Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Future Energy

Transfer learning for power system fault location using artificial neural networks

View Full Paper
Ask AI
Bookmark
Share

Authors

SPStefanos PetridisPIPetros IliadisASAngelos Saverios Skembris

Discussion

Loading...

Member takes

Overview

Application of transfer learning improves fault classification accuracy and reduces computational time in power systems.

Key Points

  • Transfer learning accelerates fault detection in power systems, leading to significant improvements in training efficiency.
  • Fault classification performance increases, achieving reductions in training epochs by 40.6% to 61.0% across different feeders.
  • The analysis utilized various IEEE test feeders, including the 13-bus, 34-bus, 37-bus, and 123-bus systems.
  • Computational time is also reduced by 24.0% to 49.5%, enhancing the overall practical viability for utilities.

Cite This Study

Petridis et al. (2025) studied this question.

synapsesocial.com/papers/68c1a12754b1d3bfb60dbf42https://doi.org/10.55670/fpll.fuen.4.3.4
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine Learning Algorithm for Modelling and Analysis of Faults in Secondary Power Distribution Networks2025
  2. 2Fault Location in Distribution Network Based on RNN and Transfer Learning2024 · 3 citations
  3. 3FAULT DIAGNOSIS ON A POWER SYSTEM TRANSMISSION LINE USING NEURAL NETWORK2026
  4. 4Transmission Line Fault Isolation Using Artificial Intelligence via Neural Networks2025
  5. 5A method for determining the location and type of fault in transmission network using neural networks and power quality monitors2024 · 1 citations