基于ALIF-GAF-AlexNet的微电机故障分类  

Micro-motor Fault Classification Based on ALIF-GAF-AlexNet

作　　者：刘其洪[1] 陈璐 李伟光[1] 伍世豪 LIU Qihong;CHEN Lu;LI Weiguang;WU Shihao(School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou Guangdong 510641,China)

机构地区：[1]华南理工大学机械与汽车工程学院,广东广州510641

出　　处：《机床与液压》2024年第9期186-191,共6页Machine Tool & Hydraulics

摘　　要：微电机是一种重要的动力驱动元件,其诊断过程并不复杂,但人工听音比较低效且诊断结果片面,投入大量的人工对其进行分类是不合理的。为了提高微电机的诊断效率和实用性,提出一种诊断方法。使用自适应局部迭代滤波方法来降低噪声,然后用格拉姆角场将特征提取后的声音信号转换为图像,将转换后的图像应用深度卷积神经网络模型进行分类研究。基于微电机声音信号实验采集装置,对采集的数据应用所提出的方法进行故障诊断分类,并与其他方法进行比较。结果表明,该方法比其他方法具有更高的分类精度,准确率达到94.1%。Micro motor is an important power element,its diagnosis process is not complicated,but it is unreasonable to invest a lot of manual sorting,which will bring inefficient and one-sided diagnosis results.In order to improve the diagnostic efficiency and practicability of micro motor,a diagnostic method was proposed.The adaptive local iterative filtering method was used to reduce the noise,then the Gram angle field was used to convert the input sound signal after feature extraction into an image.The converted images were classified by deep convolutional neural network model.The efficiency of the proposed method was evaluated by the data set collected in the experiment.The results show that this method has higher classification accuracy than other methods,the accuracy achieves 94.1%.

关 键 词：微电机 ALIF GAF 深度学习 

分 类 号：V231.92[航空宇航科学与技术—航空宇航推进理论与工程] TH133.2[机械工程—机械制造及自动化]