用于复杂煤灰熔融特性预测的加权耦合神经网络模型

詹子仪; 黄延凯; 喻鑫; 周子健; 于敦喜; 徐明厚

doi:10.3969/j.issn.1008-0198.2025.06.009

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

用于复杂煤灰熔融特性预测的加权耦合神经网络模型

源网协调与能源转换利用 | 更新时间：2026-02-06

- 用于复杂煤灰熔融特性预测的加权耦合神经网络模型
- Research on Weighted Coupled Neural Network Model for Prediction of Fusibility of Coal Ash with Complex Composition
- 湖南电力 2025年45卷第6期页码：68-75
- 作者机构：
  
  华中科技大学煤燃烧与低碳利用全国重点实验室,湖北,武汉,430074
- 作者简介：
- 基金信息：
  
  国家重点研发计划（2023YFB4102701）;国家自然科学基金项目（52476115）;新疆维吾尔自治区重大科技专项（2024A01005-2）;湖北省中央引导地方科技发展资金（2024CSA088）
- DOI：10.3969/j.issn.1008-0198.2025.06.009
  中图分类号： TK227.1
- 网络首发：2026-01-13，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
詹子仪, 黄延凯, 喻鑫, 周子健, 于敦喜, 徐明厚. 用于复杂煤灰熔融特性预测的加权耦合神经网络模型[J]. 湖南电力, 2025, 45(6): 68-75.

詹子仪, 黄延凯, 喻鑫, et al. Research on Weighted Coupled Neural Network Model for Prediction of Fusibility of Coal Ash with Complex Composition[J]. 2025, 45(6): 68-75.
詹子仪, 黄延凯, 喻鑫, 周子健, 于敦喜, 徐明厚. 用于复杂煤灰熔融特性预测的加权耦合神经网络模型[J]. 湖南电力, 2025, 45(6): 68-75. DOI： 10.3969/j.issn.1008-0198.2025.06.009.

詹子仪, 黄延凯, 喻鑫, et al. Research on Weighted Coupled Neural Network Model for Prediction of Fusibility of Coal Ash with Complex Composition[J]. 2025, 45(6): 68-75. DOI： 10.3969/j.issn.1008-0198.2025.06.009.

摘要

针对常规神经网络预测复杂煤灰熔融特性存在较大误差的问题

提出一种新型加权耦合神经网络（weight coupled neural network

WCN）预测模型。其特征在于

基于煤灰Si-Al-Ca-Fe体系竞争反应机理

对传统前馈神经网络进行改进

将煤灰硅铝比（silica-to-alumina ratio

S/A）和钙铁比（calcium-to-iron ratio

C/F）作为特征项输入权重网络

再与组分网络的输出耦合

使神经网络具有灵活可调的预测权重

从而提高模型适应性和预测精度。对比煤灰软化温度预测结果表明

WCN模型对测试集预测的最大误差低于60 ℃

优于国家标准（GB/T 219—2008）对煤灰熔融特性复现性的要求（80 ℃）;相比常规极端梯度提升算法和反向传播神经网络模型

WCN模型对复杂高碱煤（准东煤）灰的预测精度分别提高了32.8%和83%。研究表明

WCN模型在煤灰适应性和预测精度等方面均有较大提升

具有较好应用价值。

Abstract

To address the significant errors associated with conventional neural network models in predicting the fusibility of coal ash with complex composition

a novel weighted coupled neural network model (WCN) is proposed. It is particularly characterized by the modification of the traditional feedforward neural network based on the competitive reaction mechanisms of the coal ash Si-Al-Ca-Fe systems. Specifically

the silica-to-alumina ratio (S/A) and calcium-to-iron ratio (C/F) of coal ash are incorporated as feature items into a weighted network

whose outputs are then coupled with those of the component network

enabling the neural network to have flexible and adjustable prediction weights

thereby enhancing the model's adaptability and prediction accuracy. Comparison of the prediction results of coal ash softening temperature by different models demonstrates that the maximum errors of the WCN model in the prediction of the test set is below 60 ℃

outperforming the reproducibility requirement (80 ℃) for coal ash fusion characteristics in the Chinese National Standard(GB/T 219—2008). Furthermore

compared to the conventional eXtreme Gradient Boosting(XGBOOST) and back propagation neural network(BPNN) models

the WCN model improves prediction accuracy for complex high-alkali coal(e.g.

Zhundong coal) ash by 32.8% and 83%

respectively. The study shows that the WCN model achieves significant improvements in both coal ash adaptability and prediction accuracy

demonstrating considerable application value.

关键词

Keywords

references

LI X,LI J,WU G G,et al.Clean and efficient utilization of sodium-rich Zhundong coals in China:Behaviors of sodium species during thermal conversion processes[J]. Fuel,2018,218:162-173.

刘涛,李新新,王伟林,等. 煤灰熔融性的影响因素及其调控[J]. 山东科技大学学报(自然科学版),2014,33(4):43-49.

刘硕,杨伏生,张小艳,等. 煤灰熔融温度预测方法研究现状[J]. 洁净煤技术,2016,22(1):60-65.

张德祥,龙永华,高晋生,等. 煤灰中矿物的化学组成与灰熔融性的关系[J]. 华东理工大学学报(自然科学版),2003,29(6):590-594.

郑烨. 准东煤灰熔融特性及掺烧煤矸石的影响机理[D]. 北京:华北电力大学(北京),2021.

AN H Q,LIU Z,SUN K D,et al.A machine learning framework for intelligent prediction of ash fusion temperature characteristics[J]. Fuel,2024,362:130799.

LIANG W,WANG G W,NING X J,et al.Application of BP neural network to the prediction of coal ash melting characteristic temperature[J]. Fuel,2020,260:116324.

LIU X,WANG X Y,GAO Y F,et al.Prediction and optimization of coal ash flow temperature using machine learning approaches[J]. Fuel,2026,404:136115.

CHEN T Q,GUESTRIN C.XGBoost:A scalable tree boosting system[C] //The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco,USA. Association for Computing Machinery,2016:785-794.

张显显,白进,孔令学,等. 高钠煤气化过程中的灰化学研究进展[J]. 洁净煤技术,2023,29(7):110-124.

史永胜,卢红玲. 锅炉掺烧高碱金属煤的试验研究[J]. 华北电力技术,2013(1):39-42.

王云刚,赵钦新,马海东,等. 准东煤灰熔融特性试验研究[J]. 动力工程学报,2013,33(11):841-846.

杨燕梅,张海,张扬,等. Si/Al/Na/Ca对准东煤灰熔融特性的影响[J]. 工程热物理学报,2018,39(8):1858-1863.

孙文娟,梁国治. 矿物组成对淮南煤灰熔融特性的影响及熔融机理[J]. 长春师范大学学报,2021,40(12):69-75.

代百乾,乌晓江,陈玉爽,等. 煤灰熔融行为及其矿物质作用机制的量化研究[J]. 动力工程学报,2014,34(1):70-76.

LI J Z,WANG X Y,WANG B,et al.Effect of silica and alumina on petroleum coke ash fusibility[J]. Energy & Fuels,2017,31(12):13494-13501.

张玉魁,张海霞,朱志平. 淮东煤流化床气化飞灰的理化特性研究[J]. 燃料化学学报,2016,44(3):305-313.

程翼,李寒旭,武成利. 助熔剂对淮南煤灰熔融特性的影响行为研究[J]. 煤炭技术,2005,24(12):90-92.

毛军,徐明厚,李帆,等. 碱性矿物质对煤灰熔融特性影响的研究[J]. 华中科技大学学报(自然科学版),2003,31(4):59-62.

刘薄鉴治,金晶,何翔. 铁含量对准东高铁煤燃烧过程中灰熔融特性与矿物演变的影响[J]. 动力工程学报,2025,45(2):198-204,299.

AHAD N,QADIR J,AHSAN N.Neural networks in wireless networks:techniques,applications and guidelines[J]. Journal of Network and Computer Applications,2016,68:1-27.

ZHANG M,TAO F,ZUO Y,et al.Top ten intelligent algorithms towards smart manufacturing[J]. Journal of Manufacturing Systems,2023,71:158-171.

NIAZKAR M,MENAPACE A,BRENTAN B,et al.Applications of XGBoost in water resources engineering:a systematic literature review(Dec 2018-May 2023)[J]. Environmental Modelling & Software,2024,174:105971.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高压直流输电系统输电电缆的故障定位方法

基于融合模型驱动和数据驱动的电动汽车充电负荷预测

基于jieba中文分词的电力客户精准分类方法

基于分段预测及天气相似日选择的区域电网短期负荷预测方法