TY - GEN
T1 - Complex Power Quality Disturbance Identification Based on GAF-MTF Three-Channel Feature Fusion
AU - Shiheng, Li
AU - Zhiwei, Huang
AU - Zhihua, Yang
AU - Qinghong, Chen
AU - Dong, Yawen
AU - Kaicheng, Li
AU - Wentao, Yuan
AU - Aoao, Xu
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The diversification of equipment in power system and the complexity of operating conditions gradually lead to the development of power quality disturbance to the complex power quality disturbances(CPQDs) which is released simultaneously by multiple types of disturbance. It is important to identify the type of CPQDs reliably and effectively for the stable operation of power grid. In this paper, a CPQDs identification architecture based on GASF-GADF-MTF three-channel multi-dimensional feature fusion plus transformer is proposed. Firstly, the CPQDs singal is converted into RGB three-channel data by using Gram summing field(GASF), Gram-diff-field(GADF) and Markov-transfer-field(MTF). The two-dime image of feature fusion is obtained. Then the transformer network is used to classify and discriminate the two-dime images containing the complex power quality disturbance characteristics. Simulation results show that the proposed method is reliable and effective, and has the advantages of good noise robustness and strong generalization ability.
AB - The diversification of equipment in power system and the complexity of operating conditions gradually lead to the development of power quality disturbance to the complex power quality disturbances(CPQDs) which is released simultaneously by multiple types of disturbance. It is important to identify the type of CPQDs reliably and effectively for the stable operation of power grid. In this paper, a CPQDs identification architecture based on GASF-GADF-MTF three-channel multi-dimensional feature fusion plus transformer is proposed. Firstly, the CPQDs singal is converted into RGB three-channel data by using Gram summing field(GASF), Gram-diff-field(GADF) and Markov-transfer-field(MTF). The two-dime image of feature fusion is obtained. Then the transformer network is used to classify and discriminate the two-dime images containing the complex power quality disturbance characteristics. Simulation results show that the proposed method is reliable and effective, and has the advantages of good noise robustness and strong generalization ability.
KW - Dimension transformation
KW - Gram Angle field(GAF)
KW - Markov transfer field(MTF)
KW - Multi-feature fusion
KW - complex power quality disturbance(CPQDs)
KW - transformer
UR - https://www.scopus.com/pages/publications/85218180083
U2 - 10.1109/CIYCEE63099.2024.10846361
DO - 10.1109/CIYCEE63099.2024.10846361
M3 - 会议稿件
AN - SCOPUS:85218180083
T3 - 2024 IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2024
BT - 2024 IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2024
Y2 - 6 November 2024 through 8 November 2024
ER -