Disconnector Fault Diagnosis Based on Multi-Granularity Contrast Learning

被引:1
作者
Xie, Qian [1 ]
Tang, Haiyi [1 ]
Liu, Baize [1 ]
Li, Hui [1 ]
Wang, Zhe [2 ]
Dang, Jian [1 ]
机构
[1] Xian Univ Technol, Sch Elect Engn, Xian 710048, Peoples R China
[2] Xian Univ Technol, Inst Water Resources & Hydroelect Engn, Xian 710048, Peoples R China
关键词
disconnector; fault diagnosis; contrastive learning; multi-granularity; continuous wavelet transform; DATA AUGMENTATION; TIME-SERIES;
D O I
10.3390/pr11102981
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Most disconnector fault diagnosis methods have high accuracy in model training. However, it is a challenging task to maintain high accuracy, a faster diagnosis speed, and less computation in practical situations. In this paper, we propose a multi-granularity contrastive learning (MG-CL) framework. First, the original disconnector current data are transformed into two different but related classes: strongly enhanced and weakly enhanced data, by using the strong and weak enhancement modules. Second, we propose the coarse-grained contrastive learning module to preliminarily judge the possibility of faults by learning the features of strongly/weakly enhanced data. Finally, in order to further judge the fault causes, we propose a fine-grained contrastive learning module. By comparing the differences in the data, the final fault type was judged. Our proposed MG-CL framework shows higher accuracy and speed compared with the previous model.
引用
收藏
页数:21
相关论文
共 36 条
[1]   An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition [J].
Ahmed, Md. Rayhan ;
Islam, Salekul ;
Islam, A. K. M. Muzahidul ;
Shatabda, Swakkhar .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 218
[2]   The Performance Analysis of Time Series Data Augmentation Technology for Small Sample Communication Device Recognition [J].
Cai, Zhuoran ;
Ma, Wenxuan ;
Wang, Xinrui ;
Wang, Hanhong ;
Feng, Zhongming .
IEEE TRANSACTIONS ON RELIABILITY, 2023, 72 (02) :574-585
[3]  
Chen Q., 2023, P 2023 IEEE 3 INT C
[4]   Unsupervised Visual Representation Learning via Multi-Dimensional Relationship Alignment [J].
Cheng, Haoyang ;
Li, Hongliang ;
Qiu, Heqian ;
Wu, Qingbo ;
Zhang, Xiaoliang ;
Meng, Fanman ;
Ngan, King Ngi .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 :1613-1626
[5]   A Data-Driven Fine-Management and Control Method of Gas-Extraction Boreholes [J].
Cheng, Xiaoyang ;
Sun, Haitao .
PROCESSES, 2022, 10 (12)
[6]   On Mutual Information-Based Optimal Quantizer Design [J].
Dulek, Berkan .
IEEE COMMUNICATIONS LETTERS, 2022, 26 (05) :1008-1011
[7]   An expert-based investigation of the Common Vulnerability Scoring System [J].
Holm, Hannes ;
Afridi, Khalid Khan .
COMPUTERS & SECURITY, 2015, 53 :18-30
[8]   Self-Supervision-Augmented Deep Autoencoder for Unsupervised Visual Anomaly Detection [J].
Huang, Chao ;
Yang, Zehua ;
Wen, Jie ;
Xu, Yong ;
Jiang, Qiuping ;
Yang, Jian ;
Wang, Yaowei .
IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (12) :13834-13847
[9]   An Improved Method for Total Radiated Power Tests in Anechoic Chambers [J].
Huang, Shan ;
Li, Furong ;
Chen, Xiaoming .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[10]   A New Data Augmentation Method for Time Series Wearable Sensor Data Using a Learning Mode Switching-Based DCGAN [J].
Jeon, Haneul ;
Lee, Donghun .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) :8671-8677