Construction of intelligent transformer anomaly detection model based on LSTM combined with optical flow features
More details
Hide details
1
School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand
Submission date: 2024-08-21
Final revision date: 2024-12-20
Acceptance date: 2025-02-19
Online publication date: 2025-02-24
Corresponding author
Shuzong Zhao
School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand
Diagnostyka 2025;26(1):2025115
KEYWORDS
TOPICS
ABSTRACT
Transformers are very important for the transmission and distribution of electricity,but due to changes in load and the influence of the working environment,various faults may occur in transformers.To accurately and quickly detect faults in transformers,conduct effective fault diagnosis and equipment maintenance,this study solves the problems of data imbalance and temporal data in transformers by introducing a long short-term memory network with fatigue factors.In addition,a fusion model is ultimately constructed by combining the recursive all-pair field transformation streamer method to achieve more accurate and robust optical flow estimation in the model.The experiment indicated that the maximum accuracy of the predicted values combined with the model was around 95%,and the minimum was around 35%.Compared to other models,the maximum accuracy of actual values was around 80%, and the minimum accuracy was better at 10%.In the application experiment,the frequency of insulation faults was the least obvious, with only 10 faults.The resistance fault was evident,with a total of 100 faults.The combined model could well reflect the fluctuation of fault current and the collection of fault number by different sensors.Therefore, the proposed model has high accuracy,good precision, and outstanding application effects,which can provide new ideas for the construction of intelligent transformer anomaly detection models.
REFERENCES (22)
1.
Choudhuri S, Adeniye S, Sen A. Distribution alignment using complement entropy objective and adaptive consensus-based label refinement for partial domain adaptation. Artificial Intelligence and Applications 2023;1(1):43-51.
https://doi.org/10.47852/bonvi....
2.
Long XM, Chen YJ, Zhou J. Development of AR experiment on electric-thermal effect by open framework with simulation-based asset and User-Defined Input. Artificial Intelligence and Applications 2023;1(1):52-57.
https://doi.org/10.47852/bonvi....
3.
Amanul I, Othman F, Sakib N, Babu HMH. Prevention of Shoulder-Surfing attack using shifting condition with the digraph substitution rules. Artificial Intelligence and Applications 2023;1(1):58-68.
https://doi.org/10.48550/arXiv....
4.
Zhang ZP, Wang GB. LSTM network optimization and task network construction based on heuristic algorithm. Journal of Computational Methods in Sciences and Engineering, 2024;24(2):697-714.
https://doi.org/10.3233/JCM-23....
5.
Feng Q, Tu Y, Hou C, Cao B. TLN-LSTM: An automatic modulation recognition classifier based on a two-layer nested structure of LSTM network for extremely long signal sequences. International Journal of Web Information Systems 2024;20(3):248-267.
https://doi.org/10.1108/IJWIS-....
6.
He Y, Pang Y. Automatic detection of transformer health based on bayesian network model. Applied Mathematics and Nonlinear Sciences 2023;8(2):2069-2076.
https://doi.org/10.2478/amns.2....
7.
Duval M, Buchacz J. Detection of carbonization of paper in transformers using duval pentagon 2 and triangle 5. IEEE Transactions on Dielectrics and Electrical Insulation 2023;30(4):1534-1539.
https://doi.org/10.1109/TDEI.2....
8.
Kia MY, Saniei MS, Seyyed G. A novel cyber-attack modelling and detection in overcurrent protection relays based on wavelet signature analysis. IET Generation, Transmission & Distribution 2023;17(7): 1585-1600.
https://doi.org/10.1049/gtd2.1....
9.
Doorwar A, Bhalja BR, Malik OP. Novel approach for synchronous generator protection using new differential component. Transactions on Energy Conversion 2023;38(1):180-191.
https://doi.org/10.1109/TEC.20....
10.
Pramanik S, Ganesh A, Duvvury Chaitanya VSB. Double-End Excitation of a Single Isolated Transformer Winding: An improved frequency response analysis for fault detection. IEEE Transactions on Power Delivery 2022;37(1):619-626.
https://doi.org/10.1109/TPWRD.....
11.
Eruvai M, Chilaka R. Oil health index calculation and incipient fault diagnosis in power transformers using fuzzy logic. Insight: Non-Destructive Testing and Condition Monitoring 2022; 64(1): 28-37.
https://doi.org/10.1784/insi.2....
13.
Windmann S, Westerhold T. Fault detection in automated production systems based on a long short-term memory autoencoder. at - Automatisierungstechnik 2024;72(1):47-58.
https://doi.org/10.1515/auto-2....
14.
Aljemely AH, Xuan J, Al-Azzawi O, Jawad FKJ. Intelligent fault diagnosis of rolling bearings based on LSTM with large margin nearest neighbor algorithm. Neural Computing and Applications 2022;34(22): 19401-19421.
https://doi.org/10.1007/s00521....
15.
Sun HB, Fan YG. Fault diagnosis of rolling bearings based on CNN and LSTM networks under mixed load and noise. Multimedia Tools and Applications 2023; 82(28): 43543-43567.
https://doi.org/10.1007/s11042....
16.
Sampat C, Ramachandran R. Optimizing energy efficiency of a twin-screw granulation process in Real-Time Using a Long Short-Term Memory (LSTM) Network. ACS Engineering Au 2024;4(2):278-289.
https://doi.org/10.1021/acseng....
17.
Bouziane SE, Khadir MT. Towards an energy management system based on a multi-agent architecture and LSTM networks. Journal of Experimental & Theoretical Artificial Intelligence 2024;3(4):469-487.
https://doi.org/10.1080/095281....
18.
Li WT. Construction and analysis of QPSO-LSTM model in network security situation prediction. Journal of Cyber Security and Mobility 2024;13(3):417-438.
https://doi.org/10.13052/jcsm2....
19.
Bian C, Huang G. Predicting PM2.5 concentration with enhanced state-trend awareness and uncertainty analysis using bagging and LSTM neural networks. Journal of Environmental Quality 2024;53(4):441-455.
https://doi.org/10.1002/jeq2.2....
20.
Shen Z, Liu X, Li W, Li XY, Wang Q. Classification of visually induced motion sickness based on phase-locked value functional connectivity matrix and CNN-LSTM. Sensors (Basel, Switzerland) 2024;24(12): 3936-3936.
https://doi.org/10.3390/s24123....
21.
Ding C, Zhao J, Sun S. Concept drift adaptation for time series anomaly detection via transformer. Neural Processing Letters 2023;55(3):2081-2101.
https://doi.org/10.1007/s11063....
22.
Jin X, Ma C, Luo S, Zeng P, Wei Y. Distributed IIoT anomaly detection scheme based on blockchain and federated learning. Journal of Communications and Networks 2024;26(2):252-262.
https://doi.org/10.23919/JCN.2....