基于Mobile-VIT的旋转机械故障诊断方法  

A Fault Diagnosis Method of Rotating Machinery Based on Mobile-VIT

作　　者：付忠广[1] 王诗云 高玉才 周湘淇 FU Zhong-guang;WANG Shi-yun;GAO Yu-cai;ZHOU Xiang-qi(Key Laboratory of Power Station Energy Transfer Conversion and System of Ministry of Education,North China Electric Power University,Beijing 102206,China)

机构地区：[1]华北电力大学电站能量传递转化与系统教育部重点实验室,北京102206

出　　处：《汽轮机技术》2023年第2期119-121,86,共4页Turbine Technology

基　　金：国家自然科学基金资助项目(50776029,51036002)。

摘　　要：主要提出了一种基于Mobile-VIT神经网络技术的旋转机械故障的识别分析方法:首先,将旋转的机械构件在其各种连续运行工作状态条件下获得的高频振动信号通过短时的傅里叶变换方法转换为时频图像;然后,将图像输入到搭建好的Mobile-VIT网络模型中,通过其对时频图的识别以及特征提取实现旋转机械故障诊断。实验结果表明,提出的方法具有较高的故障识别准确率,能够有效识别旋转机械的运行状态。A method of fault identification and analysis of rotating machinery based on Mobile VIT neural network technology was proposed:firstly,the high-frequency vibration signals obtained by rotating mechanical components under various continuous operating conditions were converted into time-frequency images through short-time Fourier transform method.Then the images were input into the built Mobile VIT network model,and fault diagnosis of rotating machinery was realized through its recognition of time-frequency images and feature extraction.The experimental results showed that the method proposed in this paper has a high accuracy of fault identification,and can effectively identify the running state of rotating machinery.

关 键 词：旋转机械 故障诊断 短时傅里叶变换 深度学习 Mobile-VIT 

分 类 号：TH17[机械工程—机械制造及自动化] TK14[动力工程及工程热物理—热能工程]