FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-110220

Research Article |

Performance Assessment of Customized LSTM based Deep Learning Model for Predictive Maintenance of Transformer

Author(s): G V S S N Srirama Sarma1*, B Ravindranath Reddy2, Pradeep M Nirgude3 and P Vasudeva Naidu4

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 11, Issue 2

Publisher : FOREX Publication

Published : 10 June 2023

e-ISSN : 2347-470X

Page(s) : 389-400

DOI: https://doi.org/10.37391/IJEER.110220

Abstract

To improve predictive maintenance of transformers with small DGA datasets, customized LSTM network named C-LSTM is devised to circumvent the boundaries of the standard-LSTM network, which had an increased rate of classification error than conventional machine learning techniques. The study compares the performance of traditional machine learning algorithms with the customized LSTM model using various metrics such as validation accuracy, test accuracy, precision, recall, and F1-score. Additionally, the comparison includes the evaluation of seven fault detecting diagnostic techniques, including discharges of low/high energy, thermal/electrical faults, partial discharge, and low/medium/high thermal faults. The results indicate that the customized LSTM model outperforms traditional machine learning methods with a validation accuracy of 100% and a test accuracy of 98.57%.

Keywords: DGA, Duval Triangle method, Decision Tree, ANN, SVM, LSTM, C-LSTM.




G V S S N Srirama Sarma*, Research Scholar, JNTUH, Hyderabad, India & Assistant Professor, Department of Electrical and Electronics Engineering, Matrusri Engineering College, Saidabad, Hyderabad, India; Email: music.sarma2016@gmail.com

B Ravindranath Reddy, Deputy Executive Engineer, Jawaharlal Nehru Technological University Hyderabad (JNTUH University), Hyderabad, India; Email: bumanapalli_brreddy@yahoo.co.in

Pradeep M Nirgude, Additional Director, UHV Research Laboratory, CPRI, Hyderabad, India; Email: pmnirgude@cpri.in

P Vasudeva Naidu, Associate Professor, Department of Electrical and Electronics Engineering, Matrusri Engineering College, Saidabad, Hyderabad, India; Email: pvdnaidu81@gmail.com

    [1] Jiajun Duan, Yigang He, Bolun Du, Ruaa M. Rashad Ghandour, Wenjie Wu and Hui Zhang, "Intelligent Localization of Transformer Internal Degradations Combining Deep Convolutional Neural Networks and Image Segmentation", IEEE Access, Vol. 7, pp. 62705-62720, 2019. [Cross Ref]
    [2] Bing Zeng, Jiang Guo ,Fangqing Zhang , Wenqiang Zhu , Zhihuai Xiao , Sixu Huang and Peng Fan "Prediction Model for Dissolved Gas Concentration in Transformer Oil Based on Modified Grey Wolf Optimizer and LSSVM with Grey Relational Analysis and Empirical Mode Decomposition", Energies Vol.13, pp.422.,2020. [Cross Ref]
    [3] Jinzhong Li, Qiaogen Zhang, Ke Wang , Jianyi Wang, Tianchun Zhou and Yiyi Zhang "Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine", IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 23, no. 2, pp. 1198-1206, 2016. [Cross Ref]
    [4] Wenxiong Mo, Hongbing Wang, Le Luan, Tusongjiang.Kari and Wensheng Gao, "Power transformer fault diagnosis using support vector machine and particle swarm optimization", 10th International Symposium on Computational Intelligence and Design (ISCID), vol. 1, pp. 511-515. IEEE, 2017. [Cross Ref]
    [5] Yiyi Zhang, Xin Li, Hanbo Zheng, Huilu Yao, Jiefeng Liu, Chaohai Zhang, Hongbo Peng, Jian Jiao, "A Fault Diagnosis Model of Power Transformers Based on Dissolved Gas Analysis Features Selection and Improved Krill Herd Algorithm Optimized Support Vector Machine", IEEE Access, Vol. 7, pp. 102803-102811, 2019. [Cross Ref]
    [6] Shuaibing Li, Guangning Wu, Bo Gao, Changjin Hao, Dongli Xin and Xiaobing Yin, “Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 23, no. 1, pp. 586-595, February 2016. [Cross Ref]
    [7] Alhaytham Alqudsi and Ayman El-Hag, "Application of Machine Learning in Transformer Health Index Prediction", Vol.12, pp.2694, 2019. [Cross Ref]
    [8] Bing Zeng, Jiang Guo, Wenqiang Zhu, Zhihuai Xiao, Fang Yuan and Sixu Huang, "A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM", Energies 12, Vol. no. 21, pp. 4170, 2019. [Cross Ref]
    [9] Chang LIU, Hongzhi ZHANG, Zhicheng Xie, Zhixun Wang, Le Chen, Xiangning Lin, Hongfa,Ding, Zhengtian Li, Weihong Xiong, "Combined forecasting method of dissolved gases concentration and its application in condition-based maintenance", IEEE Transactions on Power Delivery 34, Vol no. 4, pp.1269-1279, 2018. [Cross Ref]
    [10] Christian Gianoglio, Edoardo Ragusa, Paolo Gastaldo, Federico Gallesi and Francesco Guastavino, "Online Predictive Maintenance Monitoring Adopting Convolutional Neural Networks", Energies 14, Vol. no. 15, pp. 4711, 2021. [Cross Ref]
    [11] Bo Qi, Yiming Wang, Peng Zhang, Chengrong Li, Hongbin Wang and Jinxiang Chen, "A novel self-decision fault diagnosis model based on state-oriented correction for power transformer", IEEE Transactions on Dielectrics and Electrical Insulation 27, Vol. no. 6, pp. 1778-1786, 2020. [Cross Ref]
    [12] Chuye Hu, Yang Zhong, Yiqi Lu, Xiaotong Luo and Shaorong Wang, "A Prediction Model for Time Series of Dissolved Gas Content in Transformer Oil Based on LSTM". Journal of Physics: Conference Series. 1659. 012030, 2020. [Cross Ref]
    [13] Farzana Kabir, Brandon Foggo and N Anpeng Yu, "Data Driven Predictive Maintenance of Distribution Transformers", China International Conference on Electricity Distribution, 2018. [Cross Ref]
    [14] Haroldo de Faria Jr.n , João Gabriel Spir Costa, Jose Luis Mejia Olivas ,"Review on Monitoring Methods for Predictive Maintenance of Power Transformer based on DGA " Renewable and Sustanable Energy Reviews, Vol. 46, no. 015, pp: 201, 2019. [Cross Ref]
    [15] Hong Yang, Aidan LaBella and Travis Desell, "Predictive maintenance for general aviation using convolutional transformers", Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, no. 11, pp. 12636-12642, 2022. [Cross Ref]
    [16] Gadepalli Srirama Sarma, Bumanapalli Ravindranath Reddy, Pradeep Nirgude and Pudi Vasudeva Naidu, “A long short-term memory based prediction model for transformer fault diagnosis using dissolved gas analysis with digital twin technology”, International Journal of Power Electronics and Drive Systems (IJPEDS),Vol.13, No. 2, June 2022, pp:1266-1276, ISSN:2088-8694 http://doi.org/10.11591/ijpeds.v13.i2.pp2166-1276. [Cross Ref]
    [17] Nithin Zope, Syed Imran Ali, Sanjeevikumar Padmanaban, Mahajan Sagar Bhaskar and Lucian Mihet Popa, "Analysis of 132kV/33kV 15MVA power transformer dissolved gas using transport-X Kelman Kit through Duval's triangle and Roger's Ratio prediction", IEEE International Conference on Industrial Technology (ICIT), Lyon, pp. 1160- 1164, 2018. [Cross Ref]
    [18] Okan Ozgonenel and Serap Karagol, "Power transformer protection based on decision tree approach", IET Electric Power Applications 8, Vol. no. 7, pp. 251-256, 2014. [Cross Ref]
    [19] Ganyun, L. V., Cheng Haozhong, Zhai Haibao, and Dong Lixin. "Fault diagnosis of power transformer based on multi-layer SVM classifier." Electric Power Systems Research 74, no. 1, pp: 1-7, 2005. [Cross Ref]
    [20] Bing Zeng, Jiang Guo, Wenqiang Zhu, Zhihuai Xiao, Fang Yuan and Sixu Huang, "A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM", Energies 12, Vol. no. 21, pp. 4170, 2019. [Cross Ref]
    [21] Xin Zhang, Shengyuan Wang , Yijun Jiang , Feifei Wu1 and Chenming Sun, "Prediction of dissolved gas in power transformer oil based on LSTM-GA", IOP Conference Series: Earth and Environmental Science, The Fifth International Conference on Energy Engineering and Environmental Protection, Vol. 675, pp.17-19, November 2020. [Cross Ref]
    [22] Gaiping Sun, Chuanwen Jiang, Xu Wang and Xiu Yang, "Short-term building load forecast based on a data-mining feature selection and LSTMRNN method," IEEJ Transactions on Electrical and Electronic Engineering, Vol. 15, no. 7, pp. 1002-1010, 2020. [Cross Ref]
    [23] Martin Sundermeyer, Hermann Ney and Ralf Schlüter, "From Feedforward to Recurrent LSTM Neural Networks for Language Modeling", IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 23, no. 3, pp. 517-529, March 2015. [Cross Ref]
    [24] H. Chuye Y. Zhong, Y. Lu, X. Luo and S. Wang, “A Prediction Model for Time Series of Dissolved Gas Content in Transformer Oil Based on LSTM,” International Conference on Ubiquitous Power Internet of Things (UPIOT 2020) & 4th International Symposium on Green Energy and Smart Grid (SGESG 2020) Vol. 1659, pp. 1-9, 012030, 2020. [Cross Ref]
    [25] J. Namgung, S. Son, and Y. S. Moon, "Efficient Deep Learning Models for DGA Domain Detection”, Security and Communication Networks, Vol. 2021, no. 8887881, pp. 1-15, 2021. [Cross Ref]
    [26] Lin and Shih-Lin, “Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults” electronics 10, no.18: 2266, 2021. [Cross Ref]
    [27] Ren, F., Jiang, Z., Wang, X. et al. “A DGA Domain Names Detection Modeling Method based on Integrating an Attention Mechanism and Deep Neural Network”. Cybersecur 3, volume 4, 2020, https://doi.org/10.1186/s42400-020-00046-6. [Cross Ref]
    [28] Luis P. Silvestrin, Mark Hoogendoorn and Ger Koole,"A Comparative Study of State-of-the-Art Machine Learning Algorithms for Predictive Maintenance," 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 760-767, 2019. [Cross Ref]
    [29] K. D. Patekar and B. Chaudhry, "DGA Analysis of Transformer using Artificial Neutral Network to Improve Reliability in Power Transformers," 2019 IEEE 4th International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), Chennai, India, 2019. [Cross Ref]
    [30] Vita, Vasiliki, Georgios Fotis, Veselin Chobanov, Christos Pavlatos, and Valeri Mladenov. 2023. "Predictive Maintenance for Distribution System Operators in Increasing Transformers’ Reliability" Electronics 12, no. 6: 1356, https://doi.org/10.3390/electronics12061356. [Cross Ref]

G V S S N Srirama Sarma, B Ravindranath Reddy, Pradeep M Nirgude and P Vasudeva Naidu (2023), Performance Assessment of Customized LSTM based Deep Learning Model for Predictive Maintenance of Transformer. IJEER 11(2), 389-400. DOI: 10.37391/IJEER.110220.