Font Size: a A A

Research On Turbine Heat Consumption Modeling And Initial Pressure Optimization Based On Backtracking Search Algorithm

Posted on:2021-05-19Degree:MasterType:Thesis
Country:ChinaCandidate:S X ShangFull Text:PDF
GTID:2392330611971420Subject:Engineering
Abstract/Summary:PDF Full Text Request
In recent years,with the rapid development of China's economy,the scope of energy applications continues to expand,and appropriate and reasonable allocation of social resources has become a response strategy actively advocated by the state.However,there are many high-power,large-capacity units that are difficult to operate in variable-load operation for a long time when the thermal power plant participates in the peak shaving of the power grid.This will significantly reduce the thermal economic performance of the unit and violate the concept of high energy efficiency.In order to improve the energy utilization rate of the unit,the main steam pressure of the steam turbine unit is optimized to improve the thermal economic performance index of the unit.The optimization of the main steam pressure makes the unit safe and normal operation.Therefore,this paper takes the research direction from the establishment of heat rate model and the optimization of model parameters.First,research and analyze the Backtracking Search Optimization Algorithm(BSA).In order to improve the algorithm's lack of group directionality and mutation diversity,the algorithm is improved to increase the global optimal individual,divide subgroups,and improve mutation control parameters.In order to reflect the performance of the improved algorithm,it is tested using classic test functions and compared with other optimization algorithms.Simulation results show that the Improved Backtracking Search Optimization Algorithm(I-BSA)has good performance.Optimization capabilities to meet usage needsSecondly,the parameters and activation function parameters in the fast learning network model are optimized,and a new combined model I-BSA-FLN is proposed.Tested on the UCI dataset,the results show that the optimized model works well.Then,using the steam turbine heat rate data set as training data,the I-BSA-FLN model is trained for experiments.The results show that the I-BSA-FLN model has a good tracking ability in predicting the heat rate.Finally,the I-BSA optimization algorithm is used to optimize the main steam pressure,which is the most important factor affecting the heat consumption rate of the steam turbine,to obtain the pressure under various load conditions,and to fit theoptimal pressure curve.Compared with the operating pressure curve given by the manufacturer,the pressure curve obtained through optimization can better guide the safe and economic operation of the steam turbine unit in practice.
Keywords/Search Tags:steam turbine, heat rate, main steam pressure, fast learning network, back search optimization algorithm
PDF Full Text Request
Related items