Steam pressure prediction method and device based on LSTM deep recurrent neural network

Abstract

The invention discloses a steam pressure prediction method and device based on an LSTM deep recurrent neural network, and the method comprises the steps: obtaining an operation parameter matrix through collecting the operation data of a steam boiler system, carrying out the recombination of the operation parameter matrix of the steam boiler system according to an LSTM model, and obtaining a sample set; randomly selecting the sample size in the sample set as a training data set and a verification data set, and constructing an initial steam pressure prediction model based on the LSTM deep recurrent neural network by taking the training data set and the verification data set as input; hyper-parameters in the initial steam pressure prediction model are optimized, the optimized hyper-parameters serve as controlled variables, an LSTM deep recurrent neural network steam pressure prediction model is trained, and a steam pressure dynamic prediction model is obtained; and inputting real-time operation data of the steam boiler system to obtain a steam pressure predicted value. The characteristics of high coupling and large lag of a steam boiler system are overcome, and a prediction model with high applicability and high prediction precision is established.

Description

technical field [0001] The present application relates to the technical field of industrial steam boiler combustion, and in particular to a steam pressure prediction method and device based on an LSTM deep cyclic neural network. Background technique [0002] A steam boiler is a heat exchange equipment that produces steam. It uses the energy released by the combustion of coal, oil, gas, biomass and other fuels, and transfers these energy to water through the heat transfer process, so that the water becomes steam, and the steam is supplied to the industrial production facility. The required heat energy is converted into mechanical energy through steam power engines, or into electrical energy through steam turbine generators, or directly supplied to downstream heat users. Too high steam pressure may lead to safety accidents such as boiler explosion; too low steam pressure will inevitably reduce steam quality; steam pressure must be in a moderate range. Therefore, boiler steam ...

AI Technical Summary

Problems solved by technology

[0004] For this reason, this application provides a steam pressure prediction method and device based on LSTM deep cycle neural network to solve the problems of mutual coupling between various factors affecting steam pressure and large pure lag of the boiler system existing in the prior art

Images