A Deep Learning Model for NOx Emissions Prediction of a 660 MW Coal-Fired Boiler Considering Multiscale Dynamic Characteristics

A Deep Learning Model for NOx Emissions Prediction of a 660 MW Coal-Fired Boiler Considering Multiscale Dynamic Characteristics

Coal-fired boilers significantly contribute to nitrogen oxides (NOx) emissions, posing critical environmental and health risks. Effective prediction of NOx emissions is essential for optimizing control measures and achieving stringent emission standards. This study applies a Multiscale Graph Convolu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianrong Huang, Yanlong Ji, Haiquan Yu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Atmosphere
Subjects:
NOx emissions prediction
coal-fired boiler
multiscale dynamic characteristics
graph convolutional network
deep learning
Online Access:https://www.mdpi.com/2073-4433/16/5/533
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Coal-fired boilers significantly contribute to nitrogen oxides (NOx) emissions, posing critical environmental and health risks. Effective prediction of NOx emissions is essential for optimizing control measures and achieving stringent emission standards. This study applies a Multiscale Graph Convolutional Network (MSGNet) designed to capture multiscale dynamic relationships among operational parameters of a 660 MW coal-fired boiler. MSGNet employs Fast Fourier Transform (FFT) for automatic periodic pattern recognition, adaptive graph convolution for dynamic inter-variable relationships, and a multihead attention mechanism to assess temporal dependencies comprehensively. Compared with the existing state of the art, the proposed structure achieves a good performance of 2.176 mg/m<sup>3</sup>, 1.652 mg/m<sup>3</sup>, and 0.988 of RMSE, MAE, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>. Experimental evaluations demonstrate that MSGNet achieves superior predictive performance compared with traditional methods such as LSTM, BiLSTM, and GRU. Results underscore MSGNet’s robust accuracy, stability, and generalization capability, highlighting its potential for advanced emission control and environmental management applications in thermal power generation.
ISSN:2073-4433

Similar Items