Dual-module multi-head spatiotemporal joint network with SACGA for wind turbines fault detection

被引:0
作者
Wang, Tian [1 ]
Yin, Linfei [1 ]
机构
[1] Guangxi Univ, Sch Elect Engn, Nanning 530004, Guangxi, Peoples R China
基金
中国国家自然科学基金;
关键词
Auxiliary classifier generative adversarial; network; Fault detection; Spatiotemporal joint representation; Wind turbine; Imbalanced data; DIAGNOSIS; MODEL; LOAD;
D O I
10.1016/j.energy.2024.132906
中图分类号
O414.1 [热力学];
学科分类号
摘要
Fault detection in wind turbines (WTs) was commonly characterized by an imbalance of fault class data, which could lead to a degradation of fault detection performance. In addition, temporal and spatial interaction information is not considered in the fault detection process, which weakens the model performance. Based on the above problems, this study proposes a novel dual-module multi-head spatiotemporal joint network with slidingwindow auxiliary classifier generating adversary (DMSJN-SACGA). The proposed DMSJN-SACGA in this study consists of four parts: data generation, dual-module feature encoder, multi-head spatiotemporal joint representation, and fault classification decoder. Firstly, the designed SACGA module, which utilizes the labeled fault data of WTs, generates high-quality fault class data to alleviate the problem of imbalanced fault class data of WTs. Secondly, the designed dual-module spatiotemporal joint representation framework learns the interactions between spatial attribute representation and time sequence representation to realize spatiotemporal joint representation. Compared to training with real data only, the key metrics of macro-F1 are 0.23 higher and g-meanF1 are 0.332 higher for the proposed DMSJN-SACGA trained with the addition of generative data. Compared to the other baseline models, the proposed DMSJN-SACGA has a superior performance in realizing the effective classification of WTs fault detection.
引用
收藏
页数:16
相关论文
共 52 条
  • [1] Interpretable bilinear attention network with domain adaptation improves drug-target prediction
    Bai, Peizhen
    Miljkovic, Filip
    John, Bino
    Lu, Haiping
    [J]. NATURE MACHINE INTELLIGENCE, 2023, 5 (02) : 126 - 136
  • [2] GAN-Based Multi-Task Learning Approach for Prognostics and Health Management of IIoT
    Behera, Sourajit
    Misra, Rajiv
    Sillitti, Alberto
    [J]. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024, 21 (03) : 2742 - 2762
  • [3] Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series
    Bianchi, Filippo Maria
    Scardapane, Simone
    Lokse, Sigurd
    Jenssen, Robert
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (05) : 2169 - 2179
  • [4] Stochastic Dynamic Power Dispatch With Human Knowledge Transfer Using Graph-GAN Assisted Inverse Reinforcement Learning
    Chen, Junbin
    Yu, Tao
    Pan, Zhenning
    Zhang, Mengyue
    Lu, Guanhua
    Zhu, Kedong
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2024, 15 (03) : 3303 - 3315
  • [5] On Wilcoxon rank sum test for condition monitoring and fault detection of wind turbines
    Dao, Phong B.
    [J]. APPLIED ENERGY, 2022, 318
  • [6] eBoF: Interactive Temporal Correlation Analysis for Ensemble Data Based on Bag-of-Features
    Ding, Zhifei
    Han, Jiahao
    Qian, Rongtao
    Shen, Liming
    Chen, Siru
    Yu, Lingxin
    Zhu, Yu
    Liu, Richen
    [J]. IEEE TRANSACTIONS ON BIG DATA, 2023, 9 (06) : 1726 - 1737
  • [7] Deep Spatial-Temporal 2-D CNN-BLSTM Model for Ultrashort-Term LiDAR-Assisted Wind Turbine's Power and Fatigue Load Forecasting
    Dolatabadi, Amirhossein
    Abdeltawab, Hussein
    Mohamed, Yasser Abdel-Rady, I
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (04) : 2342 - 2353
  • [8] k-Nearest neighbour based approach for the protection of distribution network with renewable energy integration
    Gangwar, Amit Kumar
    Shaik, Abdul Gafoor
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2023, 220
  • [9] Real-time monitoring, fault prediction and health management for offshore wind turbine systems
    Gao, Zhiwei
    China, Peter Odgaard
    [J]. RENEWABLE ENERGY, 2023, 218
  • [10] Bilinear Graph Networks for Visual Question Answering
    Guo, Dalu
    Xu, Chang
    Tao, Dacheng
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (02) : 1023 - 1034