AUTHOR=Duan Dawei , Ma Hongzhong , Yang Qifan , Li Nan 

TITLE=Fault diagnosis of free-conducting particles within GIL based on vibration signals

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1088549

DOI=10.3389/fenrg.2023.1088549

ISSN=2296-598X

ABSTRACT=Free-conducting particle fault is a serious safety hazard for gas insulated line (GIL). How to diagnose the free-conducting particle faults in a quantitative manner becomes an open and challenging issue. This paper proposes a vibration signal-based fault diagnosis method to accurately identify the free-conducting particle faults with different quantities and sizes. The proposed method integrates variational mode decomposition (VMD), self-adapting whale optimization algorithm-multiscale permutation entropy (SAWOA-MPE) and deep forest (DF). First, the raw vibration signals of free-conducting particle faults are decomposed via VMD, and the decomposed signals are reconstructed based on the correlation degree. Then, SAWOA is employed to optimize the critical parameters of MPE, and the optimized MPE is utilized to extract the fault features of the reconstructed signals. Finally, the extracted feature vectors are trained and tested to construct a valid DF classification model that identifies the free-conducting particle faults. The experimental results indicate that the identification accuracy of the proposed method can reach 99.5%. Moreover, comparative tests based on various feature vector extraction methods and classification models further validate the superiority of the proposed method.