Predictive AI Maintenance of Distribution Oil‐Immersed Transformer via Multimodal Data Fusion: A New Dynamic Multiscale Attention CNN‐LSTM Anomaly Detection Model for Industrial Energy Management

Elvis Tamakloe; Benjamin Kommey; Jerry John Kponyo; Eric Tutu Tchao; Andrew Selasi Agbemenu; Griffith Selorm Klogo

doi:10.1049/elp2.70011

journal article Open Access Jan 01, 2025

Predictive AI Maintenance of Distribution Oil‐Immersed Transformer via Multimodal Data Fusion: A New Dynamic Multiscale Attention CNN‐LSTM Anomaly Detection Model for Industrial Energy Management

Elvis Tamakloe Benjamin Kommey

Jerry John Kponyo Eric Tutu Tchao

Andrew Selasi Agbemenu

Griffith Selorm Klogo

IET Electric Power Applications Vol. 19 No. 1 · Institution of Engineering and Technology (IET)

View at Publisher Save 10.1049/elp2.70011

Abstract

ABSTRACT
Reactive and preventive maintenance strategies have been applied to avert transformer failures and safeguard their operations. However, these approaches have limitations of high operational downtimes, over‐ and under‐maintenance issues, maintenance fatigue and revenue loss. The advancements in machine learning and artificial intelligence have positively altered the machine and equipment maintenance landscape. Thus, predictive maintenance (PdM), in contrast to the above‐listed maintenance approaches, has laid the foundation for improving transformer maintenance by identifying incipient failures to solve the existing challenges. Recent developments in predictive maintenance of distribution power transformers have made great strides, but to solve the current challenge of accurate fault identification, this study proposed a new model architecture (DMSA CNN‐LSTM) using multimodal data fusion to address anomaly detection. A classification accuracy, F1‐score, precision and recall of 0.9917, 0.9714, 0.9781 and 0.9647, respectively, were produced on a fused multimodal dataset at a computational time of 619.898 s. The performance was afterwards evaluated against other state‐of‐the‐art benchmark models. The significance of this study lies in providing a scalable data‐driven architecture suitable for real‐time deployment in providing predictive solutions for transformers at a higher performance efficiency. This approach leverages deep neural networks that provide a comprehensive diagnostic and prognostic approach to mitigate transformer faults and breakdowns.

Topics

No keywords indexed for this article. Browse by subject →

References

77

[1]

10.1016/j.jmsy.2019.11.002

[2]

10.2991/icoemis-19.2019.59

[3]

10.1016/j.ress.2017.05.041

[4]

10.1109/gpecom49333.2020.9247887

[5]

10.1016/j.engfailanal.2019.02.014

[6]

10.1016/j.egyr.2021.11.084

[7]

Evans K. (2021)

[8]

10.3390/s23135970

[9]

10.1109/icais50930.2021.9395903

[10]

Population–Urbanization–Energy Nexus: A Review

Ram Avtar, Saurabh Tripathi, Ashwani Kumar et al.

Resources 10.3390/resources8030136

[11]

10.1007/s00521‐022‐07366‐3

[12]

10.1016/j.ijepes.2012.07.026

[13]

10.1016/j.cie.2020.106889

[14]

10.1109/tpwrd.2019.2900543

[15]

10.1109/induscon51756.2021.9529721

[16]

10.1049/iet‐gtd.2017.1862

[17]

10.1109/tpwrd.2022.3152745

[18]

10.1016/j.ijepes.2021.107356

[19]

10.1109/access.2022.3174860

[20]

10.1016/j.ress.2022.109043

[21]

10.1108/jqme‐06‐2021‐0052

[22]

10.1016/j.epsr.2021.107519

[23]

10.1109/tdei.2023.3253463

[24]

10.3390/en5041081

[25]

Overview and Partial Discharge Analysis of Power Transformers: A Literature Review

Md Rashid Hussain, Shady S. Refaat, Haitham Abu-Rub

IEEE Access 10.1109/access.2021.3075288

[26]

10.1109/jsen.2021.3066809

[27]

10.1049/iet‐smt.2015.0076

[28]

10.1109/access.2020.3038386

[29]

Koroglu S. "A Case Study on Fault Detection in Power Transformers Using Dissolved Gas Analysis and Electrical Test Methods" Journal of Electrical Systems (2016)

[30]

10.1109/icpeca47973.2019.8975638

[31]

10.3390/en16217430

[32]

Fault detection and diagnosis in power transformers: a comprehensive review and classification of publications and methods

Ali Reza Abbasi

Electric Power Systems Research 10.1016/j.epsr.2022.107990

[33]

10.1049/hve.2017.0026

[34]

10.1016/j.ijepes.2023.109606

[35]

10.1109/tim.2020.2975386

[36]

10.1049/gtd2.12149

[37]

10.1049/esi2.12012

[38]

10.3390/en13102644

[39]

Partial Discharge Detection Using Piezoelectric Sensors on Power Transformer: A Review

Sorokhaibam Nilakanta Meitei

IEEE Sensors Journal 10.1109/jsen.2024.3379037

[40]

10.1016/j.rser.2024.114327

[41]

10.1002/tee.23328

[42]

10.1016/j.engfailanal.2021.105356

[43]

10.3390/en16124626

[44]

10.1109/tdei.2020.008965

[45]

10.1016/j.ijepes.2020.106748

[46]

10.31185/ejuow.vol11.iss2.445

[47]

10.3390/en14164997

[48]

10.1016/j.rser.2017.05.165

[49]

(1986)

[50]

(2023)

Showing 50 of 77 references

Metrics

12

Citations

77

References

Details

Published: Jan 01, 2025
Vol/Issue: 19(1)
License: View

Authors

E

Elvis Tamakloe