Please wait a minute...
工程设计学报  2025, Vol. 32 Issue (3): 281-295    DOI: 10.3785/j.issn.1006-754X.2025.04.179
机械设计理论与方法     
基于数字孪生的变压器热点温度预测预警技术研究
李佰霖1,2(),马云帆1,2,3,陈昱锐4,罗远林5,褚凡武6,付文龙1,2()
1.三峡大学 电气与新能源学院,湖北 宜昌 443002
2.三峡大学 梯级水电站运行与控制湖北省重点实验室,湖北 宜昌 443002
3.云南电网有限责任公司 楚雄供电局,云南 楚雄 675000
4.国网甘肃省电力公司 兰州;供电公司,甘肃 兰州 730050
5.中国电力建设集团 华东勘测设计研究院有限公司,浙江 杭州 311122
6.中国电力科学研究院 电力工业电气设备质量检验测试中心,湖北 武汉 430074
Research on transformer hotspot temperature prediction and warning technology based on digital twin
Bailin LI1,2(),Yunfan MA1,2,3,Yurui CHEN4,Yuanlin LUO5,Fanwu CHU6,Wenlong FU1,2()
1.College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China
2.Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges University, Yichang 443002, China
3.Chuxiong Power Supply Bureau, Yunnan Power Grid Co. , Ltd. , Chuxiong 675000, China
4.Lanzhou Power Supply Company, State Grid Gansu Electric Power Company, Lanzhou 730050, China
5.Huadong Engineering Corporation Limited, Power Construction Corporation of China, Hangzhou 311122, China
6.Power Industry Equipment Quality Inspection Center, China Electric Power Research Institute, Wuhan 430074, China
 全文: PDF(7141 KB)   HTML
摘要:

变压器热点温度对电网系统的可靠性和稳定性有直接影响。针对传统变压器管理模式复杂以及变压器热点温度预测方法存在成本高、计算效率低和计算误差高等问题,提出了一种基于数字孪生的变压器热点温度预测预警技术。首先,搭建变压器数字孪生六维模型,实现了系统数据共通、多源融合和虚实交互等功能。然后,构建可承载人工智能与机器学习算法的感知交互驱动型数字孪生系统,并采用混沌自适应粒子群优化(chaotic adaptive particle swarm optimization, CAPSO)算法对BP(back propagation,反向传播)神经网络的权重和阈值进行优化,加快了原始网络的收敛速度,同时建立了基于CAPSO-BP的变压器热点温度预测模型。最后,利用变压器现场监测数据在虚拟引擎平台上进行仿真分析,实现了变压器热点温度预测预警系统各功能的开发应用并验证了预测模型的可行性和有效性。研究结果为数字孪生变压器系统由数字化向智能化转型提供了新的思路和理论依据。

关键词: 变压器数字孪生人工智能机器学习混沌自适应粒子群优化反向传播神经网络温度预测    
Abstract:

The hotspot temperature of transformers has a direct impact on the reliability and stability of the power grid system. In response to the problems of complex traditional transformer management mode and high cost, low computational efficiency and high computational error in the transformer hotspot temperature prediction methods, a transformer hotspot temperature prediction and warning technology based on digital twin is proposed. Firstly, a six-dimensional digital twin model of the transformer was built to achieve functions such as system data sharing, multi-source fusion and virtual-real interaction. Then, a digital twin system driven by perception-interaction that could support artificial intelligence and machine learning algorithms was constructed. The chaotic adaptive particle swarm optimization (CAPSO) algorithm was adopted to optimize the weights and thresholds of the BP (back propagation) neural network, which accelerated the convergence speed of the original network. Meanwhile, a transformer hotspot temperature prediction model based on CAPSO-BP was established. Finally, the on-site monitoring data of transformers were used for simulation on the virtual engine platform, and the development and application of various functions of the transformer hotspot temperature prediction and warning system were implemented. Concurrently, the feasibility and effectiveness of the prediction model were verified. The research results provide new ideas and theoretical basis for the transformation of the digital twin transformer system from digitalization to intelligence.

Key words: transformer    digital twin    artificial intelligence    machine learning    chaotic adaptive particle swarm optimization    back propagation neural network    temperature prediction
收稿日期: 2024-11-11 出版日期: 2025-07-02
CLC:  TM 432  
基金资助: 国家自然科学基金资助项目(51741907);梯级水电站运行与控制湖北省重点实验室开放基金资助项目(2021KJX04)
通讯作者: 付文龙     E-mail: libailin@ctgu.edu.cn;ctgu_fuwenlong@126.com
作者简介: 李佰霖(1987—),男,讲师,博士,从事水力发电厂运维数字化、电力设备在线监测与故障诊断等研究,E-mail: libailin@ctgu.edu.cn,https://orcid.org/0000-0002-1174-465X
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李佰霖
马云帆
陈昱锐
罗远林
褚凡武
付文龙

引用本文:

李佰霖,马云帆,陈昱锐,罗远林,褚凡武,付文龙. 基于数字孪生的变压器热点温度预测预警技术研究[J]. 工程设计学报, 2025, 32(3): 281-295.

Bailin LI,Yunfan MA,Yurui CHEN,Yuanlin LUO,Fanwu CHU,Wenlong FU. Research on transformer hotspot temperature prediction and warning technology based on digital twin[J]. Chinese Journal of Engineering Design, 2025, 32(3): 281-295.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2025.04.179        https://www.zjujournals.com/gcsjxb/CN/Y2025/V32/I3/281

图1  数字孪生变压器热点温度预测系统六维模型
图2  数字孪生变压器热点温度预测预警系统
图3  主变压器实物图
图4  强迫油循环水冷变压器的散热原理
参数绕组热点温度冷却器入口水温冷却器入口水压油箱入口油温油箱入口油压
绕组热点温度1.000-0.705-0.1790.9950.780
冷却器入口水温-0.7051.0000.273-0.712-0.660
冷却器入口水压-0.1790.2731.000-0.2210.066
油箱入口油温0.995-0.712-0.2211.0000.777
油箱入口油压0.780-0.6600.0660.7771.000
表1  变压器绕组热点温度的相关性分析结果
图5  变压器绕组热点温度相关性分析结果的热力图
图6  测试函数
图7  不同PSO算法的寻优结果
图8  BP神经网络拓扑结构
图9  基于CAPSO-BP的变压器热点温度预测流程
图10  变压器运行数据实时监控界面
图11  变压器热点温度预测预警系统运行流程
顶层油温1/℃顶层油温2/℃

冷却器入口

水温/℃

油箱入口

油温/℃

油箱入口

油压/Pa

环境温度/℃负载电流/A

绕组热点

温度/℃

34.033.723.835.041.924.542259.3
33.733.523.834.841.924.542159.2
33.933.423.834.551.624.241858.7
39.038.123.838.550.924.142363.9
40.139.823.839.551.824.142365.7
41.140.523.839.851.524.842467.0
41.140.723.840.051.325.442667.7
41.341.023.740.151.526.542869.1
38.839.023.938.542.227.142967.0
表2  部分变压器现场监测数据
图12  基于CAPSO-BP模型的变压器绕组热点温度预测结果
图13  基于传统BP模型的变压器绕组热点温度预测结果
图14  基于PSO-BP模型的变压器绕组热点温度预测结果
模型?MAE/℃?RMSE/℃计算时间/s
传统BP模型0.2040.49113.2
PSO-BP模型0.1490.2449.6
CAPSO-BP模型0.0580.1536.3
表3  3种预测模型的误差和计算时间
图15  不考虑冷却器入口水温的变压器绕组热点温度预测结果
图16  不考虑油箱入口油温的变压器绕组热点温度预测结果
图17  不考虑油箱入口油压的变压器绕组热点温度预测结果
情况?MAE?RMSE
不考虑冷却器入口水温0.1570.260
不考虑油箱入口油温0.1830.368
不考虑油箱入口油压0.1620.323
表4  不同情况下CAPSO-BP模型的误差对比 (℃)
图18  不同时间段内的变压器绕组热点温度预测结果
图19  变压器热点温度预测预警数字化服务平台
图20  变压器热点温度预警系统评估结果
[1] 郭克莎. 中国产业结构调整升级趋势与“十四五”时期政策思路[J]. 中国工业经济, 2019(7): 24-41.
GUO K S. The trend of industrial structure adjustment and upgrading in China and the thoughts of policy adjustment during the “14th Five-Year Plan”[J]. China Industrial Economics, 2019(7): 24-41.
[2] 李晖, 刘栋, 姚丹阳. 面向碳达峰碳中和目标的我国电力系统发展研判[J]. 中国电机工程学报, 2021, 41(18): 6245-6259.
LI H, LIU D, YAO D Y. Analysis and reflection on the development of power system towards the goal of carbon emission peak and carbon neutrality[J]. Proceedings of the CSEE, 2021, 41(18): 6245-6259.
[3] 韩肖清, 李廷钧, 张东霞, 等. 双碳目标下的新型电力系统规划新问题及关键技术[J]. 高电压技术, 2021, 47(9): 3036-3046.
HAN X Q, LI T J, ZHANG D X, et al. New issues and key technologies of new power system planning under double carbon goals[J]. High Voltage Engineering, 2021, 47(9): 3036-3046.
[4] 陶飞, 刘蔚然, 刘检华, 等. 数字孪生及其应用探索[J]. 计算机集成制造系统, 2018, 24(1): 1-18. doi:10.3901/JME.2018.16.011
TAO F, LIU W R, LIU J H, et al. Digital twin and its potential application exploration[J]. Computer Integrated Manufacturing Systems, 2018, 24(1): 1-18.
doi: 10.3901/JME.2018.16.011
[5] 王方, 甘甜, 王煜栋, 等. 航空发动机燃烧室数字孪生体系关键技术[J]. 航空动力学报, 2023, 38(7): 1546-1560.
WANG F, GAN T, WANG Y D, et al. Key technology of digital twin system for aero-engine combustors[J]. Journal of Aerospace Power, 2023, 38(7): 1546-1560.
[6] 刘夏阳, 芦超越, 刘晓荣, 等. 数字孪生技术在援外医疗队培训中的应用[J]. 海军军医大学学报, 2023, 44(2): 245-250. doi:10.25236/ajets.2023.060209
LIU X Y, LU C Y, LIU X R, et al. Application of digital twin technology in training medical aid teams to work in foreign countries[J]. Academic Journal of Naval Medical University, 2023, 44(2): 245-250.
doi: 10.25236/ajets.2023.060209
[7] 杨康, 吴少培, 董志宇, 等. 铁路货车钩舌检修数字孪生车间的研究与应用[J]. 计算机集成制造系统, 2024, 30(7): 2474-2485.
YANG K, WU S P, DONG Z Y, et al. Research and application of digital twins workshop for inspection and repair of coupler knuckle of railway wagon[J]. Computer Integrated Manufacturing Systems, 2024, 30(7): 2474-2485.
[8] 赵龙飞, 姜晓轶, 洪宇, 等. 智慧海洋数字孪生技术及其应用[J]. 科技导报, 2024, 42(4): 91-101.
ZHAO L F, JIANG X Y, HONG Y, et al. Smart ocean digital twin technology and its application[J]. Science & Technology Review, 2024, 42(4): 91-101.
[9] 罗德宁, 刘启虞, 郭德全. 基于TMS的数字孪生城市分层影像数据实时绘制方法[J]. 工程科学与技术, 2023, 55(6): 39-45.
LUO D N, LIU Q Y, GUO D Q. A real-time rendering method of layered image data in digital twin city based on TMS[J]. Advanced Engineering Sciences, 2023, 55(6): 39-45.
[10] 王成山, 董博, 于浩, 等. 智慧城市综合能源系统数字孪生技术及应用[J]. 中国电机工程学报, 2021, 41(5): 1597-1608.
WANG C S, DONG B, YU H, et al. Digital twin technology and its application in the integrated energy system of smart city[J]. Proceedings of the CSEE, 2021, 41(5): 1597-1608.
[11] ROSEN R, VON WICHERT G, LO G, et al. About the importance of autonomy and digital twins for the future of manufacturing[J]. IFAC-PapersOnLine, 2015, 48(3): 567-572.
[12] 陶飞, 张萌, 程江峰, 等. 数字孪生车间: 一种未来车间运行新模式[J]. 计算机集成制造系统, 2017, 23(1): 1-9.
TAO F, ZHANG M, CHENG J F, et al. Digital twin workshop: a new paradigm for future workshop[J]. Computer Integrated Manufacturing Systems, 2017, 23(1): 1-9.
[13] 陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
TAO F, LIU W R, ZHANG M, et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1): 1-18.
[14] 段现银, 邵宇轩, 彭芳瑜, 等. 基于数字孪生的复杂件多机器人智能加工方法[J]. 华中科技大学学报(自然科学版), 2024, 52(6): 1-9.
DUAN X Y, SHAO Y X, PENG F Y, et al. Digital twins based multi-robot intelligent machining method for complex components[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2024, 52(6): 1-9.
[15] 王红军, 林俊强, 邹湘军, 等. 基于数字孪生的果园虚拟交互系统构建[J]. 系统仿真学报, 2024, 36(6): 1493-1508.
WANG H J, LIN J Q, ZOU X J, et al. Construction of a virtual interactive system for orchards based on digital twin[J]. Journal of System Simulation, 2024, 36(6): 1493-1508.
[16] 朱军, 朱庆, 祝兵, 等. 数字孪生驱动的桥梁智能建造方法[J]. 遥感学报, 2024, 28(5): 1340-1349.
ZHU J, ZHU Q, ZHU B, et al. Intelligent bridge construction method driven by digital twin[J]. National Remote Sensing Bulletin, 2024, 28(5): 1340-1349.
[17] 韩冬辰, 张弘, 刘燕, 等. 从BIM到BDT:关于建筑数字孪生体(BDT)的构想研究[J]. 建筑学报, 2020(10): 95-101.
HAN D C, ZHANG H, LIU Y, et al. From BIM to BDT: research on the conception of building digital twin[J]. Architectural Journal, 2020(10): 95-101.
[18] JIANG J R. An improved cyber-physical systems architecture for Industry 4.0 smart factories[C]//2017 International Conference on Applied System Innovation. Sapporo, May 13-17, 2017.
[19] WANG B C, ZHENG P, YIN Y, et al. Toward human-centric smart manufacturing: a human-cyber-physical systems (HCPS) perspective[J]. Journal of Manufacturing Systems, 2022, 63: 471-490.
[20] 周建兴, 张浩成, 高启滨, 等. 基于SABRE技术的高超声速预冷飞行器应用分析[J]. 推进技术, 2018, 39(10): 2196-2206.
ZHOU J X, ZHANG H C, GAO Q B, et al. Analysis of vehicle applications propelled by SABRE-based precooling hypersonic engine[J]. Journal of Propulsion Technology, 2018, 39(10): 2196-2206.
[21] 严兴煜, 高赐威, 陈涛, 等. 数字孪生虚拟电厂系统框架设计及其实践展望[J]. 中国电机工程学报, 2023, 43(2): 604-619.
YAN X Y, GAO C W, CHEN T, et al. Framework design and application prospect for digital twin virtual power plant system[J]. Proceedings of the CSEE, 2023, 43(2): 604-619.
[22] 张冀, 马也, 张荣华, 等. 数字孪生变电站框架设计与关键技术研究[J]. 工程科学与技术, 2023, 55(6): 15-30.
ZHANG J, MA Y, ZHANG R H, et al. Framework design and key technology research of digital twin substation[J]. Advanced Engineering Sciences, 2023, 55(6): 15-30.
[23] 刘云鹏, 刘一瑾, 刘刚, 等. 电力变压器智能运维的数字孪生体构想[J]. 中国电机工程学报, 2023, 43(22): 8636-8652.
LIU Y P, LIU Y J, LIU G, et al. Digital twin conception of intelligent operation and maintenance of power transformer[J]. Proceedings of the CSEE, 2023, 43(22): 8636-8652.
[24] 齐波, 张鹏, 张书琦, 等. 数字孪生技术在输变电设备状态评估中的应用现状与发展展望[J]. 高电压技术, 2021, 47(5): 1522-1538.
QI B, ZHANG P, ZHANG S Q, et al. Application status and development prospects of digital twin technology in condition assessment of power transmission and transformation equipment[J]. High Voltage Engineering, 2021, 47(5): 1522-1538.
[25] 廖瑞金, 罗豪, 成立, 等. 面向数字孪生变压器的计算机辅助运维(CAM+)构架与关键技术[J]. 高电压技术, 2024, 50(3): 924-940.
LIAO R J, LUO H, CHENG L, et al. Computer aided maintenance (CAM+) framework and key technologies towards digital twin transformers[J]. High Voltage Engineering, 2024, 50(3): 924-940.
[26] 李佰霖, 陈昱锐, 褚凡武, 等. 基于混合采样和CAWOA-BP的变压器故障诊断[J]. 水电能源科学, 2024, 42(3): 216-220.
LI B L, CHEN Y R, CHU F W, et al. Transformer fault diagnosis based on hybrid sampling and CAWOA-BP[J]. Water Resources and Power, 2024, 42(3): 216-220.
[27] 孙毅卫, 赵清抗, 刘新颜, 等. 智能变压器绕组热点温升的在线监测[J]. 电气工程学报, 2014, 9(2): 30-32.
SUN Y W, ZHAO Q K, LIU X Y, et al. On-line monitoring of hot spot temperature rise of intelligent transformer winding[J]. Journal of Electrical Engineering, 2014, 9(2): 30-32.
[28] 刘辉, 刘强, 张立, 等. 基于改进参数辨识方法的变压器绕组热点温度计算[J]. 变压器, 2018, 55(4): 68-74.
LIU H, LIU Q, ZHANG L, et al. Transformer winding hot spot temperature calculation based on improved parameter identification method[J]. Transformer, 2018, 55(4): 68-74.
[29] 张晓华, 吕志瑞, 孙云生, 等. 基于修正热路模型的油浸式变压器绕组热点温度计算研究[J]. 电测与仪表, 2025, 62(3): 78-84.
ZHANG X H, LÜ Z R, SUN Y S, et al. Research of hot spot temperature calculation in oil-immersed transformer based on modified thermal model[J]. Electrical Measurement & Instrumentation, 2025, 62(3): 78-84.
[30] 孙晨茜, 李琳. 非正弦激励下高频变压器的温度分布计算与分析[J]. 高压电器, 2022, 58(10): 96-105.
SUN C X, LI L. Calculation and analysis of temperature distribution of high-frequency transformer under non-sinusoidal excitation[J]. High Voltage Apparatus, 2022, 58(10): 96-105.
[31] 李飞, 江航龙. 矿用隔爆型干式变压器温升的计算流体动力学仿真分析[J]. 变压器, 2024, 61(6): 12-15.
LI F, JIANG H L. Computational fluid dynamics simulation analysis of temperature rise of mine explosion-proof dry type transformer[J]. Transformer, 2024, 61(6): 12-15.
[32] LI B L, MA Y F, ZHANG C, et al. Research and application of digital electrical substation virtual engineering education system[J]. Computer Applications in Engineering Education, 2024, 32(6): e22777.
[33] 王丰华, 周翔, 高沛, 等. 基于绕组热分布的改进油浸式变压器绕组热点温度计算模型[J]. 高电压技术, 2015, 41(3): 895-901.
WANG F H, ZHOU X, GAO P, et al. Improved thermal circuit model of hot spot temperature in oil-immersed transformers based on heat distribution of winding[J]. High Voltage Engineering, 2015, 41(3): 895-901.
[1] 薛杨,刘森,吕杰,彭锦,司恒远. 基于耦合场快速计算的核电厂主变压器数字孪生体搭建[J]. 工程设计学报, 2024, 31(6): 716-724.
[2] 孙宝印,郝永平,张誉瀚,李子洋. 基于数字孪生的热电池保温棉自动缠绕系统研究[J]. 工程设计学报, 2024, 31(4): 538-546.
[3] 谢章伟,张兴波,徐哲,张羽,张丰云,王茜,王萍萍,孙树峰,王海涛,刘纪新,孙维丽,曹爱霞. 基于数字孪生的激光加工零件表面温度监控系统的构建[J]. 工程设计学报, 2023, 30(4): 409-418.
[4] 徐哲,孙树峰,张兴波,王茜,张丰云,王萍萍,谢章伟,张羽,刘纪新,孙维丽,曹爱霞. 基于数字孪生的光学位移台交互控制系统[J]. 工程设计学报, 2023, 30(2): 254-261.
[5] 张旭辉,鞠佳杉,杨文娟,吕欣媛. 基于数字孪生的复杂矿用设备预测性维护系统[J]. 工程设计学报, 2022, 29(5): 643-650.
[6] 李梦,尹宗军. 一种零件综合质量评定方法研究[J]. 工程设计学报, 2022, 29(4): 410-418.
[7] 傅贵武, 王兴波, 田英. 基于五轴加工中心智能生产线的数字孪生应用研究[J]. 工程设计学报, 2021, 28(4): 426-432.
[8] 白仲航, 孙意为, 许彤, 丁满. 基于设计任务的概念设计中产品数字孪生模型的构建[J]. 工程设计学报, 2020, 27(6): 681-689.
[9] 王安邦, 孙文彬, 段国林. 基于数字孪生与深度学习技术的制造加工设备智能化方法研究[J]. 工程设计学报, 2019, 26(6): 666-674.