A Review on Learning to Solve Combinatorial Optimisation Problems in Manufacturing

Cong Zhang; Yaoxin Wu; Yining Ma; Wen Song; Zhang Le; Zhiguang Cao; Jie Zhang

doi:10.1049/cim2.12072

A Review on Learning to Solve Combinatorial Optimisation Problems in Manufacturing

Cong Zhang
, Yaoxin Wu
, Yining Ma
, Wen Song (Corresponding author)
, Zhang Le
, Zhiguang Cao
, Jie Zhang

Research output: Contribution to journal › Article › Academic › peer-review

47 Citations (Scopus)

160 Downloads (Pure)

Abstract

An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas for addressing challenging problems in manufacturing systems. We collect the literature targeting three aspects: scheduling, packing, and routing, which correspond to three pivotal cooperative production links of today's manufacturing system, that is, production, packing, and logistics respectively. For each aspect, we first present and discuss the state-of-the-art research. Then we summarise and analyse the development trends and point out future research opportunities and challenges.

Original language	English
Article number	e12072
Number of pages	24
Journal	IET Collaborative Intelligent Manufacturing
Volume	5
Issue number	1
DOIs	https://doi.org/10.1049/cim2.12072
Publication status	Published - 3 Mar 2023
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber-Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF-PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027.

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber‐Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF‐PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027.

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber-Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF-PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027. This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber‐Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF‐PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027.

Keywords

bin packing
combinatorial optimisation
deep reinforcement learning
job shop scheduling
manufacturing systems
vehicle routing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1049/cim2.12072

pdfFinal published version, 903 KBLicence: CC BY-NC-ND

Cite this

@article{ad78f790da774feb9f862d37df8b9b70,

title = "A Review on Learning to Solve Combinatorial Optimisation Problems in Manufacturing",

abstract = "An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas for addressing challenging problems in manufacturing systems. We collect the literature targeting three aspects: scheduling, packing, and routing, which correspond to three pivotal cooperative production links of today's manufacturing system, that is, production, packing, and logistics respectively. For each aspect, we first present and discuss the state-of-the-art research. Then we summarise and analyse the development trends and point out future research opportunities and challenges.",

keywords = "bin packing, combinatorial optimisation, deep reinforcement learning, job shop scheduling, manufacturing systems, vehicle routing",

author = "Cong Zhang and Yaoxin Wu and Yining Ma and Wen Song and Zhang Le and Zhiguang Cao and Jie Zhang",

note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber-Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF-PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027. Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber‐Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF‐PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027. ",

year = "2023",

month = mar,

day = "3",

doi = "10.1049/cim2.12072",

language = "English",

volume = "5",

journal = "IET Collaborative Intelligent Manufacturing",

issn = "2516-8398",

publisher = "Institution of Engineering and Technology",

number = "1",

}

TY - JOUR

T1 - A Review on Learning to Solve Combinatorial Optimisation Problems in Manufacturing

AU - Zhang, Cong

AU - Wu, Yaoxin

AU - Ma, Yining

AU - Song, Wen

AU - Le, Zhang

AU - Cao, Zhiguang

AU - Zhang, Jie

N1 - Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber-Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF-PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027. Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62102228 and the Shandong Provincial Natural Science Foundation under Grant ZR2021QF063. This work was also supported by the A*STAR Cyber‐Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF‐PP Grant A19C1a0018, and Model Factory@SIMTech. Finally, this work is supported in part by the A*Star Career Development Fund under Grant C222812027.

PY - 2023/3/3

Y1 - 2023/3/3

N2 - An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas for addressing challenging problems in manufacturing systems. We collect the literature targeting three aspects: scheduling, packing, and routing, which correspond to three pivotal cooperative production links of today's manufacturing system, that is, production, packing, and logistics respectively. For each aspect, we first present and discuss the state-of-the-art research. Then we summarise and analyse the development trends and point out future research opportunities and challenges.

AB - An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas for addressing challenging problems in manufacturing systems. We collect the literature targeting three aspects: scheduling, packing, and routing, which correspond to three pivotal cooperative production links of today's manufacturing system, that is, production, packing, and logistics respectively. For each aspect, we first present and discuss the state-of-the-art research. Then we summarise and analyse the development trends and point out future research opportunities and challenges.

KW - bin packing

KW - combinatorial optimisation

KW - deep reinforcement learning

KW - job shop scheduling

KW - manufacturing systems

KW - vehicle routing

UR - https://www.scopus.com/pages/publications/85149487801

U2 - 10.1049/cim2.12072

DO - 10.1049/cim2.12072

M3 - Article

AN - SCOPUS:85149487801

SN - 2516-8398

VL - 5

JO - IET Collaborative Intelligent Manufacturing

JF - IET Collaborative Intelligent Manufacturing

IS - 1

M1 - e12072

ER -

A Review on Learning to Solve Combinatorial Optimisation Problems in Manufacturing

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this