A multi-head attention network with adaptive meta-transfer learning for RUL prediction of rocket engines. (September 2022)

• Record Type: Journal Article
• Authors: Pan, Tongyang; Chen, Jinglong; Ye, Zhisheng; Li, Aimin
• Is Part Of: Reliability engineering & system safety. Volume 225(2022)
• Publication Date: 2022-09
• Subjects: Remaining useful life -- Deep neural network -- Rocket engine -- Transfer learning; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2022.108610
• Languages: English
• ISSNs: 0951-8320

Abstract

Abstract: Accurate prediction of remaining useful life (RUL) is necessary to ensure stable and safe operations for rocket engines. The paper proposed a multi-head attention network coupled with adaptive meta-transfer learning for RUL prediction. By combining the convolution-based branch with an attention-based branch, the multi-head attention network is proposed for accurate RUL prediction of cryogenic bearings in rocket engines under the steady stage. In addition, an adaptive model-agnostic meta-transfer learning strategy is developed to further improve the performance under small sample circumstances with adaptive hyper-parameters. To demonstrate the superiority, the proposed method is compared with typical benchmark algorithms using real monitoring data from a high-precision cryogenic rocket engine experiment platform. Results indicate that the proposed method achieves better performance compared with existing models under multiple evaluation indexes. Highlights: A multi-head attention network with dual branches is proposed for RUL prediction. A coupling unit is designed to complete dimension alignment for two branches. An adaptive meta-transfer learning strategy is proposed for knowledge transfer. We built a cryogenic experiment platform in liquid nitrogen for verification.