中国舰船研究2025，Vol.20Issue(2)：39-46,8.DOI:10.19693/j.issn.1673-3185.03739
基于全局注意力残差收缩网络的柱塞泵故障诊断方法
Fault diagnosis of piston pump based on global attention residual shrinkage network
摘要
Abstract
[Objective]Aiming at the problem of insufficient feature extraction in traditional neural net-works under strong noise interference,a new global attention residual shrinkage network is proposed for accur-ate diagnosis of piston pump faults in complex environments.[Methods]First,data segmentation is per-formed on the original signals.Then,a new global feature extractor with an attention mechanism is estab-lished to extract fault-related features from the signals,while a threshold softening mechanism is introduced to minimize noise interference.Back propagation optimization is then performed on the network model to reduce loss and improve the model's diagnostic performance.Finally,the feature extraction results are input into the fault classifier for fault identification.The effectiveness of the proposed method is verified by using a piston pump fault simulation test bed.[Results]The results show that,compared with other models,the estab-lished global attention residual shrinkage network model has higher diagnostic accuracy and stronger anti-in-terference ability.[Conclusion]The proposed method demonstrates accurate fault diagnosis in complex and harsh environments.关键词
残差网络/注意力机制/故障分析/故障诊断/柱塞泵Key words
residual networks/attention mechanism/failure analysis/fault diagnosis/piston pump分类
交通工程引用本文复制引用
王晓琪,吴轲,赵观辉,吴军..基于全局注意力残差收缩网络的柱塞泵故障诊断方法[J].中国舰船研究,2025,20(2):39-46,8.基金项目
湖北省自然科学基金重点类项目(2021CFA026) （2021CFA026）
国家自然科学基金面上项目(51875225) （51875225）
