbines under different load trends are studied.For the steady state condition library,the K-means algorithm combined with the weighted association algorithm is used to obtain the target value of the heat loss characteristic parameter under typical working conditions,and the target value working condition library under full working condition is established by the least squares fitting method.Secondly,the method of heat loss deviation analysis is established.The MFOA algorithm is proposed and the heat consumption characteristic model of steam turbine unit based on MFOA-GRNN is established.The MFOA algorithm increases the population size and population optimization space based on the traditional FOA algorithm,and improves the performance of the heat loss characteristic model.Based on the MFOA-GRNN heat consumption characteristic model and the target value working condition library,the heat loss deviation analysis model is established,and the model is verified by specific cases.Furthermore,the energy efficiency monitoring and diagnostic methods of the steam turbine unit are studied.In-depth analysis of the characteristics of energy efficiency anomalies,in view of the limitations of heat rate in the evaluation of energy efficiency changes,proposed energy efficiency deviation index,established a multi-parameter estimation model based on MSET algorithm,the actual vector of heat loss characteristic parameters For input,the unit energy efficiency state is determined by comparing the degree of deviation between the model input vector and the estimated vector.Aiming at the abnormal energy efficiency of the unit,a longitudinal calibration method for the unit is proposed,and the changes of heat consumption characteristic parameters at different time periods are compared to analyze the cause of the abnormality.The results of the example verify the reliability of the energy efficiency monitoring model and the benchmarking method.Finally,according to the model built in this paper,the energy analysis and diagnosis software for steam turbines is developed.