电子测量与仪器学报

高乐乐,崔宝珍,王浩楠.应用 Adabelief 优化器的 MSDNet 在多工况下滚动轴承的故障诊断[J].电子测量与仪器学报,2022,36(11):170-177

应用 Adabelief 优化器的 MSDNet 在多工况下滚动轴承的故障诊断

Fault diagnosis of rolling bearings in variable multi-load conditionsbased on MSDNet based on Adabelief optimizer

DOI：

英文关键词:rolling bearing MSDNet multi-load conditions fault diagnosis

基金项目:国家自然科学基金（51175480）、省重点研发计划（国际合作）（201903D421008）、中北大学先进制造技术山西省重点实验室开放课题研究基金（XJZZ202007）项目资助

作者	单位
高乐乐	1.中北大学机械工程学院
崔宝珍	1.中北大学机械工程学院
王浩楠	1.中北大学机械工程学院

Author	Institution
Gao Lele	1.School of Mechanical Engineering, North University of China
Cui Baozhen	1.School of Mechanical Engineering, North University of China
Wang Haonan	1.School of Mechanical Engineering, North University of China

摘要点击次数: 522

全文下载次数: 695

中文摘要:

针对滚动轴承在多工况条件下故障特征难以识别的问题,从数据驱动的角度出发应用一维多尺度密集网络(MSDNet) 对轴承进行故障诊断。首先,将时域信号作为 MSDNet 的直接输入,保持了信号本有的固有特性;其次采用 3 个并行卷积操作来提取轴承故障信号内部的多尺度信息,密集网络的加入防止了信息传递过程中的特征丢失,适当缓解了模型中的梯度消失问题;然后训练过程中采用 Adabelief 优化算法优化模型参数,使得模型在快速收敛的同时又提高了其泛化性能;最后通过混淆矩阵和特征可视化图展示出模型的分类性能,在凯斯西储大学轴承实验数据集和西安交通大学数据集上进行了多次实验,应用该算法故障识别率可达到 98%以上,证明了该方法的有效性。

英文摘要:

It is difficult to identify the fault features of rolling bearings under multiple working conditions. In this paper, one-dimensional multi-scale dense network (MSDNet) was applied to fault diagnosis of rolling bearings from the perspective of data-driven. Firstly, the time domain signal is used as the direct input of MSDNet to maintain the inherent characteristics of the signal. Secondly, three parallel convolution operations were used to extract multi-scale information inside the bearing fault signals. The addition of dense network prevented the loss of features in the process of information transmission, and alleviated the gradient disappearance problem in the model appropriately. Then, the Adabelief optimization algorithm is used to optimize the model parameters during the training process, which makes the model converge quickly and improve its generalization performance. Finally, confusion matrix and feature visualization were used to demonstrate the classification performance of the model. Several experiments have been carried out on Case Western Reserve University bearing datasets and Xi′an Jiaotong University datasets, and the fault recognition rate of the proposed algorithm can reach more than 98%, which proves the effectiveness of the proposed method.

查看全文查看/发表评论下载PDF阅读器