IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v16y2023i5p2382-d1085337.html
   My bibliography  Save this article

Deep Learning-Based Transformer Moisture Diagnostics Using Long Short-Term Memory Networks

Author

Listed:
  • Aniket Vatsa

    (Department of Electrical Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad 826004, India)

  • Ananda Shankar Hati

    (Department of Electrical Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad 826004, India)

  • Vadim Bolshev

    (Laboratory of Power Supply and Heat Supply, Federal Scientific Agroengineering Centre VIM, 109428 Moscow, Russia)

  • Alexander Vinogradov

    (Laboratory of Power Supply and Heat Supply, Federal Scientific Agroengineering Centre VIM, 109428 Moscow, Russia)

  • Vladimir Panchenko

    (Department of Theoretical and Applied Mechanics, Russian University of Transport, 127994 Moscow, Russia)

  • Prasun Chakrabarti

    (Department of Computer Science and Engineering, ITM SLS Baroda University, Vadodara 391510, India)

Abstract

Power transformers play a crucial role in maintaining the stability and reliability of energy systems. Accurate moisture assessment of transformer oil-paper insulation is critical for ensuring safe operating conditions and power transformers’ longevity in large interconnected electrical grids. The moisture can be predicted and quantified by extracting moisture-sensitive dielectric feature parameters. This article suggests a deep learning technique for transformer moisture diagnostics based on long short-term memory (LSTM) networks. The proposed method was tested using a dataset of transformer oil moisture readings, and the analysis revealed that the LSTM network performed well in diagnosing oil insulation moisture. The method’s performance was assessed using various metrics, such as R-squared, mean absolute error, mean squared error, root mean squared error, and mean signed difference. The performance of the proposed model was also compared with linear regression and random forest (RF) models to evaluate its effectiveness. It was determined that the proposed method outperformed traditional methods in terms of accuracy and efficiency. This investigation demonstrates the potential of a deep learning approach for identifying transformer oil insulation moisture with a R 2 value of 0.899, thus providing a valuable tool for power system operators to monitor and manage the integrity of their transformer fleet.

Suggested Citation

  • Aniket Vatsa & Ananda Shankar Hati & Vadim Bolshev & Alexander Vinogradov & Vladimir Panchenko & Prasun Chakrabarti, 2023. "Deep Learning-Based Transformer Moisture Diagnostics Using Long Short-Term Memory Networks," Energies, MDPI, vol. 16(5), pages 1-14, March.
    • Handle: RePEc:gam:jeners:v:16:y:2023:i:5:p:2382-:d:1085337
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/16/5/2382/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/16/5/2382/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Fan, Guo-Feng & Yu, Meng & Dong, Song-Qiao & Yeh, Yi-Hsuan & Hong, Wei-Chiang, 2021. "Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling," Utilities Policy, Elsevier, vol. 73(C).
    2. Zha, Wenshu & Liu, Yuping & Wan, Yujin & Luo, Ruilan & Li, Daolun & Yang, Shan & Xu, Yanmei, 2022. "Forecasting monthly gas field production based on the CNN-LSTM model," Energy, Elsevier, vol. 260(C).
    3. Pawel Zukowski & Przemyslaw Rogalski & Tomasz N. Kołtunowicz & Konrad Kierczynski & Marek Zenker & Alexander D. Pogrebnjak & Matej Kucera, 2022. "DC and AC Tests of Moisture Electrical Pressboard Impregnated with Mineral Oil or Synthetic Ester—Determination of Water Status in Power Transformer Insulation," Energies, MDPI, vol. 15(8), pages 1-16, April.
    4. Giovanni Hernandez & Abner Ramirez, 2022. "Dielectric Response Model for Transformer Insulation Using Frequency Domain Spectroscopy and Vector Fitting," Energies, MDPI, vol. 15(7), pages 1-14, April.
    5. Inmaculada Fernández, 2022. "The Need for Experimental and Numerical Analyses of Thermal Ageing in Power Transformers," Energies, MDPI, vol. 15(17), pages 1-4, September.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Shi, Changfeng & Zhi, Jiaqi & Yao, Xiao & Zhang, Hong & Yu, Yue & Zeng, Qingshun & Li, Luji & Zhang, Yuxi, 2023. "How can China achieve the 2030 carbon peak goal—a crossover analysis based on low-carbon economics and deep learning," Energy, Elsevier, vol. 269(C).
    2. Feng, Zhanyu & Zhang, Jian & Jiang, Han & Yao, Xuejian & Qian, Yu & Zhang, Haiyan, 2024. "Energy consumption prediction strategy for electric vehicle based on LSTM-transformer framework," Energy, Elsevier, vol. 302(C).
    3. Stefenon, Stefano Frizzo & Seman, Laio Oriel & Aquino, Luiza Scapinello & Coelho, Leandro dos Santos, 2023. "Wavelet-Seq2Seq-LSTM with attention for time series forecasting of level of dams in hydroelectric power plants," Energy, Elsevier, vol. 274(C).
    4. Moreno, Sinvaldo Rodrigues & Seman, Laio Oriel & Stefenon, Stefano Frizzo & Coelho, Leandro dos Santos & Mariani, Viviana Cocco, 2024. "Enhancing wind speed forecasting through synergy of machine learning, singular spectral analysis, and variational mode decomposition," Energy, Elsevier, vol. 292(C).
    5. Shichao Huang & Jing Zhang & Yu He & Xiaofan Fu & Luqin Fan & Gang Yao & Yongjun Wen, 2022. "Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer," Energies, MDPI, vol. 15(10), pages 1-14, May.
    6. Karla Schröder & Gonzalo Farias & Sebastián Dormido-Canto & Ernesto Fabregas, 2024. "Comparative Analysis of Deep Learning Methods for Fault Avoidance and Predicting Demand in Electrical Distribution," Energies, MDPI, vol. 17(11), pages 1-13, June.
    7. Fargalla, Mandella Ali M. & Yan, Wei & Deng, Jingen & Wu, Tao & Kiyingi, Wyclif & Li, Guangcong & Zhang, Wei, 2024. "TimeNet: Time2Vec attention-based CNN-BiGRU neural network for predicting production in shale and sandstone gas reservoirs," Energy, Elsevier, vol. 290(C).
    8. Fuquan Song & Heying Ding & Yongzheng Wang & Shiming Zhang & Jinbiao Yu, 2023. "A Well Production Prediction Method of Tight Reservoirs Based on a Hybrid Neural Network," Energies, MDPI, vol. 16(6), pages 1-22, March.
    9. Przemyslaw Goscinski & Zbigniew Nadolny & Andrzej Tomczewski & Ryszard Nawrowski & Tomasz Boczar, 2023. "The Influence of Heat Transfer Coefficient α of Insulating Liquids on Power Transformer Cooling Systems," Energies, MDPI, vol. 16(6), pages 1-15, March.
    10. Zhou, Wei & Li, Xiangchengzhen & Qi, ZhongLi & Zhao, HaiHang & Yi, Jun, 2024. "A shale gas production prediction model based on masked convolutional neural network," Applied Energy, Elsevier, vol. 353(PA).
    11. Mi, Hanning & Chen, Sijie & Li, Qingxin & Shi, Ming & Hou, Shuoming & Zheng, Linfeng & Xu, Chengke & Yan, Zheng & Li, Canbing, 2024. "Strategic bidding by predicting locational marginal price with aggregated supply curve," Energy, Elsevier, vol. 304(C).
    12. Xiangming Kong & Yuetian Liu & Liang Xue & Guanlin Li & Dongdong Zhu, 2023. "A Hybrid Oil Production Prediction Model Based on Artificial Intelligence Technology," Energies, MDPI, vol. 16(3), pages 1-16, January.
    13. Li, Daolun & Zhou, Xia & Xu, Yanmei & Wan, Yujin & Zha, Wenshu, 2023. "Deep learning-based analysis of the main controlling factors of different gas-fields recovery rate," Energy, Elsevier, vol. 285(C).
    14. Wang, Jun & Cao, Junxing, 2024. "Reservoir properties inversion using attention-based parallel hybrid network integrating feature selection and transfer learning," Energy, Elsevier, vol. 304(C).
    15. Li, Baozhu & Lv, Xiaotian & Chen, Jiaxin, 2024. "Demand and supply gap analysis of Chinese new energy vehicle charging infrastructure: Based on CNN-LSTM prediction model," Renewable Energy, Elsevier, vol. 220(C).
    16. Fang, Yu & Jia, Chunhong & Wang, Xin & Min, Fan, 2024. "A fusion gas load prediction model with three-way residual error amendment," Energy, Elsevier, vol. 294(C).
    17. Banglong Pan & Hanming Yu & Hongwei Cheng & Shuhua Du & Shutong Cai & Minle Zhao & Juan Du & Fazhi Xie, 2023. "A CNN–LSTM Machine-Learning Method for Estimating Particulate Organic Carbon from Remote Sensing in Lakes," Sustainability, MDPI, vol. 15(17), pages 1-15, August.
    18. Hossam Fraihat & Amneh A. Almbaideen & Abdullah Al-Odienat & Bassam Al-Naami & Roberto De Fazio & Paolo Visconti, 2022. "Solar Radiation Forecasting by Pearson Correlation Using LSTM Neural Network and ANFIS Method: Application in the West-Central Jordan," Future Internet, MDPI, vol. 14(3), pages 1-24, March.
    19. Jiang, Wei & Wang, Xin & Zhang, Shu, 2023. "Integrating multi-modal data into AFSA-LSTM model for real-time oil production prediction," Energy, Elsevier, vol. 279(C).
    20. Zhang, Yunfei & Zhou, Zhihua & Du, Yahui & Shen, Jun & Li, Zhenxing & Yuan, Jianjuan, 2023. "A data transfer method based on one dimensional convolutional neural network for cross-building load prediction," Energy, Elsevier, vol. 277(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:16:y:2023:i:5:p:2382-:d:1085337. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.