A method and system for predicting gas utilization rate based on hybrid neural network

Abstract

The invention relates to a method and system for predicting gas utilization rate based on a hybrid neural network, and relates to the technical field of gas-steam combined cycle power generation. By obtaining the working condition parameters, gas consumption and compressed air volume corresponding to the power generation of the gas turbine unit in multiple preset periods, and dividing the completed working condition parameters, gas consumption, compressed air volume and corresponding power generation Establish a single neural network model, train the single neural network model with gas consumption as the input, and combine the single neural network models to generate the first hybrid neural network model when the training is completed, and according to the first mixed neural network model in multiple preset periods A hybrid neural network model is combined to generate a second hybrid neural network model, and the gas consumption is used as the input parameter of the second hybrid neural network model to obtain the predicted value of power generation, which improves the accurate prediction of the gas utilization rate, thereby further improving Reliability of gas turbine power plant operation.

Description

technical field [0001] The invention relates to the technical field of gas-steam combined cycle power generation, in particular to a method and system for predicting gas utilization rate based on a hybrid neural network. Background technique [0002] Gas-steam combined cycle generator set (hereinafter referred to as gas turbine) has the advantages of environmental friendliness, high energy utilization rate, large adjustment range, fast adjustment speed and quick load response. Good peak performance and other characteristics. [0003] However, due to the large-scale construction of thermal power and new energy, the peak-shaving capacity of the power grid is improved, and the gas-turbine power plant is mainly positioned to adjust the balance between supply and demand of urban natural gas, optimize the layout of urban power sources, enhance the safe operation of the power grid and natural gas pipeline network, and undertake double peak-shaving The important task: not only adju...

AI Technical Summary

Problems solved by technology

[0005] To this end, the present invention provides a method and system for predicting gas utilization rate based on a hybrid neural network to overcome the problem in the prior art that the gas utilization rate of gas turbine units cannot be accurately predicted, resulting in low reliability of power supply for gas-fired power plants

Images