IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v12y2019i6p995-d213890.html
   My bibliography  Save this article

A Dynamic Adam Based Deep Neural Network for Fault Diagnosis of Oil-Immersed Power Transformers

Author

Listed:
  • Minghui Ou

    (Guangxi Key Laboratory of Power System Optimization and Energy Technology, Guangxi University, Nanning 530004, China)

  • Hua Wei

    (Guangxi Key Laboratory of Power System Optimization and Energy Technology, Guangxi University, Nanning 530004, China)

  • Yiyi Zhang

    (Guangxi Key Laboratory of Power System Optimization and Energy Technology, Guangxi University, Nanning 530004, China)

  • Jiancheng Tan

    (College of Electrical Engineering, Guangxi University, Nanning 530004, China)

Abstract

This paper presents a Dynamic Adam and dropout based deep neural network (DADDNN) for fault diagnosis of oil-immersed power transformers. To solve the problem of incomplete extraction of hidden information with data driven, the gradient first-order moment estimate and second-order moment estimate are used to calculate the different learning rates for all parameters with stable gradient scaling. Meanwhile, the learning rate is dynamically attenuated according to the optimal interval. To prevent over-fitted, we exploit dropout technique to randomly reset some neurons and strengthen the information exchange between indirectly-linked neurons. Our proposed approach was utilized on four datasets to learn the faults diagnosis of oil-immersed power transformers. Besides, four benchmark cases in other fields were also utilized to illustrate its scalability. The simulation results show that the average diagnosis accuracies on the four datasets of our proposed method were 37.9%, 25.5%, 14.6%, 18.9%, and 11.2%, higher than international electro technical commission (IEC), Duval Triangle, stacked autoencoders (SAE), deep belief networks (DBN), and grid search support vector machines (GSSVM), respectively.

Suggested Citation

  • Minghui Ou & Hua Wei & Yiyi Zhang & Jiancheng Tan, 2019. "A Dynamic Adam Based Deep Neural Network for Fault Diagnosis of Oil-Immersed Power Transformers," Energies, MDPI, vol. 12(6), pages 1-16, March.
    • Handle: RePEc:gam:jeners:v:12:y:2019:i:6:p:995-:d:213890
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/12/6/995/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/12/6/995/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jun Lin & Gehao Sheng & Yingjie Yan & Jiejie Dai & Xiuchen Jiang, 2018. "Prediction of Dissolved Gas Concentrations in Transformer Oil Based on the KPCA-FFOA-GRNN Model," Energies, MDPI, vol. 11(1), pages 1-13, January.
    2. Jiefeng Liu & Hanbo Zheng & Yiyi Zhang & Hua Wei & Ruijin Liao, 2017. "Grey Relational Analysis for Insulation Condition Assessment of Power Transformers Based Upon Conventional Dielectric Response Measurement," Energies, MDPI, vol. 10(10), pages 1-16, October.
    3. Enwen Li & Linong Wang & Bin Song & Siliang Jian, 2018. "Improved Fuzzy C-Means Clustering for Transformer Fault Diagnosis Using Dissolved Gas Analysis Data," Energies, MDPI, vol. 11(9), pages 1-17, September.
    4. Muhammad Ali & Dae-Hee Son & Sang-Hee Kang & Soon-Ryul Nam, 2017. "An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy," Energies, MDPI, vol. 10(11), pages 1-24, November.
    5. Jing Wu & Kun Li & Jing Sun & Li Xie, 2018. "A Novel Integrated Method to Diagnose Faults in Power Transformers," Energies, MDPI, vol. 11(11), pages 1-8, November.
    6. Zixia Sang & Chengxiong Mao & Jiming Lu & Dan Wang, 2013. "Analysis and Simulation of Fault Characteristics of Power Switch Failures in Distribution Electronic Power Transformers," Energies, MDPI, vol. 6(8), pages 1-23, August.
    7. Jiake Fang & Hanbo Zheng & Jiefeng Liu & Junhui Zhao & Yiyi Zhang & Ke Wang, 2018. "A Transformer Fault Diagnosis Model Using an Optimal Hybrid Dissolved Gas Analysis Features Subset with Improved Social Group Optimization-Support Vector Machine Classifier," Energies, MDPI, vol. 11(8), pages 1-18, July.
    8. Lefeng Cheng & Tao Yu, 2018. "Dissolved Gas Analysis Principle-Based Intelligent Approaches to Fault Diagnosis and Decision Making for Large Oil-Immersed Power Transformers: A Survey," Energies, MDPI, vol. 11(4), pages 1-69, April.
    9. Yiyi Zhang & Jiefeng Liu & Hanbo Zheng & Hua Wei & Ruijin Liao, 2017. "Study on Quantitative Correlations between the Ageing Condition of Transformer Cellulose Insulation and the Large Time Constant Obtained from the Extended Debye Model," Energies, MDPI, vol. 10(11), pages 1-17, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Zhi-Jun Li & Wei-Gen Chen & Jie Shan & Zhi-Yong Yang & Ling-Yan Cao, 2022. "Enhanced Distributed Parallel Firefly Algorithm Based on the Taguchi Method for Transformer Fault Diagnosis," Energies, MDPI, vol. 15(9), pages 1-22, April.
    2. El-Sayed M. El-kenawy & Fahad Albalawi & Sayed A. Ward & Sherif S. M. Ghoneim & Marwa M. Eid & Abdelaziz A. Abdelhamid & Nadjem Bailek & Abdelhameed Ibrahim, 2022. "Feature Selection and Classification of Transformer Faults Based on Novel Meta-Heuristic Algorithm," Mathematics, MDPI, vol. 10(17), pages 1-28, September.

    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. Lefeng Cheng & Tao Yu, 2018. "Dissolved Gas Analysis Principle-Based Intelligent Approaches to Fault Diagnosis and Decision Making for Large Oil-Immersed Power Transformers: A Survey," Energies, MDPI, vol. 11(4), pages 1-69, April.
    2. Fenglan Tian & Zhongzhao Jing & Huan Zhao & Enze Zhang & Jiefeng Liu, 2019. "A Synthetic Condition Assessment Model for Power Transformers Using the Fuzzy Evidence Fusion Method," Energies, MDPI, vol. 12(5), pages 1-17, March.
    3. Hanbo Zheng & Jiefeng Liu & Yiyi Zhang & Yijie Ma & Yang Shen & Xiaochen Zhen & Zilai Chen, 2018. "Effectiveness Analysis and Temperature Effect Mechanism on Chemical and Electrical-Based Transformer Insulation Diagnostic Parameters Obtained from PDC Data," Energies, MDPI, vol. 11(1), pages 1-17, January.
    4. Tusongjiang Kari & Wensheng Gao & Ayiguzhali Tuluhong & Yilihamu Yaermaimaiti & Ziwei Zhang, 2018. "Mixed Kernel Function Support Vector Regression with Genetic Algorithm for Forecasting Dissolved Gas Content in Power Transformers," Energies, MDPI, vol. 11(9), pages 1-19, September.
    5. Jiake Fang & Hanbo Zheng & Jiefeng Liu & Junhui Zhao & Yiyi Zhang & Ke Wang, 2018. "A Transformer Fault Diagnosis Model Using an Optimal Hybrid Dissolved Gas Analysis Features Subset with Improved Social Group Optimization-Support Vector Machine Classifier," Energies, MDPI, vol. 11(8), pages 1-18, July.
    6. Enwen Li & Linong Wang & Bin Song & Siliang Jian, 2018. "Improved Fuzzy C-Means Clustering for Transformer Fault Diagnosis Using Dissolved Gas Analysis Data," Energies, MDPI, vol. 11(9), pages 1-17, September.
    7. Zhilin Lyu & Qing Wei & Yiyi Zhang & Junhui Zhao & Emad Manla, 2018. "Adaptive Virtual Impedance Droop Control Based on Consensus Control of Reactive Current," Energies, MDPI, vol. 11(7), pages 1-17, July.
    8. Fahad M. Almasoudi, 2023. "Grid Distribution Fault Occurrence and Remedial Measures Prediction/Forecasting through Different Deep Learning Neural Networks by Using Real Time Data from Tabuk City Power Grid," Energies, MDPI, vol. 16(3), pages 1-20, January.
    9. Nuria Novas & Alfredo Alcayde & Isabel Robalo & Francisco Manzano-Agugliaro & Francisco G. Montoya, 2020. "Energies and Its Worldwide Research," Energies, MDPI, vol. 13(24), pages 1-41, December.
    10. Fabio Henrique Pereira & Francisco Elânio Bezerra & Shigueru Junior & Josemir Santos & Ivan Chabu & Gilberto Francisco Martha de Souza & Fábio Micerino & Silvio Ikuyo Nabeta, 2018. "Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations," Energies, MDPI, vol. 11(7), pages 1-12, June.
    11. Fang Yuan & Jiang Guo & Zhihuai Xiao & Bing Zeng & Wenqiang Zhu & Sixu Huang, 2019. "A Transformer Fault Diagnosis Model Based on Chemical Reaction Optimization and Twin Support Vector Machine," Energies, MDPI, vol. 12(5), pages 1-18, March.
    12. Lefeng Cheng & Tao Yu & Guoping Wang & Bo Yang & Lv Zhou, 2018. "Hot Spot Temperature and Grey Target Theory-Based Dynamic Modelling for Reliability Assessment of Transformer Oil-Paper Insulation Systems: A Practical Case Study," Energies, MDPI, vol. 11(1), pages 1-26, January.
    13. Hui Huang & Chengxiong Mao & Jiming Lu & Dan Wang, 2014. "Electronic Power Transformer Control Strategy in Wind Energy Conversion Systems for Low Voltage Ride-through Capability Enhancement of Directly Driven Wind Turbines with Permanent Magnet Synchronous G," Energies, MDPI, vol. 7(11), pages 1-18, November.
    14. Yuhong Wang & Lei Chen & Hong Zhou & Xu Zhou & Zongsheng Zheng & Qi Zeng & Li Jiang & Liang Lu, 2021. "Flexible Transmission Network Expansion Planning Based on DQN Algorithm," Energies, MDPI, vol. 14(7), pages 1-21, April.
    15. Kai Ding & Chen Yao & Yifan Li & Qinglong Hao & Yaqiong Lv & Zengrui Huang, 2022. "A Review on Fault Diagnosis Technology of Key Components in Cold Ironing System," Sustainability, MDPI, vol. 14(10), pages 1-28, May.
    16. Michał Jasiński & Tomasz Sikorski & Zbigniew Leonowicz & Klaudiusz Borkowski & Elżbieta Jasińska, 2020. "The Application of Hierarchical Clustering to Power Quality Measurements in an Electrical Power Network with Distributed Generation," Energies, MDPI, vol. 13(9), pages 1-19, May.
    17. Ismoil Odinaev & Andrey Pazderin & Murodbek Safaraliev & Firuz Kamalov & Mihail Senyuk & Pavel Y. Gubin, 2024. "Detection of Current Transformer Saturation Based on Machine Learning," Mathematics, MDPI, vol. 12(3), pages 1-18, January.
    18. Pawel Szczesniak, 2019. "Challenges and Design Requirements for Industrial Applications of AC/AC Power Converters without DC-Link," Energies, MDPI, vol. 12(8), pages 1-18, April.
    19. Sameh Ziad Ahmed Dabbak & Hazlee Azil Illias & Bee Chin Ang & Nurul Ain Abdul Latiff & Mohamad Zul Hilmey Makmud, 2018. "Electrical Properties of Polyethylene/Polypropylene Compounds for High-Voltage Insulation," Energies, MDPI, vol. 11(6), pages 1-13, June.
    20. Feng Yang & Lin Du & Lijun Yang & Chao Wei & Youyuan Wang & Liman Ran & Peng He, 2018. "A Parameterization Approach for the Dielectric Response Model of Oil Paper Insulation Using FDS Measurements," Energies, MDPI, vol. 11(3), pages 1-17, March.

    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:12:y:2019:i:6:p:995-:d:213890. 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.