Early warning of transformer equipment based on robot infrared temperature prediction

Lijie Sun; Junfei Zhu; Weishang Gao; Qin Gao; Márk Domonkos; Lijie Sun; Junfei Zhu; Weishang Gao; Qin Gao; Márk Domonkos

doi:10.3934/electreng.2026011

AIMS Electronics and Electrical Engineering

2026, Volume 10, Issue 2: 265-284. doi: 10.3934/electreng.2026011

Previous Article Next Article

Research article Special Issues

Early warning of transformer equipment based on robot infrared temperature prediction

1.
School of Art and Design, Taizhou University, Taizhou, 318000, China
2.
State Grid Taizhou Power Supply Company, Taizhou 318000, Zhejiang, China
3.
School of Intelligent Manufacturing, Taizhou University, Taizhou 318000, China
4.
Robotics Research Center, Eötvös Loránd university, Budapest 1088, Hungary

Received: 13 August 2025 Revised: 15 January 2026 Accepted: 29 January 2026 Published: 01 April 2026

Smart grid construction is a goal of the State Grid Corporation of China (SGCC). Transformer equipment, as the foundation of substation power supply and a critical component of the national power grid, requires stable operation. This paper proposes an early warning method for transformer equipment based on robot infrared temperature prediction, which mainly includes three parts: robot infrared temperature measurement, GWO-SVR temperature prediction based on historical equipment data, and determination of defect types according to heating defect classification standards for transformer equipment. This paper leverages the strong generalization ability of support vector regression (SVR), which maintains good prediction performance on small-sample data. To address limitations in the traditional SVR model caused by penalty factors and kernel function parameters, the Greey Wolf Optimizer (GWO) is introduced to optimize parameters and achieve optimal selection. The resulting GWO-SVR model is used for equipment temperature prediction, and defect types are identified in advance using dual-level grading standards from the state and the Taizhou Power Bureau, enabling early warning of transformer equipment. Compared with the GRNN, BP neural network, SVR model, LSTM, and Attention-LSTM, the GWO-SVR achieves better performance in substation temperature prediction, as evaluated by mean absolute error (MAE) and mean square error (MSE) metrics. In addition, GWO-SVR enables heat fault early warning based on temperature prediction and classification standards of heating defects for transformer equipment. This paper contributes to the unique application context of State Grid intelligence with previously unaddressed challenges.
- transformer equipment,
- temperature prediction,
- SVR,
- GWO,
- time series
Citation: Lijie Sun, Junfei Zhu, Weishang Gao, Qin Gao, Márk Domonkos. Early warning of transformer equipment based on robot infrared temperature prediction[J]. AIMS Electronics and Electrical Engineering, 2026, 10(2): 265-284. doi: 10.3934/electreng.2026011

Related Papers:

Abstract

Smart grid construction is a goal of the State Grid Corporation of China (SGCC). Transformer equipment, as the foundation of substation power supply and a critical component of the national power grid, requires stable operation. This paper proposes an early warning method for transformer equipment based on robot infrared temperature prediction, which mainly includes three parts: robot infrared temperature measurement, GWO-SVR temperature prediction based on historical equipment data, and determination of defect types according to heating defect classification standards for transformer equipment. This paper leverages the strong generalization ability of support vector regression (SVR), which maintains good prediction performance on small-sample data. To address limitations in the traditional SVR model caused by penalty factors and kernel function parameters, the Greey Wolf Optimizer (GWO) is introduced to optimize parameters and achieve optimal selection. The resulting GWO-SVR model is used for equipment temperature prediction, and defect types are identified in advance using dual-level grading standards from the state and the Taizhou Power Bureau, enabling early warning of transformer equipment. Compared with the GRNN, BP neural network, SVR model, LSTM, and Attention-LSTM, the GWO-SVR achieves better performance in substation temperature prediction, as evaluated by mean absolute error (MAE) and mean square error (MSE) metrics. In addition, GWO-SVR enables heat fault early warning based on temperature prediction and classification standards of heating defects for transformer equipment. This paper contributes to the unique application context of State Grid intelligence with previously unaddressed challenges.

References

[1]	Wu Y, Lin J, Liu J (2025) Switch monitoring algorithm for 220 kV terminal substation startup process based on multi time scale graph mode. Electr Pow Syst Res 239: 1‒8. https://doi.org/10.1016/j.epsr.2024.111181 doi: 10.1016/j.epsr.2024.111181
[2]	Sun S, Chen P, Lin Z, Zhang Z, Li Q (2025) Evolution characteristics and BLEVE risk analysis of overheating transformer oil under sudden depressurization. Fuel 393: 135075. https://doi.org/10.1016/j.fuel.2025.135075 doi: 10.1016/j.fuel.2025.135075
[3]	Wu B, Wang X, Qi S, Ma X (2025) Emergency backup power robust planning for urban agglomeration power grids with a high proportion of new energy sources in extreme disaster scenarios. Electr Pow Syst Res 247: 111715. https://doi.org/10.1016/j.epsr.2025.111715 doi: 10.1016/j.epsr.2025.111715
[4]	Amin A, Bibo A, Panyam M, Tallapragada P (2023) An Uncertainty-Aware Health Monitoring Model for Wind Turbine Drivetrains Based On Bayesian Neural Network. IFAC PapersOnLine 56: 235‒240. https://doi.org/10.1016/j.ifacol.2023.12.030 doi: 10.1016/j.ifacol.2023.12.030
[5]	Zhang X, Pan Y, Cao Y, Liu B, Yu X (2024) Cloud-based battery failure prediction and early warning using multi-source signals and machine learning. J Energy Storage 93: 112004. https://doi.org/10.1016/j.est.2024.112004 doi: 10.1016/j.est.2024.112004
[6]	Sahoo SR, Gupta BB (2021) Multiple features based approach for automatic fake news detection on social networks using deep learning. Appl Soft Comput 100: 106983. https://doi.org/10.1016/j.asoc.2020.106983 doi: 10.1016/j.asoc.2020.106983
[7]	Cvitić I, Peraković D, Periša M (2021) Ensemble machine learning approach for classification of IoT devices in smart home. Int J Mach Learn Cyb 12: 3179‒3202. https://doi.org/10.1007/s13042-020-01241-0 doi: 10.1007/s13042-020-01241-0
[8]	Zheng Y, Luo J, Chen J, Chen Z, Shang P (2023) Natural gas spot price prediction research under the background of Russia-Ukraine conflict-based on FS-GA-SVR hybrid model. J Environ Manage 344: 118446. https://doi.org/10.1016/j.jenvman.2023.118446 doi: 10.1016/j.jenvman.2023.118446
[9]	Wu X, Xu Z, Liu Y, Chen Z, Huang J, Chen Y (2024) Failure prediction method of heat transfer tube of nuclear power steam generator based on WOA-SVR. J Radiat Res Appl Sci 17: 100907. https://doi.org/10.1016/j.jrras.2024.100907 doi: 10.1016/j.jrras.2024.100907
[10]	Wu W, Chen K, Tsotsas E (2024) Prediction of particle mixing in rotary drums by a DEM data-driven PSO-SVR model. Powder Technol 434: 119365. https://doi.org/10.1016/j.powtec.2024.119365 doi: 10.1016/j.powtec.2024.119365
[11]	Afaridegan E, Fatahi-Alkouhi R, Azarm P, Amanian N (2025) Enhanced prediction of discharge coefficient in sharp-edged width constrictions using a novel hybrid SVR-IWOA and machine learning models. J Hydrol 657: 133103. https://doi.org/10.1016/j.jhydrol.2025.133103 doi: 10.1016/j.jhydrol.2025.133103
[12]	Judge MA, Franzitta V, Curto D, Guercio A, Cirrincione G, Khattak HA (2024) A comprehensive review of artificial intelligence approaches for smart grid integration and optimization. Energy Conversion and Management: X 24: 100724. https://doi.org/10.1016/j.ecmx.2024.100724 doi: 10.1016/j.ecmx.2024.100724
[13]	Ma H, Tang JM (2020) Short-Term Load Forecasting of Microgrid Based on Chaotic Particle Swarm Optimization. Procedia Computer Science 166: 546‒550. https://doi.org/10.1016/j.procs.2020.02.026 doi: 10.1016/j.procs.2020.02.026
[14]	Pham BT, Bui KTT, Prakash I, Ly HB (2024) Hybrid artificial intelligence models based on adaptive neuro fuzzy inference system and metaheuristic optimization algorithms for prediction of daily rainfall. Physics and Chemistry of the Earth, Parts A/B/C 134: 103563. https://doi.org/10.1016/j.pce.2024.103563 doi: 10.1016/j.pce.2024.103563
[15]	Kaya E, Kaya A, Baştemur Kaya C (2025) Adaptive Network-Based Fuzzy Inference System Training Using Nine Different Metaheuristic Optimization Algorithms for Time-Series Analysis of Brent Oil Price and Detailed Performance Analysis. Symmetry 17: 786. https://doi.org/10.3390/sym17050786 doi: 10.3390/sym17050786
[16]	Hao XH, Yang ZJ, Hao, Y (2021) Medium and long term prediction method of wind power based on improved gm-arma combination model. Electrotechnical 7: 11‒13.
[17]	Fatemidokht H, Rafsanjani MK, Gupta BB (2021) Efficient and secure routing protocol based on artificial intelligence algorithms with UAV-assisted for vehicular ad hoc networks in intelligent transportation systems. IEEE T Intell Transp Syst 22: 4757‒4769. https://doi.org/10.1109/TITS.2020.3041746 doi: 10.1109/TITS.2020.3041746
[18]	Yu T, Gan Q, Feng G, Han G (2022) A new fuzzy cognitive maps classifier based on capsule network. Knowledge-Based Systems 250: 108950. https://doi.org/10.1016/j.knosys.2022.108950 doi: 10.1016/j.knosys.2022.108950
[19]	Sun L, Hou J, Xing CJ, Fang Z (2022) A robust hammerstein-wiener model identification method for highly nonlinear systems. Processes 10: 2664. https://doi.org/10.3390/pr10122664 doi: 10.3390/pr10122664
[20]	Hou J, Su H, Yu C, Chen F, Li P (2022) Bias-correction errors-in-variables Hammerstein model identification. IEEE T Ind Electron 70: 7268‒7279. https://doi.org/10.1109/TIE.2022.3199931 doi: 10.1109/TIE.2022.3199931
[21]	Meghraoui K, Racharak T, Ait El Kadi K, Bensiali S, Sebari I (2025) A New Integrated Neurosymbolic Approach for Crop-Yield Prediction Using Environmental Data and Satellite Imagery at Field Scale. Artificial Intelligence in Geosciences 6: 100125. https://doi.org/10.1016/j.aiig.2025.100125 doi: 10.1016/j.aiig.2025.100125
[22]	Xu X, Lin Z, Li X, Shang C, Shen Q (2022) Multi-objective robust optimisation model for MDVRPLS in refined oil distribution. Int J Prod Res 60: 6772‒6792. https://doi.org/10.1080/00207543.2021.1887534 doi: 10.1080/00207543.2021.1887534
[23]	Tang JN, Jin X, Zhang JZ, Lang YX, Liu JX (2017) Application analysis of dl/t 664-2016 code for application of infrared diagnosis of live equipment. Smart grid 5: 924‒928.
[24]	Lauren J (2020) Support vector regression. In Machine Learning, 123‒140. Academic Press: Cambridge, Massachusetts. https://doi.org/10.1016/B978-0-12-815739-8.00007-9
[25]	Abirami S, Pethuraj M, Uthayakumar M, Chitra P (2024) A systematic survey on big data and artificial intelligence algorithms for intelligent transportation system. Case Stud Transp Pol 17: 101247. https://doi.org/10.1016/j.cstp.2024.101247 doi: 10.1016/j.cstp.2024.101247
[26]	Feng X, Xia WZ, Wang Z, Qian ZM, Liu J, Xu XQ (2021) Neural network water quality prediction of urban sewage plant based on SVR error compensation technology. Water purification technology 40: 92‒98 + 158.
[27]	Selselejoo M, Ahmadifar HR (2025) DT-GWO: A hybrid decision tree and GWO-based algorithm for multi-objective task scheduling optimization in cloud computing. Sustainable Computing: Informatics and Systems 47: 101138. https://doi.org/10.1016/j.suscom.2025.101138 doi: 10.1016/j.suscom.2025.101138
[28]	Wang C, Yang YL, Cai G, Zhang T (2024) Improvement of normalized prediction model of soil thermal conductivity. Int Commun Heat Mass Transfer 157: 107792. https://doi.org/10.1016/j.icheatmasstransfer.2024.107792 doi: 10.1016/j.icheatmasstransfer.2024.107792
[29]	Kim YS, Kim MK, Fu N, Liu J, Wang J, Srebric J (2025) Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models. Sustain Cities Soc 118: 105570. https://doi.org/10.1016/j.scs.2024.105570 doi: 10.1016/j.scs.2024.105570
[30]	Fatemidokht H, Rafsanjani MK, Gupta BB, Hsu CH (2021) Efficient and secure routing protocol based on artificial intelligence algorithms with UAV-assisted for vehicular ad hoc networks in intelligent transportation systems. IEEE T Intell Transp Syst 22: 4757‒4769. https://doi.org/10.1109/TITS.2020.3041746 doi: 10.1109/TITS.2020.3041746
[31]	Kumar N, Poonia V, Gupta BB, Goyal MK (2021) A novel framework for risk assessment and resilience of critical infrastructure towards climate change. Technol Forecast Soc 165: 120532. https://doi.org/10.1016/j.techfore.2020.120532 doi: 10.1016/j.techfore.2020.120532
[32]	Sebastian A, Tantia V (2025) Multi-variate LSTM with attention mechanism for the Indian stock market. International Journal of Information Management Data Insights 5: 100350. https://doi.org/10.1016/j.jjimei.2025.100350 doi: 10.1016/j.jjimei.2025.100350
[33]	Zhao ML, Niu JR, Yang CG (2002) Discrimination of the concepts of temperature, relative temperature difference and temper-ature difference ratio in infrared detection technology. Inner Mongolia electric power technology 06: 8‒10+15.

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)