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,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,利用所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。
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.An end-to-end convolutional block attention module-sparse temporal convolutional network with soft thresholding(CBAM-STCN)was proposed for gearbox fault diagnosis.Firstly,the Hilbert transform was employed to convert the gear fault vibration signal into an envelope spectrum signal.Then,this signal was 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 was 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.
作者
万志国
王治国
赵伟
窦益华
WAN Zhi-guo;WANG Zhi-guo;ZHAO Wei;DOU Yi-hua(School of Mechanical Engineering,Xi'an Shiyou University,Xi'an 710000,China)
出处
《科学技术与工程》
北大核心
2025年第9期3760-3768,共9页
Science Technology and Engineering
基金
陕西省自然科学基础研究计划(2022JQ-412)。
关键词
齿轮箱
故障智能诊断
混合注意力机制
软阈值化
时间卷积神经网络
gearbox
intelligent fault diagnosis
convolutional block attention module(CBAM)
soft thresholding
temporal convolutional network(TCN)
