摘要
在基于深度学习的电机轴承故障诊断中,一般采用基于生成对抗网络(generative adversarial networks,GANs)的数据增强方法以获取足量故障数据,从而保证模型的性能。一维时序信号下的数据增强会出现生成数据质量差、网络训练速度慢以及训练过程繁琐等问题,该文针对此,提出一种基于二维灰度图及辅助分类生成对抗网络(2D gray pixel images and auxiliary classifier generative adversarial networks,2D-ACGANs)的数据增强方法。首先将原始的一维时序信号转换为二维灰度图,以得到适用于二维卷积神经网络的输入数据;在此基础上结合辅助分类生成对抗网络,将原始数据的标签作为此网络的输入进行数据增强,该方法较一维数据增强方法有效减少网络训练参数量,同时解决传统方法中训练繁琐及标签信息丢失的问题。最后将提出的方法用于电机轴承的故障实验数据中进行对比验证,结果表明改进的2D-ACGANs算法能生成更高质量的数据,有效提高故障识别准确率及网络训练速度,具备良好的工程应用可行性。
In the motor bearing fault diagnosis based on the deep learning, generally adopt data augmentation method based on generative adversarial networks(GANs) in order to get sufficient fault data, thereby ensuring the outstanding performance of the model. Problems such as poor data generation quality, slow network training speed and tedious training may occur in the data augmentation of 1 D time-domain signal. To solve these problems, this paper proposed a data augmentation method based on 2 D gray pixel images and auxiliary classifier generative adversarial networks(2 D-ACGANs). Firstly, the raw time-domain signal was converted into 2 D gray pixel images to obtain the input data suitable for the two-dimensional convolutional neural network. On this basis, combining with the ACGANs, the label of the raw data was used as the input of the network for data augmentation. Compared with the 1 D data augmentation method, this method can effectively reduce the quantity of network training parameters, and at the same time solved the problems of tedious training and loss of label information in the traditional method. Finally, the proposed method was applied to the real data of motor bearings fault diagnosis for comparison and verification. The results show that the improved 2 D-ACGANs algorithm can generate higher quality data, effectively improve the fault recognition accuracy and the network training speed, and has good engineering application feasibility.
作者
肖雄
肖宇雄
张勇军
宋国明
张飞
XIAO Xiong;XIAO Yuxiong;ZHANG Yongjun;SONG Guoming;ZHANG Fei(Institute of Engineering Technology,University of Science and Technology Beijing,Haidian District,Beijing 100083,China;Electric and Resources,National Taipei University of Technology,Taibei 100,Taiwan Province,China)
出处
《中国电机工程学报》
EI
CSCD
北大核心
2021年第2期738-748,共11页
Proceedings of the CSEE
基金
国家自然科学基金(青年科学基金项目)(51907006)
北京科技大学与台北科技大学学术合作专题研究计划经费资助(06310059)。
关键词
电机轴承
故障诊断
生成对抗网络
二维灰度图
数据增强
motor bearing
fault diagnosis
generative adversarial networks
2D gray pixel images
data augmentation
