•  
  •  
 

Journal of System Simulation

Abstract

Abstract: Aiming at the inability of existing intelligent algorithms for transformer fault diagnosis to quickly and efficiently identify transformer faults, resulting in fault misdetection and untimely detection, this paper proposes a transformer fault diagnosis method using the improved sparrow optimization algorithm to optimize the two-layer fault diagnostic model of XGBoost combined with the digital twin technology. The method adopts advanced sensors to collect oil and gas data and temperature data of the transformer, uses 5G module to transmit the real-time data to the digital twin system. The system monitors the temperature data in real-time by setting the equipment alarm threshold; optimizes the twolayer fault diagnostic model of XGBoost using the improved sparrow optimization algorithm to process real-time fault identification of the oil and gas data, and finally identifies and warns of faults by combining with the digital twin technology. Experimental results indicate that this method significantly enhances the efficiency and stability of fault identification and early warning, demonstrating substantial advantages compared to existing transformer fault diagnosis methods.

First Page

775

Last Page

790

CLC

TP274; TM41

Recommended Citation

Jiang Lun, Wang Dajiang, Sun Wenlei, et al. Research on Transformer Fault Diagnosis Method Based on Digital Twin[J]. Journal of System Simulation, 2025, 37(3): 775-790.

Corresponding Author

Sun Wenlei

DOI

10.16182/j.issn1004731x.joss.23-1402

Download

Share

COinS