基于CBAM-STCN的齿轮箱故障智能诊断方法
DOI:
作者:
作者单位:

西安石油大学机械工程学院

作者简介:

通讯作者:

中图分类号:

TP277

基金项目:

陕西省自然科学基础研究计划项目(2022JQ-412)


Intelligent Fault Diagnosis Method for Gearboxes Based on CBAM-STCN
Author:
Affiliation:

1.School of Mechanical Engineering,Xi'2.'3.an Shiyou University,Xi'4.an 710000;5.China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对齿轮箱在多种工况下故障特征存在差异,故障诊断易受噪声干扰,导致故障诊断模型泛化性差和识别准确率低的问题。本文提出一种端到端的具有混合注意力机制和软阈值化特点的时间卷积神经网络(convolutional block attention module-sparse temporal convolutional network with soft thresholding, CBAM-STCN)齿轮箱故障诊断模型识别分类方法。首先,利用希尔伯特变换将齿轮故障振动信号转换为包络谱信号;然后,将其输入到CBAM-STCN故障诊断模型中;该模型嵌入的混合注意力机制模块(convolutional block attention module, CBAM),能够自适应学习通道和空间注意力的权重,提取与故障特征相关的敏感信息;嵌入的软阈值函数能够最小化模型输出和原输入之间的差异;最后,利用本文提出的方法对两种工况、不同类型的齿轮故障进行识别分类。结果表明:CBAM-STCN故障诊断模型对齿轮故障智能诊断的平均准确率为98.95%。该方法对于齿轮箱故障的智能诊断具有一定的参考价值。

    Abstract:

    For gearboxes, variations in fault characteristics under different operating conditions, susceptibility to noise interference in fault diagnosis, lead to poor generalization and low recognition accuracy of fault diagnosis models. This paper proposes an end-to-end convolutional block attention module-sparse temporal convolutional network with soft thresholding(CBAM-STCN) for gearbox fault diagnosis. Firstly, the Hilbert transform is employed to convert the gear fault vibration signal into an envelope spectrum signal. Then, this signal is input into the CBAM-STCN fault diagnosis model. The model integrates a hybrid attention mechanism module, the Convolutional Block Attention Module (CBAM), which adaptively learns the weights of channel and spatial attention to extract information sensitive to fault features. The embedded soft thresholding function minimizes the discrepancy between the model's output and the original input. Finally, the proposed method is utilized to identify and classify various types of gear faults under two different conditions. The results indicate that the CBAM-STCN model achieves an average accuracy of 98.95% in intelligent gear fault diagnosis, demonstrating its potential value for gearbox fault diagnosis.

    参考文献
    相似文献
    引证文献
引用本文

万志国,王治国,赵伟,等. 基于CBAM-STCN的齿轮箱故障智能诊断方法[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-04-02
  • 最后修改日期:2024-06-01
  • 录用日期:2024-07-09
  • 在线发布日期:
  • 出版日期: