A multi-neural-network learning for lot sizing and sequencing on a flow-shop

Lee, In; Gupta, Jatinder N. D.; Amar, Amar D.

doi:10.1145/372202.372210

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each output node specifies the probability that an order is to be placed. Lee et al (2001) address a lotsizing and scheduling problem with multiple machines. Two separate ANNs are developed.…”

Section: Ann In Lotsizingmentioning

confidence: 99%

A machine learning approach for predicting the best solution heuristic for a large scaled Capacitated Lotsizing Problem

Kärcher,

Meyr

2023

Preprint

View full text Add to dashboard Cite

For some NP-hard lotsizing problems, many different solution heuristics exist, but they have different solution qualities and computation times depending on the characteristics of the problem instance. The computation times of the individual solution heuristics increase significantly with the problem size, so that testing all available solution heuristics for large problem instances requires extensive time. Therefore, it is necessary to develop a method that allows a prediction of the best solution heuristic for the respective problem instance without testing all available solution heuristics. The Capacitated Lotsizing Problem (CLSP) is chosen as the problem to be solved, since it is well researched and several different solution heuristics exist for it. The CLSP addresses the problem of determining lotsizes on a production line given limited capacity, product-dependent setup costs, and deterministic, dynamic demand for multiple products. The objective is to minimize setup and inventory holding costs. Five different forecasting methods are presented. One of them is a two-layer neural network called CLSP-Net. It is trained on small problem instances, which can be solved very fast with the considered solution heuristics. Nevertheless, CLSP-Net is able to predict the best solution heuristic even for large problem instances.

show abstract

Section: Ann In Lotsizingmentioning

confidence: 99%