基于结渣因子监测与机器学习的水冷壁精准吹灰算法研究

史建忠; 洪兵; 温小豪; 施子福; 李培; 周永刚

doi:10.19666/j.rlfd.202507080

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于结渣因子监测与机器学习的水冷壁精准吹灰算法研究

更新时间：2026-06-12

- 基于结渣因子监测与机器学习的水冷壁精准吹灰算法研究
- Thermal Power Generation Vol. 55, Issue 4, Pages: 140-147(2026)
- 作者机构：
  
  1. 国能浙江宁海发电有限公司
  2. 浙江大学能源工程学院
  3. 浙江大学能源高效清洁利用全国重点实验室
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202507080
  CLC： TM621.2;TP181
- Published：2026
- 稿件说明：
移动端阅览
[1]史建忠,洪兵,温小豪,等.基于结渣因子监测与机器学习的水冷壁精准吹灰算法研究[J].热力发电,2026,55(04):140-147.
[1]史建忠,洪兵,温小豪,等.基于结渣因子监测与机器学习的水冷壁精准吹灰算法研究[J].热力发电,2026,55(04):140-147. DOI： 10.19666/j.rlfd.202507080.

DOI：10.19666/j.rlfd.202507080.

摘要

【目的】针对传统定时定量吹灰模式易导致水冷壁局部过吹、欠吹的问题，依托有效监测手段开展研究，旨在构建精准吹灰算法。【方法】利用新型水冷壁结渣监测传感器获取水冷壁炉内壁温，对比了3种机器学习方法构建水冷壁洁净状态下的理论炉内壁温模型，提出一种水冷壁结渣因子的计算方法，并据此构建精准吹灰算法，通过实际应用并与原定时定量吹灰模式进行对比，验证了该算法的优化效果。【结果】研究表明：随机森林回归方法建立的理论炉内壁温模型表现最佳，R

为0.92、δ

MSE

为73.77、δ

MAPE

为1.16%；精准吹灰算法实施后效果明显优于原定时定量吹灰模式，吹灰频次大幅度降低，且未造成水冷壁结渣状态恶化。【结论】该算法在保证锅炉运行安全性的前提下，有效降低了吹灰蒸汽消耗量，具有极高的工程应用价值。

Abstract

[Objective

]

Against the problem that the conventional timed and quantitative soot blowing mode is prone to cause local over-blowing and under-blowing of the waterwall

studies are carried out by relying on effective monitoring methods. As slag deposition on waterwall is a key factor affecting the safe and economic operation of thermal power boilers

long-term unresolved local over-blowing or under-blowing will not only accelerate the corrosion and wear of the waterwall

but also increase energy consumption and operational costs of power plants. Therefore

the core goal of this research is to establish a precise soot blowing algorithm to replace the conventional timed and quantitative soot blowing mode and realize adaptive and efficient soot blowing control. [Methods

]

A new type of waterwall slagging monitoring

sensor was used to monitor the in-furnace waterwall surface temperature

which can collect real-time

continuous and high-precision temperature data to lay a reliable foundation for subsequent model construction. Three machine learning methods

including eXtreme gradient boosting(XGBoost)

light gradient boosting machine(LightGBM) and random forest regression(RFR)

were compared to construct theoretical in-furnace waterwall surface temperature models under clean waterwall conditions

and a calculation method for waterwall slagging factor was proposed. On this basis

a precise soot blowing algorithm was established. To verify the optimization effect of this algorithm

a 3-month practical application test was carried out in a 1 030 MW thermal power unit

and the operation data was compared with the original timed and quantitative soot blowing mode. [Results

]

The research shows that the theoretical in-furnace waterwall surface temperature model established by the random forest regression method performed the best

with an R

of 0.92

MSE

of 73.77

and δ

MAPE

of 1.16%. The implementation of the precise soot blowing algorithm is significantly better than the original quantitative soot blowing mode

with a significant reduction in soot blowing frequency and no deterioration of the waterwall slagging state

and the local maximum temperature of the waterwall is controlled within the safe range

avoiding the risk of tube explosion caused by overheating. [Conclusion

]

This algorithm reduces the consumption of soot blowing steam while ensuring the safety of boiler operation

which directly reduces the daily operation cost of the power plant. Moreover

the reduction of soot blowing frequency also reduces the influence of high-temperature steam on the waterwall

effectively extending the service life of the waterwall and reducing the maintenance cost of the boiler. It can be popularized and applied in thermal power plants of different capacities

and has extremely high application value.

关键词

Keywords

references

杨勇平,陈衡,郝俊红,等.“双碳”目标下我国燃煤发电转型升级发展路径[J].中国电机工程学报, 2024,44(17):6900-6910.YANG Yongping, CHEN Heng, HAO Junhong, et al.Development pathways for the transformation and upgrading of China’s coal-fired power generation under the goals of carbon peak and carbon neutrality[J].Proceedings of the CSEE, 2024, 44(17):6900-6910.

卢啸风,李建波,刘卓,等.燃准东煤电站锅炉沾污结渣特性及防治措施研究进展[J].中国电机工程学报,2024, 44(18):7247-7264.LU Xiaofeng, LI Jianbo, LIU Zhuo, et al. Research progress on the characteristics and countermeasures of ash slagging and fouling in boilers burning Zhundong coal[J].Proceedings of the CSEE, 2024, 44(18):7247-7264.

王侨,李雪怡,陈北洋,等.燃煤电厂协同焚烧处置污泥成分影响及结渣特性[J].中国给水排水, 2025,41(12):33-40.WANG Qiao, LI Xueyi, CHEN Beiyang, et al. Influence of sludge composition on co-incineration disposal in coalfired power plant and its slagging characteristics[J]. China Water&Wastewater, 2025, 41(12):33-40.

苗建杰.深度调峰下影响燃煤锅炉安全运行的因素分析[D].保定:华北电力大学, 2023:1.MIAO Jianjie. Analysis of factors affecting the safe operation of coal fired boilers under deep peak load regulation[D]. Baoding:North China Electric Power University, 2023:1.

林东海.电厂锅炉运行中炉内结渣的成因与预防[J].产业与科技论坛, 2015, 14(14):70-71.LIN Donghai. Causes and prevention of slagging in power plant boilers during operation[J]. Industrial&Science Tribune, 2015, 14(14):70-71.

岑可法,樊建人,池作和,等.锅炉和热交换器的积灰、结渣、磨损和腐蚀的防止原理和计算[M].北京:科学出版社, 1994:1.CEN Kefa, FAN Jianren, CHI Zuohe, et al. Principles and calculations for preventing fouling, slagging, wear and corrosion of boilers and heat exchangers[M]. Beijing:Science Press, 1994:1.

李文华,鲍听,沈利,等.管式GGH蒸汽吹灰器改造数值模拟及工程验证[J].热力发电, 2020, 49(3):118-123.LI Wenhua, BAO Ting, SHEN Li, et al. Numerical simulation and practical verification of soot-blowing system retrofitting for tubular gas-gas heater[J]. Thermal Power Generation, 2020, 49(3):118-123.

徐力刚,黄亚继,王健,等.基于炉膛结渣监测模型的吹灰优化[J].东南大学学报(自然科学版), 2018, 48(1):63-70.XU Ligang, HUANG Yaji, WANG Jian, et al. Sootblowing optimization based on model of slagging monitoring around boiler furnace[J]. Journal of Southeast University(Natural Science Edition), 2018, 48(1):63-70.

高峰,隋海涛,石书雨,等.燃煤锅炉水冷壁热流监测在炉膛吹灰优化中的应用研究[J].工程技术研究,2023, 8(19):48-50.GAO Feng, SUI Haitao, SHI Shuyu, et al. Research on the application of water wall heat flux monitoring of coalfired boiler in furnace soot blowing optimization[J].Engineering and Technological Research, 2023, 8(19):48-50.

黄书益,王志超,白彬,等.耦合炉内气相碱金属检测的结渣预报系统研究[J].热力发电, 2023, 52(7):99-105.HUANG Shuyi, WANG Zhichao, BAI Bin, et al.Investigation of slagging prediction system in boilers coupling measurement of gaseous alkali metal in furnace[J]. Thermal Power Generation, 2023, 52(7):99-105.

BILIRGEN H. Slagging in PC boilers and developing mitigation strategies[J]. Fuel, 2014, 115:618-624.

TALER J, TALER D, LUDOWSKI P. Measurements of local heat flux to membrane water walls of combustion chambers[J]. Fuel, 2014, 115:70-83.

SHI Z, LI P, ZHOU Y G, et al. Numerical study and structural optimization of water-wall temperaturemeasurement device for ultra-supercritical boiler[J].Sensors, 2024, 24(18):6038.

马晓春,刘相宏,陈晶,等.火力发电厂分时线性智能吹灰模型的应用[J].发电设备, 2024, 38(1):30-35.MA Xiaochun, LIU Xianghong, CHEN Jing, et al.Application on intelligent soot blowing model of thermal power plant based on time sharing linearity[J]. Power Equipment, 2024, 38(1):30-35.

李孟威.基于神经网络的燃煤电站锅炉受热面积灰预测研究[D].太原:中北大学, 2022:1.LI Mengwei. Research on ash prediction of heating area of coal-fired power station boiler based on neural network[D]. Taiyuan:North University of China, 2022:1.

刘俊,黄亚继,徐文韬,等.基于热损失分析的水冷壁结渣监测和吹灰优化[J].洁净煤技术, 2024, 30(增刊2):501-507.LIU Jun, HUANG Yaji, XU Wentao, et al. Monitoring of slagging and soot-blowing optimization in waterwall based on heat loss analysis[J]. Clean Coal Technology,2024, 30(Suppl.2):501-507.

DHANUSKODI R, KALIAPPAN R, SURESH S, et al.Artificial neural networks model for predicting wall temperature of supercritical boilers[J]. Applied Thermal Engineering, 2015, 90:749-753.

TERUEL E, CORTÉS C, DÍEZ L I, et al. Monitoring and prediction of fouling in coal-fired utility boilers using neural networks[J]. Chemical Engineering Science, 2005,60(18):5035-5048.

PEÑA B, TERUEL E, DÍEZ L I. Towards soot-blowing optimization in superheaters[J]. Applied Thermal Engineering, 2013, 61(2):737-746.

LI P, LI K, ZHOU Y, et al. An effective strategy for monitoring slagging location and severity on the waterwall surface in operation coal-fired boilers[J].Energies, 2023, 16(24):7925.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于神经网络和遗传算法的气膜冷却孔结构优化

基于TrAdaBoost迁移学习的跨仪器LIBS煤质定量分析模型研究

Confidence rule base for soot blowing demand based on production data mining

Prediction of high calorific value for biomass using its proximate analysis result

Application of machine learning in state analysis of power plant equipment

Related Author

李广超

林恒

王昀皓

王建明

秦士伟

邹祥波

饶睦敏

陈公达

Related Institution

沈阳航空航天大学航空发动机学院辽宁省航空推进系统先进测试技术重点实验室

华南理工大学电力学院

广东省能源集团有限公司

广东能源集团科学技术研究院有限公司

Huaneng Shanghai Shidongkou First Power Plant

AI问答

⁰