Cross-Component Transferable Transformer Pipeline Obeying Dynamic Seesaw for Rotating Machinery with Imbalanced Data

作     者：Xu, Binbin Ma, Boquan Yang, Zheng Chen, Fei Li, Xiaobing 

作者机构：Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen518118 China School of Mechanical and Aerospace Engineering Jilin University Changchun130025 China Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology Guangzhou511370 China 

出 版 物：《SSRN》 

年 卷 期：2023年

核心收录：

主　　题：Failure analysis 

摘      要：Due to the lack of fault data in the daily work of rotating machinery components, existing data-driven fault diagnosis procedures cannot accurately diagnose fault classes and are difficult to apply to most components. At the same time, the complex and variable working conditions of components pose a challenge to the feature extraction capability of the models. Therefore, this work proposes a novel hierarchical window transformer model that obeys a dynamic seesaw (HWT-SS), and a creative strategy of transfer diagnosis between multiple rotating mechanical components combined with transfer learning is proposed. A transferable pipeline is constructed to solve the fault diagnosis of multiple components in the presence of imbalanced data. The advantages of the proposed model are validated using four datasets with different imbalance ratios, including two bearing datasets, one gearbox dataset and one motor dataset. The comparison with the benchmark models proves that the proposed model has the advantages of strong feature extraction capability and low influence of imbalanced data. The transfer tests between datasets and the visual interpretation of the model prove that the transfer diagnosis between components can further improve the diagnostic capability of the model for extremely imbalanced data. © 2023, The Authors. All rights reserved.