{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:41:15Z","timestamp":1777398075723,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T00:00:00Z","timestamp":1721520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["52077012"],"award-info":[{"award-number":["52077012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The hot spot temperature of transformer windings is an important indicator for measuring insulation performance, and its accurate inversion is crucial to ensure the timely and accurate fault prediction of transformers. However, existing studies mostly directly input obtained experimental or operational data into networks to construct data-driven models, without considering the lag between temperatures, which may lead to the insufficient accuracy of the inversion model. In this paper, a method for inverting the hot spot temperature of transformer windings based on the SA-GRU model is proposed. Firstly, temperature rise experiments are designed to collect the temperatures of the entire side and top of the transformer tank, top oil temperature, ambient temperature, the cooling inlet and outlet temperatures, and winding hot spot temperature. Secondly, experimental data are integrated, considering the lag of the data, to obtain candidate input feature parameters. Then, a feature selection algorithm based on mutual information (MI) is used to analyze the correlation of the data and construct the optimal feature subset to ensure the maximum information gain. Finally, Self-Attention (SA) is applied to optimize the Gate Recurrent Unit (GRU) network, establishing the GRU-SA model to perceive the potential patterns between output feature parameters and input feature parameters, achieving the precise inversion of the hot spot temperature of the transformer windings. The experimental results show that considering the lag of the data can more accurately invert the hot spot temperature of the windings. The inversion method proposed in this paper can reduce redundant input features, lower the complexity of the model, accurately invert the changing trend of the hot spot temperature, and achieve higher inversion accuracy than other classical models, thereby obtaining better inversion results.<\/jats:p>","DOI":"10.3390\/s24144734","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T14:45:53Z","timestamp":1721659553000},"page":"4734","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Inversion Method for Transformer Winding Hot Spot Temperature Based on Gated Recurrent Unit and Self-Attention and Temperature Lag"],"prefix":"10.3390","volume":"24","author":[{"given":"Yuefeng","family":"Hao","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9297-693X","authenticated-orcid":false,"given":"Zhanlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueli","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"},{"name":"Chengdu Power Supply Company, State Grid Sichuan Electric Power Company, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Electric Power Science Research Institute, Guizhou Power Grid Co., Ltd., Guiyang 550002, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2508512","DOI":"10.1109\/TIM.2022.3168929","article-title":"Multifeature Extraction and Semi-Supervised Deep Learning Scheme for State Diagnosis of Converter Transformer","volume":"71","author":"Xiao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"72102","DOI":"10.1109\/ACCESS.2020.2985534","article-title":"Novel Method for Comprehensive Corrosion Evaluation of Grounding Device","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106586","DOI":"10.1016\/j.ijepes.2020.106586","article-title":"A Novel Segmented Sampling Numerical Calculation Method for Grounding Parameters in Horizontally Multilayered Soil","volume":"126","author":"Dan","year":"2021","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3325","DOI":"10.1007\/s00202-022-01553-0","article-title":"3D Modeling of Winding Hot Spot Temperature in Oil-Immersed Transformers","volume":"104","author":"Kebriti","year":"2022","journal-title":"Electr. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Dao, T., and Phung, B.T. (2017, January 14\u201317). A Study of Hot-Spot Localization in Distribution Transformers. Proceedings of the 2017 1st International Conference on Electrical Materials and Power Equipment (ICEMPE), Xi\u2019an, China.","DOI":"10.1109\/ICEMPE.2017.7982048"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102268","DOI":"10.1016\/j.csite.2022.102268","article-title":"A New Method for Transformer Hot-Spot Temperature Prediction Based on Dynamic Mode Decomposition","volume":"37","author":"Yang","year":"2022","journal-title":"Case Stud. Therm. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"164392","DOI":"10.1109\/ACCESS.2020.3021673","article-title":"Hot-Spot Temperature Forecasting of the Instrument Transformer Using an Artificial Neural Network","volume":"8","year":"2020","journal-title":"IEEE Access"},{"key":"ref_8","first-page":"172","article-title":"Combination of Support Vector Regression with Particle Swarm Optimization for Hot-Spot Temperature Prediction of Oil-Immersed Power Transformer","volume":"88","author":"Chen","year":"2012","journal-title":"Prz. Elektrotechniczny"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1049\/elp2.12175","article-title":"Forecasting Thermal Parameters for Ultra-High Voltage Transformers Using Long- and Short-Term Time-Series Network with Conditional Mutual Information","volume":"16","author":"Lin","year":"2022","journal-title":"IET Electr. Power Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107380","DOI":"10.1109\/ACCESS.2019.2924709","article-title":"A Method for Hot Spot Temperature Prediction of a 10 kV Oil-Immersed Transformer","volume":"7","author":"Deng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sun, Y., Xu, G., Li, N., Li, K., Liang, Y., Zhong, H., Zhang, L., and Liu, P. (2021). Hotspot Temperature Prediction of Dry-Type Transformers Based on Particle Filter Optimization with Support Vector Regression. Symmetry, 13.","DOI":"10.3390\/sym13081320"},{"key":"ref_12","unstructured":"Bengang, W., Xinye, W., Zhoufei, Y., and Hua, H. (2017, January 11\u201314). A Method of Optimized Neural Network by L-M Algorithm to Transformer Winding Hot Spot Temperature Forecasting. Proceedings of the 2017 IEEE Electrical Insulation Conference (EIC), Baltimore, MD, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1080\/15325008.2019.1689452","article-title":"Thermal Analysis of Power Transformer Using an Improved Dynamic Thermal Equivalent Circuit Model","volume":"47","author":"Faiz","year":"2019","journal-title":"Electr. Power Compon. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8622","DOI":"10.1109\/JSEN.2022.3155706","article-title":"Research on Acoustic Events Recognition Method With Dimensionality Reduction Combining Attention and Mutual Information","volume":"22","author":"Liu","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Radivojevi\u0107, D.S., Lazovi\u0107, I.M., Mirkov, N.S., Ramadani, U.R., and Nikezi\u0107, D.P. (2023). A Comparative Evaluation of Self-Attention Mechanism with ConvLSTM Model for Global Aerosol Time Series Forecasting. Mathematics, 11.","DOI":"10.3390\/math11071744"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, F., Kong, Y., and Yang, C. (2024). Improved SSA-Based GRU Neural Network for BDS-3 Satellite Clock Bias Forecasting. Sensors, 24.","DOI":"10.3390\/s24041178"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, X., Li, H., and Fan, X. (2020). Global temperature sensing for an operating power transformer based on raman scattering. Sensors, 20.","DOI":"10.3390\/s20174903"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1109\/TPWRD.2022.3204333","article-title":"Test and Analysis on Extended Temperature Rise of 110 kV Transformer Based on Distributed Temperature Sensing","volume":"38","author":"Li","year":"2023","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_19","unstructured":"IEC Webstore (Standard No. IEC 60076-2:2011). Available online: https:\/\/webstore.iec.ch\/publication\/599."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.-Y. (2023). Segment Anything. arXiv.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_21","first-page":"187","article-title":"Mutual Information Based Feature Selection for Fingerprint Identification","volume":"43","author":"Adjimi","year":"2019","journal-title":"Informatica (Slovenia)"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25\u201329). Learning Phrase Representations Using RNN Encoder\u2013Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1016\/j.psep.2023.03.052","article-title":"A Novel Deep Learning Model Integrating CNN and GRU to Predict Particulate Matter Concentrations","volume":"173","author":"Guo","year":"2023","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"139993","DOI":"10.1109\/ACCESS.2023.3339613","article-title":"Hospital Outpatient Volume Prediction Model Based on Gated Recurrent Unit Optimized by the Modified Cheetah Optimizer","volume":"11","author":"Keyimu","year":"2023","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107800","DOI":"10.1016\/j.engappai.2023.107800","article-title":"SA-MVSNet: Self-Attention-Based Multi-View Stereo Network for 3D Reconstruction of Images with Weak Texture","volume":"131","author":"Yang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4542","DOI":"10.1109\/LRA.2022.3149569","article-title":"Hierarchical Point Cloud Encoding and Decoding With Lightweight Self-Attention Based Model","volume":"7","author":"Puang","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"128701","DOI":"10.1016\/j.energy.2023.128701","article-title":"Oil Well Production Prediction Based on CNN-LSTM Model with Self-Attention Mechanism","volume":"284","author":"Pan","year":"2023","journal-title":"Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102005","DOI":"10.1016\/j.tsep.2023.102005","article-title":"Daily Residential Heat Load Prediction Based on a Hybrid Model of Signal Processing, Econometric Model, and Support Vector Regression","volume":"43","author":"Xue","year":"2023","journal-title":"Therm. Sci. Eng. Prog."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105031","DOI":"10.1016\/j.jobe.2022.105031","article-title":"A Hybrid Deep Reinforcement Learning Ensemble Optimization Model for Heat Load Energy-Saving Prediction","volume":"58","author":"Sun","year":"2022","journal-title":"J. Build. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s13385-021-00289-8","article-title":"Bounds on Spearman\u2019s rho when at least one random variable is discrete","volume":"12","author":"Mesfioui","year":"2022","journal-title":"Eur. Actuar. J."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"10031","DOI":"10.1109\/ACCESS.2022.3142859","article-title":"Particle Swarm Optimization: A Comprehensive Survey","volume":"10","author":"Shami","year":"2022","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4734\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:20:41Z","timestamp":1760109641000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,21]]},"references-count":31,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24144734"],"URL":"https:\/\/doi.org\/10.3390\/s24144734","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,21]]}}}