Trim Loss Optimization in Paper Production Using Reinforcement Artificial Bee Colony
บทความในวารสาร
ผู้เขียน/บรรณาธิการ
กลุ่มสาขาการวิจัยเชิงกลยุทธ์
รายละเอียดสำหรับงานพิมพ์
รายชื่อผู้แต่ง: Fairee S., Khompatraporn C., Sirinaovakul B., Prom-On S.
ผู้เผยแพร่: Institute of Electrical and Electronics Engineers
ปีที่เผยแพร่ (ค.ศ.): 2020
Volume number: 8
หน้าแรก: 130647
หน้าสุดท้าย: 130660
จำนวนหน้า: 14
นอก: 2169-3536
eISSN: 2169-3536
ภาษา: English-Great Britain (EN-GB)
ดูในเว็บของวิทยาศาสตร์ | ดูบนเว็บไซต์ของสำนักพิมพ์ | บทความในเว็บของวิทยาศาสตร์
บทคัดย่อ
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.
คำสำคัญ
artificial bee colony, optimization, pulp and paper industry, stock cutting, swarm intelligence
ติดต่อสอบถามเพิ่มเติมได้ที่