Prediction of surface roughness based on sensitive factor selection and residual network
Release time:2025-02-15
Hits:
- Journal:
- Computer Integrated Manufacturing Systems
- Key Words:
- residual network; wavelet packet decomposition; correlation analysis; sensitive frequency band; surface roughness; prediction
- Abstract:
- In order to predict the surface roughness of machined parts and avoid the waste of raw materials, a surface roughness prediction method based on sensitive factor selection and residual network (ResNet) is proposed. Firstly, the correlation between the vibration signals of different sampling channels in the cutting system and the surface roughness is analyzed to determine the sensitive signal. Then, the sensitive signal is decomposed into wavelet packet coefficients of different frequency bands by wavelet packet decomposition (WPD), and the sensitive frequency band is selected by correlation analysis. Finally, the wavelet packet coefficients of each sensitive frequency band are fused to form a coefficient matrix as the input parameters of ResNet. The results show that the relative percentage error of the prediction method based on sensitive factor selection and ResNet is not more than 5.8%, the root mean square error is 0.0159, the average absolute error is 0.0133, and the determination coefficient is 0.9148. By comparing with Back Propagation neural network (BP), support vector machine (SVM) and convolutional neural network (CNN), the prediction accuracy of surface roughness prediction method based on sensitive factor selection and ResNet is improved.
- Co-author:
- DOU Weitao
- First Author:
- wanghaitao,SHAO Xianzhong
- Indexed by:
- Journal paper
- Correspondence Author:
- Lichen Shi
- Discipline:
- Engineering
- Document Type:
- J
- Translation or Not:
- no
- Date of Publication:
- 2022-01-01
- Included Journals:
- EI
- Links to published journals:
- https://kns.cnki.net/kcms/detail/11.5946.TP.20221121.1134.003.html