A meta network pruning framework for remaining useful life prediction of rocket engine bearings with temporal distribution discrepancy. (15th July 2023)

• Record Type: Journal Article
• Authors: Pan, Tongyang; Zhang, Sui; Li, Fudong; Chen, Jinglong; Li, Aimin
• Is Part Of: Mechanical systems and signal processing. Volume 195(2023)
• Publication Date: 2023-07-15
• Subjects: Remaining useful life -- Rocket engine -- Deep learning -- Attention mechanism; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2023.110271
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: Accurate remaining useful life prediction (RUL) is important for the reliability and safety of liquid rocket engines. In this paper, a meta network pruning framework with attention augmented convolutions is proposed for RUL prediction. To address the problem of distribution discrepancy in engineering data under transient working conditions, a data-driven distribution matching strategy is designed. Besides, in view of the prediction accuracy and computation complexity of the model, an iterative meta network pruning algorithm, which automatically calculates the meta-gradients of each convolutional kernel according to the chain rule, is developed to identify, and then delete the unimportant connections in the framework. The method is verified on a high-precision cryogenic rocket engine bearing experiment platform under liquid nitrogen and received better performance than benchmark algorithms.