改进MoblieNet网络在轴承轻量化诊断中的应用

Application of Improved MobileNet Network in Bearing Lightweight Diagnosis

近年来,基于神经网络的故障诊断方法在诊断的准确性、效率等方面展现出巨大的优势,然而呈指数增长的模型参数量限制了神经网络在工程实际中的应用。针对这一问题,本文提出了一种基于一维卷积神经网络改进的MobileNet网络用于实现滚动轴承的故障诊断;改进的网络能够直接应用于一维振动信号,有效降低系统硬件资源的要求,实现网络的轻量化部署;使用西储大学轴承数据集和QPZZ-Ⅱ型故障模拟试验台数据集对所提方法进行验证,本文提出的模型准确率均达99.8%以上,参数量为标准卷积神经网络的1/2。本文所提方法为在轻资源嵌入式系统中实现智能诊断提供了一种新的方法和思路。

In recent years,fault diagnosis methods based on neural networks have shown great advantages in the accuracy and efficiency of diagnosis.However,the exponentially increasing number of model parameters limits the application of neural networks in engineering practice.Aiming at this problem,this paper proposes an improved MobileNet network based on one⁃dimensional convolutional neural network for fault diagnosis of rolling bearings.The improved network can be directly applied to one⁃dimensional vibration signals,effectively reducing the requirements of system hardware resources and realizing lightweight deployment of the network;The proposed method is validated using the Western Reserve University bearing dataset and the QPZZ⁃Ⅱfault simulation test bench dataset.The accuracy of the model proposed in this paper is more than 99.8%,and the number of parameters is 1/2 of the standard convolutional neural network.The method proposed provides a new way for realizing intelligent diagnosis in light⁃resource embedded systems.