DUE DATE ASSIGNMENT USING NEURAL NETWORKS FOR STANDARD PRODUCTS IN SMALL BATCH AND MULTI ASSORTMENT MAKE-TO-ORDER COMPANY

1 GACEK Stanisław
Institution:
1 ANGA Uszczelnienia Mechaniczne sp. z o. o. Kozy, Poland, EU, sgacek@anga.com.pl
Conference:
CLC 2018 - Carpathian Logistics Congress, Wellness Hotel Step, Prague, Czech Republic, EU, December 3 - 5, 2018
Proceedings:
Proceedings CLC 2018 - Carpathian Logistics Congress
Pages:
149-155
ISBN:
978-80-87294-88-8
ISSN:
2694-9318
Published:
18th April 2019
Proceedings of the conference were published in Web of Science.
Metrics:
430 views / 153 downloads
Abstract

The purpose of the article is to investigate artificial neural network ANN use in due-date assignment DDA for standard products in the real-life small batch and multi assortment make-to-order production company. The research was conducted with the historical data and resulted in the ANN aided DDA encoded into the company ERP system. The paper contains a comparison between different due-date assignment methods. The methods include company’s own procedure, multi variable linear regression and multilayer feedforward neural network. The details of quantitative and qualitative input variables, an output variable, the neural network structure and its training are presented in the paper. DDA approach incorporating material deliveries uncertainty was applied to both the linear regression and the neural network methods. DDA using neural networks proved to outperform the other analysed methods.

Keywords: Due-date assignment, neural network, machine learning, production flow-time

© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Scroll to Top