A hybrid muti-dimension normalization layers improved ResNet based fault diagnosis method of rolling bearing
ID：58
View Protection：PUBLIC
Updated Time：2022-12-21 16:52:44
Hits：543
Poster Presentation
Start Time：Pending （Asia/Shanghai）
Duration：Pending
Session：[No Session] » [No Session Block]
Abstract
CNN, a kind of deep learning method, has been widely used in fault diagnosis. It requires a large number of training samples, but it is difficult to obtain abundant samples under different conditions. Aiming at insufficient fault samples, an improved ResNet (IResNet) is proposed in this paper. Firstly, order spectrum is computed from raw data as pre-processed samples, which will be further augmented to improve the generalization ability of the model. Secondly, IResNet is constructed by several hybrid residual building blocks fused from multi-dimensional normalization layers, which can be adopted to enhance the feature extraction ability of the model. Then, the parameters of IResNet in the source domain are transferred to identify the health status of rolling bearing in the target domain. Finally, experimental data under different working conditions are used to verify the performance of the proposed method. The experimental results indicate that the recognition accuracy of the proposed method is higher than other methods and that the proposed method can identify the health status of rolling bearing with small training samples.
Keywords
Convolutional neural network;Improved ResNet;Hybrid block;Rolling bearing;Fault diagnosis
Speaker
长波 贺
讲师 安徽大学All comments
15th August 2022 25th September 2022 - Manuscript Submission
15th October 2022 - Acceptance Notification
1st November 2022 - Camera Ready Submission
1st November 2022 10th November 2022 - Early Bird Registration
Contact Us
Website: https://icsmd2022.aconf.org
Secretary: icsmd2022@163.com
Scan the QR code and join the
WeChat Group
Comment submit