Journal cover Journal topic
Mechanical Sciences An open-access journal for theoretical and applied mechanics

Journal metrics

  • IF value: 1.211 IF 1.211
  • IF 5-year<br/> value: 1.705 IF 5-year
    1.705
  • SNIP value: indexed SNIP
    indexed
  • SJR value: indexed SJR
    indexed
  • IPP value: indexed IPP
    indexed
  • h5-index value: 15 h5-index 15
Supported by
Logo Library of Delft University of Technology Logo NWO
Affiliated to
Logo iftomm
Mech. Sci., 9, 123-146, 2018
https://doi.org/10.5194/ms-9-123-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Research article
27 Feb 2018
Tool selection method based on transfer learning for CNC machines
Jingtao Zhou1, Han Zhao2, Mingwei Wang1, and Bingbo Shi1 1The Key Laboratory of Contemporary Design and Integrated Manufacturing Technology Ministry of Education, Northwestern Polytechnical University, Xi'an, 710072, China
2China Academy of Space Technology, Beijing, 100081, China
Abstract. Owing to the changes in product requirements and development of new tool technology, traditional tool selection approach based on the human experience is leading to time-consuming and low efficiency. Under the cooperation of historical data resource accumulated by manufacturing enterprises, with human expert resource, a new tool selection mechanism can be established. In this paper, we apply transfer learning to tool selection issue. Starting from the foundation of migration, we showed a unified expression of expert experience and process case in a multi-source heterogeneous environment. Then, we propose a transfer learning algorithm (TLrAdaBoost) based on AdaBoost, which uses a small amount of target domain data (expert experience sample) and a large number of source domain low-quality data (process case sample), to build a high-quality classification model. Experimental results show the effectiveness of the proposed algorithm.

Citation: Zhou, J., Zhao, H., Wang, M., and Shi, B.: Tool selection method based on transfer learning for CNC machines, Mech. Sci., 9, 123-146, https://doi.org/10.5194/ms-9-123-2018, 2018.
Publications Copernicus
Download
Short summary
Due to the time-consuming and inefficient traditional tool selection method based on the human experience, we apply transfer learning to CNC tool selection issue in the field of industrial manufacturing. A unified expression of expert experience and process case is given in a more complex environment and then we improve the algorithm. The results show that the method we proposed can facilitate tool selection.
Due to the time-consuming and inefficient traditional tool selection method based on the human...
Share