Main Steam Temperature Prediction for Waste Incinerator Based on IGRA and CNN-LSTM

WANG Yinsong; ZHANG Ju

doi:10.19805/j.cnki.jcspe.2025.240374

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Main Steam Temperature Prediction for Waste Incinerator Based on IGRA and CNN-LSTM

更新时间：2026-10-10

- Main Steam Temperature Prediction for Waste Incinerator Based on IGRA and CNN-LSTM
- Chinese Journal of Power Engineering Vol. 45, Issue 8, Pages: 1308-1318(2025)
- 作者机构：
  
  1. 华北电力大学自动化系,河北,保定,071003
  2. 保定市综合能源系统状态检测与优化调控重点实验室,河北,保定,071003
  3. 河北省发电过程仿真与优化控制技术创新中心,河北,保定,071003
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.240374
  CLC：
- Online First：12 August 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
王印松,张炬. 基于IGRA和CNN-LSTM的垃圾焚烧炉主蒸汽温度预测动力工程学报, 2025, 45(8): 1308-1318 https://doi.

org/10.19805/j.cnki.jcspe.2025.240374
王印松,张炬. 基于IGRA和CNN-LSTM的垃圾焚烧炉主蒸汽温度预测动力工程学报, 2025, 45(8): 1308-1318 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240374.

org/10.19805/j.cnki.jcspe.2025.240374 DOI：

摘要

为了解决传统建模方法在建立焚烧炉主蒸汽温度预测模型时预测精度不高的问题

提出了一种基于改进的灰色关联分析(IGRA)和卷积-长短期记忆(CNN-LSTM)神经网络的垃圾焚烧炉主蒸汽温度预测方法。首先

使用IGRA筛选出与主蒸汽温度关联程度高的分布式控制系统(DCS)变量作为输入;其次

采用主成分分析(PCA)方法提取包含焚烧炉燃烧图像绝大部分信息的主成分特征并将其作为输入;然后

基于IGRA和粒子群优化(PSO)算法

估计出输入变量与主蒸汽温度之间的迟延向量并进行了时延补偿;最后

构建了由DCS变量和图像特征组成的时序矩阵作为输入变量的CNN-LSTM模型

实现了对主蒸汽温度未来6 min内变化趋势的预测。结果表明:相较于已有的主蒸汽温度预测模型

本文所提出模型的平均绝对误差

降低了13.07%

均方根误差

MSE

降低了13.89%

决定系数

提升了13.08%。

Abstract

In order to solve the problem of low prediction accuracy of traditional modeling methods in establishing a prediction model for the main steam temperature (MST) of incinerators

a waste incinerator MST prediction method based on improved gray relevance analysis (IGRA) and convolutional-long short-term memory (CNN-LSTM) neural network was proposed. Firstly

DCS variables with high correlation degree with MST were selected by IGRA. Secondly

principal component analysis (PCA) was applied to extract principal component features containing most of the information of the incinerator combustion image. Then

based on IGRA and particle swarm optimization

(PSO) algorithms

the delay between DCS parameters and the MST was estimated and compensated. Finally

a CNN-LSTM model with the input of time series matrix composed of DCS variables and image features was constructed to predict the change trend of MST in the next 6 minutes. Results show that compared with the existing MST prediction model

the proposed model reduces the mean absolute error

by 13.07%

reduces the root mean square error

MSE

by 13.89%

and improves the determination coefficient

by 13.08%.

关键词

Keywords

references

TANG Ling, GUO Jing, WAN Ruxing, et al. Air pollutant emissions and reduction potentials from municipal solid waste incineration in China[J]. Environmental Pollution, 2023, 319: 121021.

杨春来, 袁晓磊, 殷喆, 等. 考虑时延特性优化的燃煤锅炉主蒸汽温度预测模型[J]. 热力发电, 2022, 51(8): 124-129. YANG Chunlai, YUAN Xiaolei, YIN Zhe, et al. Prediction model of main steam temperature of coal-fired boiler considering time delay characteristic optimization[J]. Thermal Power Generation, 2022, 51(8): 124-129.

曹振乾, 印江, 张津华, 等. 基于改进粒子群优化的主蒸汽温度模糊串级控制[J]. 控制工程, 2022, 29(4): 699-706. CAO Zhenqian, YIN Jiang, ZHANG Jinhua, et al. Fuzzy cascade control of main steam temperature based on improved particle swarm optimization[J]. Control Engineering of China, 2022, 29(4): 699-706.

赵征, 王金, 周孜钰, 等. 基于ISSA-ELM的垃圾发电厂焚烧过程建模方法研究[J]. 动力工程学报, 2023, 43(12): 1649-1656. ZHAO Zheng, WANG Jin, ZHOU Ziyu, et al. Research on modelling method of the incineration process in waste-to-energy power plant based on ISSA-ELM[J]. Journal of Chinese Society of Power Engineering, 2023, 43(12): 1649-1656.

HE Haijun, MENG Xi, TANG Jian, et al. A novel self-organizing TS fuzzy neural network for furnace temperature prediction in MSWI process[J]. Neural Computing and Applications, 2022, 34(12): 9759-9776.

相明辉, 梁占伟, 孙贻超, 等. 基于BP神经网络的燃煤锅炉内H 2 S质量浓度建模预测[J ] . 动力工程学报, 2020, 40(6): 433-439. XIANG Minghui, LINAG Zhanwei, SUN Yichao, et al. Modeling and prediction of H 2 S concentration in a coal-fired boiler based on BP neural network[J ] . Journal of Chinese Society of Power Engineering, 2020, 40(6): 433-439.

BAI Baogang, BAI Yuhe, WANG Guoqing, et al. ANN/GA-ANN modeling study on operating parameter prediction for waste-to-energy plant[J]. Biomass Conversion and Biorefinery, 2024, 14(3): 4283-4298.

王煜伟, 田宏伟, 秦永新, 等. 基于火焰图像和卷积稀疏自编码的燃烧工况监测[J]. 动力工程学报, 2020, 40(9): 713-719. WANG Yuwei, TIAN Hongwei, QIN Yongxin, et al. Combustion condition monitoring based on flame imaging and convolutional sparse auto encoder[J]. Journal of Chinese Society of Power Engineering, 2020, 40(9): 713-719.

艾徐华. 基于炉膛火焰图像的锅炉燃烧稳定性判别[D]. 北京: 华北电力大学, 2019.

GOLGIYAZ S, TALU M F, ONAT C. Artificial neural network regression model to predict flue gas temperature and emissions with the spectral norm of flame image[J]. Fuel, 2019, 255: 115827.

TTH P, GARAMI A, CSORDS B. Image-based deep neural network prediction of the heat output of a step-grate biomass boiler[J]. Applied Energy, 2017, 200: 155-169.

HU Qinxuan, LONG Jisheng, WANG Shoukang, et al. A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction[J]. Journal of Zhejiang University-SCIENCE A, 2021, 22(10): 777-791.

王印松, 雷玉. 基于DCS数据和燃烧图像的垃圾焚烧炉主蒸汽温度预测[J]. 中国电机工程学报, 2023, 43(22): 8790-8800. WANG Yinsong, LEI Yu. Prediction of main steam temperature of waste incinerator based on DCS data and combustion image[J]. Proceedings of the CSEE, 2023, 43(22): 8790-8800.

谭学瑞, 邓聚龙. 灰色关联分析; 多因素统计分析新方法[J]. 统计研究, 1995(3): 46-48. TAN Xuerui, DENG Julong. Grey correlation analysis: a new method of multi-factor statistical analysis[J]. Statistical Research, 1995(3): 46-48.

SPEARMAN C. The proof and measurement of association between two things[J]. The American Journal of Psychology, 1904, 15(1): 72-101.

郑屹. 基于模糊聚类的图像分割算法研究[D]. 成都: 电子科技大学, 2022.

张婧, 刘倩. 主成分分析阈值选择差异性分析研究[J]. 数据采集与处理, 2022, 37(5): 1012-1017. ZHANG Jing, LIU Qian. Difference analysis research of threshold selection in principal component analysis[J]. Journal of Data Acquisition & Processing, 2022, 37(5): 1012-1017.

HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

YANG Guotian, WANG Yingnan, LI Xinli. Prediction of the NO x emissions from thermal power plant using long-short term memory neural network[J ] . Energy, 2020, 192: 116597.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of NOx Concentration at the SCR Inlet Based on Improved LSTM with Attention Mechanism

Dynamic Modeling of SNCR Denitrification System for Waste Incinerators Based on BKA-Transformer-BiGRU

Gas-Solid Two-phase Flow Detection Method Based on Improved MobileViT

Research on Optimal Scheduling Method for Source-Grid- Load-Storage Systems Considering Electro-Thermal Load Demands in Industrial Parks

Research on Trading Decision of Wind-Photovoltaic-Gas Combined System Participating in Day-ahead and Real-time Markets Considering Wind and Photovoltaic Uncertainty

Related Author

ZHAO Xudong

LI Jun

WANG Lin

GAO Lin

GONG Linjuan

GAO Yixuan

LIANG Yongji

WANG Wenyu

Related Institution

Huaneng Tongchuan Zhaojin Coal & Electricity Co., Ltd.

School of Economics and Management, Beijing Jiaotong University (Weihai)

National Key Laboratory of High-Efficiency Flexible Coal Power Generation and Carbon Capture Utilization and Storage

Xi'an Thermal Power Research Institute Co., LTD

Baoding Key Laboratory of Integrated Energy System State Detection and Optimized Regulation

AI问答

⁰