Improving the Efficiency of "Jacketing" by Taking Into Account the Specifics of Applied Equipment and Prefabrications Based on Machine Learning Methods

DOI

10.2991/csit-19.2019.16How to use a DOI?

Keywords

machine learning, optimization, binary classification, multi-class classification, np-complete, optical fiber, jacketing, jacket.

Abstract

The article considers the task of choosing the optimal set of silica tubes for the operation of jacketing in the production of optical fiber, taking into account the available types of silica tubes, the features of the used equipment and the quality of products in previous cycles of production. The model, which allows considering the previous experience at a performance of the operation of a jacketing during the industrial process based on the decision of a problem of classification results. The model takes into account the physical features of the process and uses the results of technological operations for further refinement and correction. For primary education, the models used already available statistical data. Practical application of the model allows getting many possible solutions to the problem of selection of jacket tubes, which helps to reduce scrap in the jacketing.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Leonid Mylnikov
AU  - Artur Mikhailov
AU  - Anatoliy Pesterev
AU  - Dmitrii Vershinin
PY  - 2019/12
DA  - 2019/12
TI  - Improving the Efficiency of "Jacketing" by Taking Into Account the Specifics of Applied Equipment and Prefabrications Based on Machine Learning Methods
BT  - Proceedings of the 21st International Workshop on Computer Science and Information Technologies (CSIT 2019)
PB  - Atlantis Press
SP  - 94
EP  - 98
SN  - 2589-4900
UR  - https://doi.org/10.2991/csit-19.2019.16
DO  - 10.2991/csit-19.2019.16
ID  - Mylnikov2019/12
ER  -