Series Arc Fault Identification in DC Distribution Based on Random Forest Predicted Probability
Abstract
Series dc arc fault generates arcing noise making it challenging to identify the arc fault location and thus endangering the systems safety. This study proposes a series arc fault identification method in a dc zonal electrical distribution using Random Forest based local detectors to monitor constant power loads, and output predicted nominal and arc fault probabilities. With full communication capability among all local detectors, the master detector makes the final decision using Random Forest algorithms. The proposed fault identification method is experimentally verified with a zonal electrical distribution testbed that comprises three constant power loads.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 2023
- Accession Number
- AD1219078
Entities
People
- Bang-hung Tsao
- Chad R. Miller
- Vu Le
- Xiu Yao
Organizations
- University at Buffalo
- University of Dayton