LAPSE:2023.26192
Published Article
LAPSE:2023.26192
Pattern Recognition of DC Partial Discharge on XLPE Cable Based on ADAM-DBN
Zhe Li, Yongpeng Xu, Xiuchen Jiang
March 31, 2023
Pattern recognition of DC partial discharge (PD) receives plenty of attention and recent researches mainly focus on the static characteristics of PD signals. In order to improve the recognition accuracy of DC cable and extract information from PD waveforms, a modified deep belief network (DBN) supervised fine-tuned by the adaptive moment estimation (ADAM) algorithm is proposed to recognize the four typical insulation defects of DC cable according to the PD pulse waveforms. Moreover, the effect of the training sample set size on recognition accuracy is analyzed. Compared with naive Bayes (NB), K-nearest neighbor (KNN), support vector machine (SVM), and back propagation neural networks (BPNN), the ADAM-DBN method has higher accuracy on four different defect types due to the excellent ability in terms of the feature extraction of PD pulse waveforms. Moreover, the increase of training sample set size would lead to the increase of recognition accuracy within a certain range.
Keywords
adaptive moment estimation (ADAM), DC cross linked polyethylene (XLPE) cable, deep belief network (DBN), partial discharge (PD), restricted Boltzmann machines (RBM)
Suggested Citation
Li Z, Xu Y, Jiang X. Pattern Recognition of DC Partial Discharge on XLPE Cable Based on ADAM-DBN. (2023). LAPSE:2023.26192
Author Affiliations
Li Z: Academy of Information Technology and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Xu Y: Academy of Information Technology and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China [ORCID]
Jiang X: Academy of Information Technology and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Journal Name
Energies
Volume
13
Issue
17
Article Number
E4566
Year
2020
Publication Date
2020-09-03
Published Version
ISSN
1996-1073
Version Comments
Original Submission
Other Meta
PII: en13174566, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2023.26192
This Record
External Link

doi:10.3390/en13174566
Publisher Version
Download
Files
[Download 1v1.pdf] (3.3 MB)
Mar 31, 2023
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
146
Version History
[v1] (Original Submission)
Mar 31, 2023
 
Verified by curator on
Mar 31, 2023
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2023.26192
 
Original Submitter
Auto Uploader for LAPSE
Links to Related Works
Directly Related to This Work
Publisher Version