Collaborative Multi-Teacher Distillation for Multi-Task Fault Detection in Power Distribution Grid

被引:0
作者
Huang, Bingzheng [1 ]
Ni, Chengxin [1 ]
Song, Junjie [1 ]
Yin, Yifan [1 ]
Chen, Ningjiang [1 ]
机构
[1] Guangxi Univ, Sch Comp & Elect Informat, Nanning, Peoples R China
来源
PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024 | 2024年
基金
中国国家自然科学基金;
关键词
knowledge distillation; multi-task collaboration; deep learning; fault detection;
D O I
10.1109/CSCWD61410.2024.10580632
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Under the background of complicated fault detection scenarios and diversified data in the current power distribution grid, it is a significant challenge to deploy high-performance fault detection models for efficient multi-task collaboration processing on lightweight edge intelligent devices. A collaborative multi-teacher distillation for multi-task fault detection in the power distribution grid(CMT-KD) is introduced, which enhances multi-task fault detection by redefining Residual Network (ResNet). We further implement model compression and acceleration by adopting the weight quantization method, while enhancing the performance of the multi-task fault detector via dynamically adapting the knowledge weights from multiple teachers. The proposed method allows for the detection of multiple power distribution grid faults with a single model, significantly reducing the number of model parameters, floating point operations, and training time, while also demonstrating favorable performance in terms of improving accuracy and reducing prediction errors.
引用
收藏
页码:2638 / 2643
页数:6
相关论文
共 20 条
  • [1] Belagoune S., 2021, MEASUREMENT, V177
  • [2] Wavelet LSTM for Fault Forecasting in Electrical Power Grids
    Branco, Nathielle Waldrigues
    Matos Cavalca, Mariana Santos
    Stefenon, Stefano Frizzo
    Quietinho Leithardt, Valderi Reis
    [J]. SENSORS, 2022, 22 (21)
  • [3] Du S., 2020, Advances in Neural Information Processing Systems, V33, P12345
  • [4] ML-Based Intermittent Fault Detection, Classification, and Branch Identification in a Distribution Network
    Hojabri, Mojgan
    Nowak, Severin
    Papaemmanouil, Antonios
    [J]. ENERGIES, 2023, 16 (16)
  • [5] Ibitoye Oladapo Tolulope, 2022, 2022 3rd International Conference on Electrical Engineering and Informatics (ICon EEI), P104, DOI 10.1109/IConEEI55709.2022.9972279
  • [6] A neural network compression method based on knowledge-distillation and parameter quantization for the bearing fault diagnosis
    Ji, Mengyu
    Peng, Gaoliang
    Li, Sijue
    Cheng, Feng
    Chen, Zhao
    Li, Zhixiong
    Du, Haiping
    [J]. APPLIED SOFT COMPUTING, 2022, 127
  • [7] A probabilistic classifier ensemble weighting scheme based on cross-validated accuracy estimates
    Large, James
    Lines, Jason
    Bagnall, Anthony
    [J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2019, 33 (06) : 1674 - 1709
  • [8] A Novel Intelligent Method for Fault Diagnosis of Steam Turbines Based on T-SNE and XGBoost
    Liang, Zhiguo
    Zhang, Lijun
    Wang, Xizhe
    [J]. ALGORITHMS, 2023, 16 (02)
  • [9] Cloud-Edge-End Cooperative Detection of Wind Turbine Blade Surface Damage Based on Lightweight Deep Learning Network
    Liu, Yajuan
    Wang, Zhen
    Wu, Xiaolun
    Fang, Fang
    Saqlain, Ali Syed
    [J]. IEEE INTERNET COMPUTING, 2023, 27 (01) : 43 - 51
  • [10] Mingxuan Li, 2021, 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), P476, DOI 10.1109/ICBAIE52039.2021.9389826