On-line part deformation prediction based on deep learning
Deformation prediction is the basis of deformation control in manufacturing process planning. This paper presents an on-line part deformation prediction method using a deep learning model during numerical control machining process, which is different from traditional methods based on finite element simulation of stress release prior to the actual machining process. A fourth-order tensor model is proposed to represent the continuous part geometric information, process information, and monitoring information, which is used as the input to the deep learning model. A deep learning framework with a conventional neural network and a recurrent neural network has been constructed and trained by monitored deformation data and process information associated with interim part geometric information. The proposed method can be generalised for different parts with certain similarities and has the potential to provide a reference for an adaptive machining control strategy for reducing part deformation. The proposed method was validated by actual machining experiments, and the results show that the prediction accuracy has been improved compared with existing methods. Furthermore, this paper shifts the difficult problem of residual stress measurement and off-line deformation prediction to the solution of on-line deformation prediction based on deformation monitoring data.
KeywordsDeformation prediction Monitoring data Deep learning Tensor model
The reported research was funded by the National Natural Science Foundation of China (Ref. 51775278), the National Natural Science Foundation of China—Chinese Aerospace Science and Technology Corporation on Advanced Manufacturing (Ref. U1537209), and the Jiangsu Province Outstanding Youth Fund (Ref. BK20140036).
- Chantzis, D., Van-Der-Veen, S., Zettler, J., & Sim, W. M. (2013). An industrial workflow to minimise part distortion for machining of large monolithic components in aerospace industry. In 14th CIRP conference on modeling of machining operations (CIRP CMMO) (Vol. 8, pp. 281–286).Google Scholar
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV (pp. 770–778).Google Scholar
- Pimenov, D. Y., Bustillo, A., & Mikolajczyk, T. (2017). Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth. Journal of Intelligent Manufacturing, 29(1), 1–17.Google Scholar
- Shang, M. E. H. (1995). Prediction of the dimensional instability resulting from machining of residually stressed components. Lubbock: Texas Tech University.Google Scholar
- Wang, P. S., Liu, Y., Guo, Y. X., Sun, C. Y., & Tong, X. (2017b). O-CNN: Octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics, 36(4), 1–11.Google Scholar
- Wang, T., Qiao, M., Zhang, M., Yang, Y., & Snoussi, H. (2018b). Data-driven prognostic method based on self-supervised learning approaches for fault detection. Journal of Intelligent Manufacturing, 3, 1–9.Google Scholar
- Wang, X., Bi, Q., Zhu, L., & Ding, H. (2018c). Improved forecasting compensatory control to guarantee the remaining wall thickness for pocket milling of a large thin-walled part. International Journal of Advanced Manufacturing Technology, 94(5–8), 1–12.Google Scholar