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

作　　者：王晓琪 吴轲 赵观辉[2,3] 吴军 WANG Xiaoqi;WU Ke;ZHAO Guanhui;WU Jun(School of Naval Architecture and Ocean Engineering,Huazhong University of Science and Technology,Wuhan 430074,China;China Ship Development and Design Center,Wuhan 430064,China;College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China)

机构地区：[1]华中科技大学船舶与海洋工程学院,湖北武汉430074 [2]中国舰船研究设计中心,湖北武汉430064 [3]浙江大学计算机科学与技术学院,浙江杭州310027

出　　处：《中国舰船研究》2025年第2期39-46,共8页Chinese Journal of Ship Research

基　　金：湖北省自然科学基金重点类项目(2021CFA026);国家自然科学基金面上项目(51875225)。

摘　　要：[目的]针对传统神经网络在强噪声干扰下特征提取能力不足的问题,提出一种新的全局注意力残差收缩网络,实现复杂环境下柱塞泵故障精准诊断。[方法]首先,对原始监测信号进行数据切分;建立一种新的带有注意力机制的全局特征提取器,从监测信号中提取故障相关特征,同时引入阈值软化机制,减少信号中噪声干扰的影响;然后,对网络模型进行反向传播优化,减少损失误差,提升模型的诊断性能;最后,将特征提取结果输入到故障分类器进行故障识别。基于柱塞泵故障模拟实验台,验证所提出方法的有效性。[结果]结果表明:相比其他模型,该全局注意力残差收缩网络模型有更高的诊断精度,且具备更强的抗干扰能力。[结论]该诊断方法能够在复杂恶劣环境下实现故障的精准诊断。[Objective]Aiming at the problem of insufficient feature extraction in traditional neural networks under strong noise interference,a new global attention residual shrinkage network is proposed for accurate diagnosis of piston pump faults in complex environments.[Methods]First,data segmentation is performed on the original signals.Then,a new global feature extractor with an attention mechanism is established 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 established global attention residual shrinkage network model has higher diagnostic accuracy and stronger anti-interference 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 

分 类 号：U664.58[交通运输工程—船舶及航道工程]