Artificial Neural Network-Based Fault Detection and Classification for Enhanced Reliability in Electrical Power Transmission Networks

Takudzwa Marshal Makumbirofa,Sheetla Prasad

Published 2025 in 2025 IEEE International Conference on Computer, Electronics, Electrical Engineering & their Applications (IC2E3)

ABSTRACT

The electrical power transmission networks (EPTNs), playing major role to transmit electrical power from location to remote location. The faults in the EPTN may degrade the performance of the whole networks even leads to inconstancy of power supply. Thus, the fault classification-based detection is essential to maintain the reliability of EPTN. However, Artificial Neural Network (ANN) is utilized to precisely detect the faults such as line-to-ground, line-to-line, three phase fault, double-line to line and transient etc. The ANN is utilized to train and update the weights of neurons in hidden layer both sides using featured data sets as inputs. The features are classified based on the type of faults based on signal characterization are extracted via time-domain and frequency-domain using fast Fourier Transform (FFT) and discrete Wavelet Transform. Validation of the model is done with MATLAB simulation, resulting in excellent faults detection and classification. A scatter plot of voltage and current shows clear clusters for different faults, highlighting the ANN’s capability to distinguish between various network contingency states. As a result, the reliability of the EPTNs is improved with suggested method. The results demonstrate that ANNs are a reliable, scalable, and extraction method for fault classification for modern power grids with significant potential in enhancing the stability and operating performance of power networks.

PUBLICATION RECORD

  • Publication year

    2025

  • Venue

    2025 IEEE International Conference on Computer, Electronics, Electrical Engineering & their Applications (IC2E3)

  • Publication date

    2025-05-15

  • Fields of study

    Not labeled

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-18 of 18 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1