基于机器学习的一体式电制热储热装置能效测试方法

doi:10.3969/j.issn.2097-0706.2026.04.003

摘要/Abstract

摘要：

“双碳”目标下，电供暖技术凭借其清洁性与灵活性实现了规模化发展，一体式电制热储热装置的准确检测与评价是高效利用该技术的关键，但瞬时状态不稳定以及供水温度和电功率周期性波动导致现有测试方法不适用于此类设备检测。提出了一种适用于一体式电制热储热装置的能效测评方法，制定了试验准备、预试验及试验检测3个阶段的检测方法及流程。基于试验检测阶段的监测数据，结合机器学习模型，实现对电制热装置全运行过程及全场景稳定状态的能效评价。研究结果表明，相比于国标规定的检测方法，该方法能够准确反映一体式电锅炉的能效水平，检测得到的多个稳定阶段效率测试结果准确性提高了5.74百分点，降低了电制热储热装置运行时瞬态不稳定及供水温度、电功率周期性波动对测试结果的不利影响，可用于其他电制热装置的检测与能效评价。

关键词: “双碳”目标, 电供暖, 一体式电制热储热装置, 机器学习, 能效评价

Abstract:

Under the dual carbon target， electric heating technology has achieved large-scale applications by virtue of its cleanliness and flexibility. Accurate detection and evaluation for the electric heating systems integrated heat storage device is the key to the efficient use of this technology. However， existing test methods are unsuitable for the detecting the systems due to instantaneous state instability and periodic fluctuations of water-supply temperature and electric power. An energy efficiency evaluation method suitable for electric heating-heat storage integrated systems is proposed， which is comprised of three processes： experimental preparation stage， pre-experimentation stage and experimental testing stage. Based on the monitoring data from the experimental testing stage， the energy efficiency evaluation executed on the electric heating device under whole-process and all-scenario steady states is realized by the machine learning model. The simulation results show that the proposed method can reflect the energy efficiency of the integrated system accurately， with an evaluation accuracy rate 5.74 percentage points higher than that obtained by the detection method specified in the national standard. And the proposed method can reduce the negative influence of transient instability and periodic fluctuations of water-supply temperature and electric power on the evaluation test for the integrated system， and can be applied to other electric heating devices for energy efficiency evaluation.

Key words: dual carbon target, electric heating, electric heating-heat storage integrated system, machine learning, energy efficiency evaluation

中图分类号:

TK01：TM924

李克成, 金璐, 成岭, 钟鸣, 贾欣怡. 基于机器学习的一体式电制热储热装置能效测试方法[J]. 综合智慧能源, 2026, 48(4): 19-26.

LI Kecheng, JIN Lu, CHENG Ling, ZHONG Ming, JIA Xinyi. Evaluation method for electric heating-heat storage integrated systems based on machine learning[J]. Integrated Intelligent Energy, 2026, 48(4): 19-26.

图/表 11

图1

图2

图3

图4

表1

表2

图5

图6

图7

图8

图9

参考文献 20

[1]	张雪, 崔向波. 城市大气环境PM2.5浓度变化特征及治理研究[J]. 资源节约与环保, 2022(3): 45-48.
	ZHANG Xue, CUI Xiangbo. Study on variation characteristics and control of PM2.5 concentration in urban atmospheric environment[J]. Resources Economization & Environmental, 2022(3): 45-48.
[2]	张赞助. 超临界直流锅炉的控制技术分析与研究[J]. 科技创新与应用, 2020(23): 156-157.
	ZHANG Zanzhu. Analysis and research on control technology of supercritical direct current boiler[J]. Technology Innovation and Application, 2020(23):156-157.
[3]	李潇. 蓄热电锅炉参与调峰的荷源优化控制策略[D]. 北京: 华北电力大学, 2021.
	LI Xiao. Load source optimization control strategy of thermal storage electric boiler participating in peak regulation[D]. Beijing: North China Electric Power University, 2021.
[4]	刘媛媛, 刘芳芳, 贾天翔, 等. 商住园区综合能源供暖(冷)系统的方案设计及运行经济性研究[J]. 综合智慧能源, 2023, 45(12): 20-28. doi: 10.3969/j.issn.2097-0706.2023.12.003
	LIU Yuanyuan, LIU Fangfang, JIA Tianxiang, et al. Design of the integrated energy heating(cooling) system for a commercial and residential park and its economy analysis[J]. Integrated Intelligent Energy, 2023, 45(12): 20-28. doi: 10.3969/j.issn.2097-0706.2023.12.003
[5]	湛金. 某矿山企业蓄热式电锅炉蓄热方式比选[J]. 世界有色金属, 2020(13):209-210.
	ZHAN Jin. Selection of Heat storage method for Regenerative electric boiler in a mining enterprise[J]. World Nonferrous Metals, 2020(13):209-210.
[6]	殷仁豪, 卢海勇, 王鹏. 电蓄热锅炉集中供暖技术研究[J]. 上海节能, 2020(7):776-783.
	YIN Renhao, LU Haiyong, WANG Peng. Research on central heating technology of electric heat storage boiler[J]. Shanghai Energy Saving, 2020(7):776-783.
[7]	郝巍, 李劲锋, 董泽源, 等. 基于柔性负荷聚合的多方协作机制电采暖项目经济性分析[J]. 电力需求侧管理, 2022, 24(2):80-85.
	HAO Wei, LI Jinfeng, DONG Zeyuan, et al. Economic analysis of electric heating projects under multi-party cooperation mechanism based on flexible load aggregation[J]. Power Demand Side Management, 2022, 24(2):80-85.
[8]	王哲, 程钢, 邢作霞, 等. 基于MPC的光电热联合系统建模与控制优化[J]. 综合智慧能源, 2024, 46(7): 21-28. doi: 10.3969/j.issn.2097-0706.2024.07.003
	WANG Zhe, CHENG Gang, XING Zuoxia, et al. Modeling and control optimization of photovoltaic-thermal heating system based on MPC[J]. Integrated Intelligent Energy, 2024, 46(7): 21-28. doi: 10.3969/j.issn.2097-0706.2024.07.003
[9]	许佳孟, 毛凌波, 黄金, 等. 电制热高温相变储热装置的蓄放热性能研究[J]. 太阳能学报, 2023, 44(8):39-44. doi: 10.19912/j.0254-0096.tynxb.2022-0597
	XU Jiameng, MAO Lingbo, HUANG Jin. et al. Study on heat storage and release performance of high temperature phase change heat storage device for electric heating[J]. Acta Energiae Solaris Sinica, 2023, 44(8):39-44. doi: 10.19912/j.0254-0096.tynxb.2022-0597
[10]	史明明, 朱睿, 刘瑞煌. 交直流电力系统与供热系统联合经济调度[J]. 综合智慧能源, 2024, 46(4): 10-16. doi: 10.3969/j.issn.2097-0706.2024.04.002
	SHI Mingming, ZHU Rui, LIU Ruihuang. Joint economic dispatch of an AC/DC power system and a heating system[J]. Integrated Intelligent Energy, 2024, 46(4): 10-16. doi: 10.3969/j.issn.2097-0706.2024.04.002
[11]	陈璟, 薛可历, 杨艺伟, 等. 固体蓄热式电锅炉选型分析[J]. 区域供热, 2022(4):65-68.
	CHEN Jing, XUE Keli, YANG Yiwen, et al. Type selection analysis of solid regenerative electric boiler[J]. District Heating, 2022(4):65-68.
[12]	江洪明, 郭捷昕. 卧式内燃锅炉的能效测试和节能诊断[J]. 节能, 2018, 37(10):122-124.
	JIANG Hongming, GUO Jiexin. Energy efficiency test and energy saving diagnosis of horizontal internal combustion boiler[J]. Energy Conservation, 2018, 37(10): 122-124.
[13]	袁静, 王选, 马骊, 等. 基于既有农村住宅能效提升的常规清洁取暖方式经济性分析[J]. 暖通空调, 2024, 54(3): 19-23.
	YUAN Jing, WANG Xuan, MA Li, et al. Economic analysis of conventional clean heating methods based on energy efficiency improvement in existing rural houses[J]. Heating Ventilating & Air Conditioning, 2024, 54(3):19-23.
[14]	张利伟, 王华润, 严干贵, 等. 考虑传热不一致性的蓄热式电锅炉负荷建模[J]. 电力系统自动化, 2023, 47(13):40-46.
	ZHANG Liwei, WANG Huarun, YAN Gangui, et al. Load modeling of regenerative electric boiler considering heat transfer inconsistency[J]. Automation of Electric Power Systems, 2023, 47(13):40-46.
[15]	江川. DCS在锅炉能效分析上的应用[J]. 科技创新与应用, 2019(3):180-181.
	JIANG Chuan. Application of DCS in boiler energy efficiency analysis[J]. Technology Innovation and Application, 2019(3): 180-181.
[16]	JIN W C, ATKINSON T A, DOUGHTY C, et al. Machine-learning-assisted high-temperature reservoir thermal energy storage optimization[J]. Renewable Energy, 2022, 197:384-397. doi: 10.1016/j.renene.2022.07.118
[17]	COONEY A Y, CAREY V P. Adaptive machine learning based control of multi-temperature, multi-module latent thermal storage ensembles[J]. Applied Thermal Engineering, 2024, 236(PB).
[18]	付颜, 潘蕾, 王钱超. 基于机器学习的锅炉送风控制系统仿真及优化[J]. 工程热物理学报, 2022, 43(7): 1777-1782.
	FU Yan, PAN Lei, WANG Qianchao. Simulation and optimization of boiler air supply control system based on machine learning[J]. Journal of Engineering Thermophysics, 2022, 43(7): 1777-1782.
[19]	卞韶帅, 刘凌, 费章胜, 等. 电站锅炉智能燃烧优化基础技术的研究与应用[J]. 电力与能源, 2024, 45(1): 90-94,106.
	BIAN Shaoshuai, LIU Ling, FEI Zhangsheng, et al. Research and application of intelligent combustion optimization basic technology for power plant boilers[J]. Power & Energy, 2024, 45(1): 90-94,106.
[20]	刘阳. 融合热负荷预测模型的相变储热供暖系统运行优化研究[D]. 天津: 天津大学, 2021.
	LIU Yang. Research on operation optimization of phase change thermal storage heating system with integrated heat load prediction model[D]. Tianjin: Tianjin University, 2021.

参数	数值
电制热装置回水温度${t}_{\mathrm{i}\mathrm{n}}^{0}$/℃	40
电制热装置试验功率${P}^{0}$/kW	60
循环水流量${q}_{m}^{0}$/(kg·s^-1)	7.2
电压${V}^{0}$/V	380
频率${f}^{0}$/Hz	50
试验环境温度${t}_{\mathrm{e}\mathrm{n}\mathrm{v}}^{0}$/℃	25
试验环境湿度${H}_{\mathrm{e}\mathrm{n}\mathrm{v}}^{0}$/%	50
${t}_{1}^{0}$/h	1.5
${t}_{2}^{0}$/h	1.0
${t}_{3}^{0}$/h	4.0

方法	时间（2028-11-23）	总热量/MJ	总电量/(kW·h)	效率/%	效率偏差/百分点
本文	20:00—21:00	70.52	21.34	91.76	0.47
本文	21:00—22:00	68.87	20.95	91.29	0.47
国标	20:00—21:00	66.89	21.29	87.29	6.21
国标	21:00—22:00	63.35	18.82	93.50	6.21