NO<sub>x</sub> emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model

QIAN Hong; ZHANG Jun; XU Bangzhi

doi:10.19666/j.rlfd.202212226

English

您当前的位置：

首页 >

文章列表页 >

NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model

Thermal Power Generation Vol. 52, Issue 8, Pages: 137-145(2023)

更新时间：2025-09-28

- NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model
- 作者机构：
  
  1. 上海电力大学自动化工程学院
  2. 上海市电站自动化技术重点实验室
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202212226
  CLC： X773
- Published：2023
- 稿件说明：
移动端阅览
QIAN Hong, ZHANG Jun, XU Bangzhi. NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model[J]. Thermal Power Generation, 2023, 52(8): 137-145.
DOI：

QIAN Hong, ZHANG Jun, XU Bangzhi. NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model[J]. Thermal Power Generation, 2023, 52(8): 137-145. DOI： 10.19666/j.rlfd.202212226.

摘要

针对当前燃煤-煤气锅炉煤气掺烧量不确定情况下对NO_x排放量预测不够准确的问题，提出一种基于注意力机制组合在线预测模型。首先，通过最大信息系数法与皮尔逊相关系数法相结合确定模型的特征变量；其次，对线性相关特征变量采用滑动时间窗口在线构建向量自回归模型（VAR），实现多维时序线性相关变量输入下对NO_x排放量的预测，而对于非线性相关特征变量通过构建在线循环极限学习机（OR-ELM）模型在线学习非线性相关变量在时序上的关系对NO_x排放量进行预测；最后，采用注意力机制对2个预测模型进行动态赋权以实现趋势预测。采用实际运行数据对该模型验证，结果表明，所构建的VAROR-ELM组合在线预测模型能够准确预测10min后的NO_x排放量变化趋势，并在不同负荷段对NO_x质量浓度进行准确预测；综合预测精度及预测时间，所构建的组合预测模型比其他单一预测模型的预测效果更好。

Abstract

Aiming at the problem of inaccurate prediction of NO_x emission concentration when the current coal-gas boiler gas mixture is uncertain and changing

a combined online prediction method based on attention mechanism is proposed. First

the characteristic variables of the model are determined by combining the maximum information coefficient method with the Pearson correlation coefficient method; Secondly

vector autoregressive(VAR) model is constructed online with sliding time window for linearly correlated characteristic variables to realize the prediction of NO_x emission concentration under the input of multi-dimensional time series linear correlation variables For non-linear-related feature variables

the relationship between NO_x emission concentration is predicted by constructing an online Recurrent extreme learning machine(OR-ELM) model online learning. Finally

Attention Mechanism(AM) is used to dynamically weight the two forecasting models to achieve trend forecasting. Through field data verification

it shows that the VAR-OR-ELM combined online prediction model constructed in this paper can accurately predict the variation trend of NO_x emission concentration after 10 minutes. Combining prediction accuracy and prediction time

the combined prediction model is better than other single prediction models.

关键词

Keywords

references

Views

289

下载量

CSCD

Alert me when the article has been cited

提交

Publicity Resources

Online learning model of backpressure prediction for direct air-cooled unit under flexible peak regulation

Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism

Real-time prediction model of feed coal quantity for boilers based on power to coal coefficient

Real tests on NO_x emission distribution characteristics of a supercritical 600 MW CFB boiler

Effect of blending CO₂ into air on combustion characteristics of CH₄

Related Author

WEN Wentao

YANG Zhenhua

QI Xiangmeng

DENG Hui

LI Yachao

LIU Haoyu

XU Haokang

GUAN Yuhan

Related Institution

Jinan University Energy and Power Research Center

华北电力大学能源动力与机械工程学院

College of Energy, Power and Mechanical Engineering, North China Electric Power University

National Energy Investment Group Co., Ltd

Shenhua Group Circulating Fluidized Bed Technology Research and Development Center

AI问答

⁰

NOx emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model

DOI：10.19666/j.rlfd.202212226

摘要

Abstract

关键词

Keywords

references

NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model