A data-driven fault detection scheme for DC distribution networks based on the adaptive boosting technique

Bo Li, Kai Liao, Jianwei Yang and Zhengyou He

Applied Energy, 2024, vol. 374, issue C, No S0306261924013321

Abstract: Direct current (dc) distribution networks are rapidly growing, but they still face serious challenges of severe converter damage due to low inertia, short fault duration, and fast-growing dc fault currents. In this regard, a data-driven fault detection scheme for dc distribution networks is presented using machine learning techniques. To have a good fault detection capability of dc distribution networks, the fault characteristics of the faulted and healthy dc lines are analyzed with lots of fault data. After preprocessing, the fault feature vector is constructed to identify the faulted line using multi-dimensional fault features. Additionally, the adaptive boosting technique, which is a kind of machine learning, is used for the data-driven fault detection scheme. It is yielded with the abilities of fault identification and fault pole discrimination, tolerance to fault location, transition resistance, and noise interference. Further, a large amount of fault data is obtained by PSCAD/EMTDC to verify the proposed detection scheme. Test results demonstrate that the proposed fault detection scheme can achieve sensitive and accurate fault identification and fault pole selection within 2.5 ms. The proposed scheme is immune to noise interference and effectively adapts to changes in voltage level and topology with high accuracy.

Keywords: Fault detection; DC distribution networks; Fault feature vector; Adaptive boosting technique (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261924013321
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:374:y:2024:i:c:s0306261924013321

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.123949

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().