跳到主要导航 跳到搜索 跳到主要内容

Data-Driven Fault Diagnosis Method for UAV Sensors Based on Spatiotemporal Cross Attention

  • Zhonghan Li
  • , Yongbo Zhang*
  • , Yutong Shi
  • , Jianchao Guo
  • , Shihao Zhu
  • , Ling Wang
  • *此作品的通讯作者
  • Beihang University
  • Peking University
  • Chongqing Institute of Technology

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Unmanned aerial vehicles (UAV) sensor fault diagnosis faces the challenges of imbalanced class and data coupling. This paper proposes a novel data-driven method, Parallel CNN-LSTM with Cross Attention (PCL-CA), which enhances the model's feature extraction capability by introducing spatiotemporal cross-attention. A parallel architecture is designed, and enhanced data is generated using multi-rate EKF, ensuring the model achieves excellent fault diagnosis performance even in the presence of imbalanced class. Experimental results show that the proposed PCL-CA method exhibits the most robust performance across four performance metrics, achieving a precision of 92.8% and an F1 score of 93.1, significantly outperforming the CNN, LSTM, BiLSTM and CNN-TransNet baseline models.

源语言英语
主期刊名2025 16th International Conference on Mechanical and Aerospace Engineering, ICMAE 2025
出版商Institute of Electrical and Electronics Engineers Inc.
242-247
页数6
ISBN(电子版)9798331513672
DOI
出版状态已出版 - 2025
活动16th International Conference on Mechanical and Aerospace Engineering, ICMAE 2025 - Rome, 意大利
期限: 15 7月 202518 7月 2025

出版系列

姓名2025 16th International Conference on Mechanical and Aerospace Engineering, ICMAE 2025

会议

会议16th International Conference on Mechanical and Aerospace Engineering, ICMAE 2025
国家/地区意大利
Rome
时期15/07/2518/07/25

学术指纹

探究 'Data-Driven Fault Diagnosis Method for UAV Sensors Based on Spatiotemporal Cross Attention' 的科研主题。它们共同构成独一无二的学术指纹。

引用此