Research on Ant Lion Optimization Algorithm for BP Neural Network in Transformer Fault Diagnosis

DOI: https://doi.org/10.62517/jbdc.202401301

Author(s)

Hao Guo*

Affiliation(s)

Inner Mongolia Power (Group) Co., Ltd, Hohhot Power Supply Branch, Hohhot, Inner Mongolia, China *Corresponding Author.

Abstract

Aiming at the problem of low accuracy in transformer fault diagnosis, an Ant Lion Optimization (ALO) algorithm is proposed to optimize the BP neural network for transformer fault diagnosis. By using the ant lion optimization algorithm to optimize the weights and thresholds of the BP neural network, the problem of premature convergence of the BP neural network can be avoided, and the accuracy of the transformer fault diagnosis model can be improved. The BP neural network model optimized by the ant lion optimization algorithm was used for transformer fault diagnosis. To verify the effectiveness of the proposed method, it was compared with the genetic algorithm optimized BP neural network (GA-BP) and the artificial bee colony (ABC-BP) algorithm optimized BP neural network methods. The experimental results showed that the proposed method has higher fault diagnosis accuracy.

Keywords

Transformer; Fault Diagnosis; BP Neural Network; Ant Lion Optimization Algorithm; Artificial Bee Colony Algorithm

References

[1]Abbasi A R, Mahmoudi M R, Avazzadeh Z. Diagnosis and clustering of power transformer winding fault types by cross-correlation and clustering analysis of FRA results. IET Generation, Transmission & Distribution, 2018, 12(19): 4301-4309. [2]Wang T, He Y, Li B, et al. Fault diagnosis of transformer based on self-powered RFID sensor tag and improved HHT. Journal of Electrical Engineering and Technology, 2018, 13(5): 2134-2143. [3]Lv G, Cheng H, Zhai H, et al. Fault diagnosis of power transformer based on multi-layer SVM classifier. Electric Power Systems Research, 2005, 75(1): 9-15. [4]Khan S A, Equbal M D, Islam T. A comprehensive comparative study of DGA based transformer fault diagnosis using fuzzy logic and ANFIS models. IEEE Transactions on Dielectrics & Electrical Insulation, 2015, 22(1): 590-596. [5]Alghamdi A S, Muhamad N A, Suleiman A A. DGA Interpretation of Oil Filled Transformer Condition Diagnosis. Transactions on Electrical and Electronic Materials, 2012, 13(5): 229-232. [6]Jingmin, Fan, Feng, et al. Hybrid RVM–ANFIS algorithm for transformer fault diagnosis. IET Generation, Transmission & Distribution, 2017, 11(14): 3637-3643. [7]Khan, Shakeb, A, et al. A Comprehensive Comparative Study of DGA Based Transformer Fault Diagnosis Using Fuzzy Logic and ANFIS Models. IEEE transactions on dielectrics and electrical insulation: A publication of the IEEE Dielectrics and Electrical Insulation Society, 2015, 22(1): 590-596. [8] Dong M, Zhao W, Yan Z. Improved method for transformer fault diagnosis based on DGA. High Voltage Engineering, 2002, 28(4): 6-8. [9]Duraisamy P, Santhanakrishnan M N, Amirtharajan R. Genetic Algorithm Optimized Grey-Box Modelling and Fuzzy Logic Controller for Tail-Actuated Robotic Fish. Neural processing letters, 2023, 55(8): 11577-11594. [10]Mansouri M, Bey M, Hassaine S, et al. Genetic algorithm optimized robust nonlinear observer for a wind turbine system based on permanent magnet synchronous generator. ISA transactions, 2022, 129(Pt B):230-242. [11]Shao R, Zhang G, Gong X. Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components. Photonics Research, 2022(8): 1868-1876. [12]Esfe M H, Hajmohammad H, Toghraie M D. Cost and Efficiency Optimizations of ZnO/EG Nanofluids Using Non-dominated Sorting Genetic Algorithm Coupled with a Statistical Method. The Korean journal of chemical engineering, 2024, 41(1): 175-186. [13]Pan Y, Yang Y, Li L W. UAVs and Mobile Sensors Trajectories Optimization with Deep Learning Trained by Genetic Algorithm towards Data Collection Scenario. Mobile networks & applications, 2023, 28(2): 808-823. [14]Chen H, Tang Q, Li X, et al. Optimization of five-axis tool grinder structure based on BP neural network and genetic algorithm. The International Journal of Advanced Manufacturing Technology, 2024, 133(5-6): 2565-2582. [15]Mpuang A P, Shibutani T. Improvements in the genetic algorithm inversion of receiver functions using extinction and a new selection approach. Computational Geosciences, 2024, 28(3): 573-585. [16]Ali E S, Abd Elazim S M, Abdelaziz A Y. Ant Lion Optimization Algorithm for Renewable Distributed Generations. Energy, 2016, 116(pt.1): 445-458.