Trim Loss Optimization in Paper Production Using Reinforcement Artificial Bee Colony
Journal article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Fairee S., Khompatraporn C., Sirinaovakul B., Prom-On S.
Publisher: Institute of Electrical and Electronics Engineers
Publication year: 2020
Volume number: 8
Start page: 130647
End page: 130660
Number of pages: 14
ISSN: 2169-3536
eISSN: 2169-3536
Languages: English-Great Britain (EN-GB)
View in Web of Science | View on publisher site | View citing articles in Web of Science
Abstract
In paper production, a jumbo reel is cut into multiple intermediate rolls, and each intermediate roll is then sheeted as finished goods. This problem is called a cutting stock problem and is proven to be NP-hard. The objective is to minimize material waste or trim loss from all the cuttings. In the case that any intermediate roll is not entirely used for its associated order, the intermediate roll itself could turn to be a dead stock. We use the concept of universal sizes of intermediate rolls to eliminate the dead stock. A pre-defined number of universal sizes of intermediate rolls is to be used to serve all the orders. The problem is solved using Reinforcement Artificial Bee Colony algorithm with Integer Linear Programming subroutine. This proposed approach is then tested with a set of 1,055 orders and 127 different sizes of sheet papers from a paper manufacturer. The results reveal that our method outperforms other algorithms. Our method offers the total trim loss of 3.51%, compared to the trim loss reported by the industry of at least 5%. This approach not only reduces the number of partially cut rolls, but also decreases the number of the jumbo reels needed to serve all the orders. Therefore, both the inventory cost and material cost can be saved. © 2013 IEEE.
Keywords
artificial bee colony, optimization, pulp and paper industry, stock cutting, swarm intelligence
Contact Information