An integrated multi-head dual sparse self-attention network for remaining useful life prediction

Committed to accident prevention, prediction of remaining useful life (RUL) plays a crucial role in prognostics health management technology. Conventional convolutional neural network and long-short-term memory network have notable limitations in the size of convolution in processing temporal data and the associations between non-adjacent data when predicting the RUL, respectively. Although the proposal of the Transformer provides an opportunity to solve the shortcomings mentioned above, Transformer still has some limitations. Precisely, the Transformer model awaits in-depth research focusing on vital local regions and decreasing computational complexity. In this sense, this paper proposes a novel integrated multi-head dual sparse self-attention network (IMDSSN) based on a modified Transformer to predict the RUL. From two sparse perspectives, the proposed IMDSSN includes a multi-head ProbSparse self-attention network (MPSN) and a multi-head LogSparse self-attention network (MLSN). Specifically, MPSN is designed to filter out the primary function of the dot product operation, thereby improving computational efficiency. Furthermore, considering the data inside the whole time window, a comprehensive logarithmic-based sparse strategy in MLSN is proposed to reduce the amount of computation. An aircraft turbofan engine dataset is used to verify the proposed IMDSSN, which demonstrates that the IMDSSN is better than some conventional approaches.

• Record URL:
  https://doi.org/10.1016/j.ress.2023.109096
• Record URL:
  http://www.sciencedirect.com/science/article/pii/S095183202300011X
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/09518320
• Supplemental Notes:
  • © 2023 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Zhang, Jiusi
  • 0000-0001-7971-680X
  • Li, Xiang
  • Tian, Jilun
  • Luo, Hao
  • Yin, Shen
• Publication Date: 2023-5

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 109096
• Serial:
  • Reliability Engineering & System Safety
  • Volume: 233
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0951-8320
  • Serial URL: https://www.sciencedirect.com/journal/reliability-engineering-and-system-safety

Subject/Index Terms

• TRT Terms: Aviation safety; Machine learning; Predictive models; Reliability; Service life; Turbofan engines
• Subject Areas: Aviation; Maintenance and Preservation; Planning and Forecasting; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01880862
• Record Type: Publication
• Files: TRIS
• Created Date: Apr 24 2023 4:19PM