Title: A fault diagnosis of electrical equipment based on improved BP neural network

Authors: Xiaoli Xing; Jin Huang

Addresses: Intelligent Manufacturing Institute, Xinxiang Vocational and Technical College, Xinxiang, 453006, China ' Zhengzhou Commercial Technician College, Zhengzhou, 450000, China

Abstract: This study proposes a fault diagnosis method based on an improved BP neural network. Initially, signals from electrical equipment are collected and pre-processed to enhance data clarity and computational speed. Subsequently, spectral analysis techniques are utilised to isolate crucial feature data. Genetic Algorithms (GA) are then employed to optimise the initial weights and biases of the Back Propagation (BP) neural network, with fitness criteria and genetic operators implemented to accelerate network refinement. Finally, a BP neural network model is established to train the network, enabling recognition of complex correlations between fault patterns and features, and yielding accurate fault identification results. Experimental results demonstrate the proposed method maintains throughput above 45 Mbit/s while keeping dropout rates consistently below 0.3.

Keywords: improved BP neural network; electrical equipment; fault diagnosis; insulation failure.

DOI: 10.1504/IJCAT.2026.154041

International Journal of Computer Applications in Technology, 2026 Vol.78 No.4, pp.296 - 304

Received: 17 Feb 2025
Accepted: 10 Jun 2025
Published online: 10 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article