Review on Learning-based Methods for shop Scheduling problems

• Published in: 2022 IEEE International Conference on e-Business Engineering (ICEBE) pp. 294 - 298
• Main Authors: Li, Xiaoxia, Lu, Xin, Wang, Wei, Jing, Yanguo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2022
• Subjects: artificial neural networks; Classifieds; Complexity theory; Industries; Job shop scheduling; Learning systems; learning-based method; Learning-based methods; Machine learning; Machine learning techniques; Manufacturing; Manufacturing performance; Neural networks; Production and Automation Engineering; Produktion och automatiseringsteknik; Reinforcement learning; Reinforcement learnings; Related works; Research opportunities; Scheduling problem; Shop scheduling; Shop scheduling problem; shop scheduling problems; VF-KDO; Virtual Manufacturing Processes
• ISBN: 9781665492454; 1665492457; 9781665492447; 1665492449
• DOI: 10.1109/ICEBE55470.2022.00058

Shop scheduling is an effective way for manufacturers to improve their manufacturing performances. However, due to its complexity, it is difficult to deal with shop scheduling problems (SSP). Thus, SSP has received a lot of attention from industry and academia. Various kinds of methods have been proposed to solve SSP. Learning-based method is just one of the most representative methods for SSP. This paper focuses on reviewing the learning-based methods for SSP. Firstly, the methods for SSP are briefly introduced. Then, its description and model are provided and its classification is discussed. Next, the learning-based methods for SSP are classified according to the machine learning technique used in the methods. Based on the classification, the related work on each type of learning-based methods for SSP is summarized and further analyzed and compared with other traditional methods. Finally, the future research opportunities and challenges of the learning-based methods for SSP are summarized.