A transfer learning based geometric position-driven machining error prediction method for different working conditions

Contribution

In this paper, we propose a sample-based transfer learning method driven by geometric position. With this method, we can learn the machining errors in some source domain working conditions and apply the learned knowledge to predict the machining errors under target domain working conditions. This kind of knowledge can make the model accurately predict the distribution law of machining errors of T-shaped thin plate in the target domain under the guidance of machining errors of a few sampling points in the target domain. It is of great significance to control and compensate the machining errors of thin-walled parts.

In addition, this method can reduce the reliance on time-consuming and expensive measurements, and improve the efficiency of obtaining machining errors.

Recommended citation: T. Zhang, H. Sun, L. Zhou, S. Zhao, F. Peng and R. Yan, "A transfer learning based geometric position-driven machining error prediction method for different working conditions," 2021 27th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), Shanghai, China, 2021, pp. 145-150, doi: 10.1109/M2VIP49856.2021.9665105. https://ieeexplore.ieee.org/abstract/document/9665105