TY - JOUR
T1 - Identify incipient faults through similarity comparison with waveform split-recognition framework
AU - Tang, Xinlu
AU - Cui, Qiushi
AU - Weng, Yang
AU - Su, Yuxiang
AU - Li, Dongdong
N1 - Funding Information:
This work was supported by the National Key Research and Development Program (No. 2018YFB2100100).
Publisher Copyright:
Copyright © 2023 Tang, Cui, Weng, Su and Li.
PY - 2023
Y1 - 2023
N2 - Introduction: Incipient faults of distribution networks, if not detected at an early stage, could evolve into permanent faults and result in significant economic losses. It is necessary to detect incipient faults to improve power grid security. However, due to the short duration and unapparent waveform distortion, incipient faults are difficult to identify. In addition, incipient faults usually have a small data volume, which compromises their pattern recognition. Methods: In this paper, an incipient fault identification method is proposed to address these problems. First, a Waveform Split-Recognition Framework (WSRF) is proposed to provide a two-step process: 1) split waveform into several segments according to cycles, and 2) recognize incipient faults through the similarity of decomposed segments. Second, we design a Similarity Comparison Network (SCN) to learn the waveform by sharing the weights of two Convolution Neural Networks (CNNs), and then calculate the gap between them through a non-linear function in high-dimensional space. Last, disassembled filters are devised to extract features from the waveform. Results: The method of initializing weights can improve the speed and Accuracy of training, and some existing datasets like MNIST consisting of 250 handwritten numbers from different people are able to provide initial weights to disassembled filters through the adaptive data distribution method. This paper uses field data and simulation data to verify the performance of SCN and WSRF. Discussion: WSRF can achieve more than 95% Accuracy in identifying incipient faults, which is much higher than three other methods in literature. And this method can achieve good results at different fault locations and different fault times. Which compromises their pattern recognition.
AB - Introduction: Incipient faults of distribution networks, if not detected at an early stage, could evolve into permanent faults and result in significant economic losses. It is necessary to detect incipient faults to improve power grid security. However, due to the short duration and unapparent waveform distortion, incipient faults are difficult to identify. In addition, incipient faults usually have a small data volume, which compromises their pattern recognition. Methods: In this paper, an incipient fault identification method is proposed to address these problems. First, a Waveform Split-Recognition Framework (WSRF) is proposed to provide a two-step process: 1) split waveform into several segments according to cycles, and 2) recognize incipient faults through the similarity of decomposed segments. Second, we design a Similarity Comparison Network (SCN) to learn the waveform by sharing the weights of two Convolution Neural Networks (CNNs), and then calculate the gap between them through a non-linear function in high-dimensional space. Last, disassembled filters are devised to extract features from the waveform. Results: The method of initializing weights can improve the speed and Accuracy of training, and some existing datasets like MNIST consisting of 250 handwritten numbers from different people are able to provide initial weights to disassembled filters through the adaptive data distribution method. This paper uses field data and simulation data to verify the performance of SCN and WSRF. Discussion: WSRF can achieve more than 95% Accuracy in identifying incipient faults, which is much higher than three other methods in literature. And this method can achieve good results at different fault locations and different fault times. Which compromises their pattern recognition.
KW - disassembled filters
KW - incipient faults identification
KW - one-shot learning
KW - similarity comparison network
KW - waveform split-recognition framework
UR - http://www.scopus.com/inward/record.url?scp=85150394915&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85150394915&partnerID=8YFLogxK
U2 - 10.3389/fenrg.2023.1132895
DO - 10.3389/fenrg.2023.1132895
M3 - Article
AN - SCOPUS:85150394915
SN - 2296-598X
VL - 11
JO - Frontiers in Energy Research
JF - Frontiers in Energy Research
M1 - 1132895
ER -