用户名 密 码 登 录 忘记密码 免费注册

网站会员中心 | 设为首页 | 加入收藏

 您好,欢迎光临中国轴承行业网         退出登陆

会员中心 | 设为首页 | 加入收藏

国外文献 > 1.轴承 > 5. 监测与诊断 > 故障诊断


关键词搜索:


标 题: A Bearing Fault Diagnosis Method Based on Multimodal Attention Feature Fusion
基于多模态注意力特征融合的轴承故障诊断方法
作 者: Jinning Peng
Jing Zhao
Jingpeng Wang
Fei Xie
Laishou Song
Cong Wang
关键词: Fault diagnosis  [故障诊断]
Convolutional neural network  [ 卷积神经网络]
Attention feature fusion  [ 注意特征融合]
Cross-condition diagnosis  [ 交叉条件诊断]
出版年: 2024
文集名: 7th International Conference on Robotics, Control and Automation Engineering (RCAE 2024)
第七届机器人、控制与自动化工程国际会议(RCAE 2024)
会议名: 7th International Conference on Robotics, Control and Automation Engineering (RCAE 2024)
第七届机器人、控制与自动化工程国际会议(RCAE 2024)
届 次: 7th
摘 要: This paper proposes a fault diagnosis method based on Multi-modal Attention Feature Fusion (MMAFF). Firstly, a multi-modal processing strategy is introduced, converting one-dimensional vibration signals into two-dimensional image modalities, and extracting features from both signal and image channels. Secondly, the attention mechanism is introduced to integrate the dual path features. Then, the diagnosis framework is obtained through an improved residual block. Finally, the method is tested on the Case Western Reserve University (CWRU) rolling bearing dataset, and cross-condition comparison experiments demonstrate that the proposed method (MMAFF) exhibits good recognition capabilities under different working conditions.

本文提出了一种基于多模态注意力特征融合(MMAFF)的故障诊断方法。首先,引入一种多模态处理策略,将一维振动信号转换为二维图像模态,并从信号和图像通道中提取特征。其次,引入注意力机制以整合双路径特征。然后,通过改进的残差块构建了诊断框架。最后,该方法在Case Western Reserve大学(CWRU)滚动轴承数据集上进行了测试,交叉条件对比实验表明,所提出的MMAFF方法在不同工作条件下均表现出良好的识别能力。
中文内容为网络AI翻译,专业术语未必准确,仅供参考。

VIP网员

联系我们 | 登录注册 | 会员管理 | 网员服务 | 服务信息 | 广告服务 | 高薪聘请 | 法律声明 | 关于我们

京公网安备 11010202009788    京ICP备2021015424号