1. Prediction model of the NOx emissions based on long short-time memory neural network
- Author
-
Hu Hongli and Liu Qing
- Subjects
Artificial neural network ,business.industry ,Computer science ,Deep learning ,Boiler (power generation) ,Thermal power station ,Atmospheric model ,Combustion ,Automotive engineering ,Electricity generation ,Artificial intelligence ,Time series ,business ,Physics::Atmospheric and Oceanic Physics ,NOx - Abstract
In this paper, the combustion process parameters of 330MW coal-fired boiler are taken as the research object. In view of the massive system data of thermal power plant, the multivariable mutual characteristics of the coal-fired boiler and the DCS stores a dynamic, high-dimensional and massive time series data. Time series forecasting method is introduced into NOx forecasting of thermal power plant in this paper. And a NOx emission forecasting model based on long short-time memory neural network is designed by using deep learning method. The research results show that LSTM can deal with NOx emissions of thermal power units very well.
- Published
- 2020
- Full Text
- View/download PDF