A Multi-Trigger Mechanism Design for Rescheduling Decision Assistance in Smart Job Shops Based on Machine Learning

Rong Duan, Siqi Wang, Ya Liu, Wei Yan (), Zhigang Jiang and Zhiqiang Pan
Additional contact information
Rong Duan: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China
Siqi Wang: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China
Ya Liu: Wuhan Marine Machinery Plant Co., Ltd., Wuhan 430084, China
Wei Yan: School of Automobile and Traffic Engineering, Wuhan University of Science and Technology, Wuhan 430081, China
Zhigang Jiang: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China
Zhiqiang Pan: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China

Sustainability, 2025, vol. 17, issue 5, 1-20

Abstract: The empowerment of lean intelligent manufacturing technologies has provided a solid foundation for enterprises to achieve a balance between economic benefits and sustainable development. In production workshops, various disruptive factors, especially in multi-variety small-batch production environments, often lead to deviations from the planned schedule. This creates an urgent need to enhance the workshop’s dynamic responsiveness and self-regulation capabilities. Existing single-trigger mechanisms in job shops focus on changes in overall performance or deviations from production goals but lack a representation of the varying degrees of impact on different equipment under multiple disturbances. This results in either over-scheduling or under-scheduling in terms of scope, thereby impacting the optimization of production efficiency and resource utilization. To address this, this paper proposes a method for coordinated decision-making on rescheduling timing and location in intelligent job shops under disturbance environments. First, by analyzing the relationship between disturbance impact and the scope of rescheduling implementation, a mapping relationship is established between disturbance impact and disturbance response hierarchy. A trigger is set up on each piece of equipment to characterize the differences in the degree of impact on different equipment, which not only reduces the complexity of disturbance information processing but also provides support for specific location decisions for disturbance response. Second, a decision module for the triggers is constructed using a multilayer perceptron, establishing a mapping relationship between process and workpiece data attributes and response categories. Based on the basic processing units of the manufacturing process and the relevant quantitative indicators of the processed objects, disturbance response strategies are generated. Finally, through a case study, the proposed method is evaluated and validated in an intelligent factory setting. The new rescheduling decision support method can effectively make timing and location decisions for disturbance events.

Keywords: multi-trigger; multiple disturbances; rescheduling decision; machine learning; sustainable manufacturing (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/5/2198/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/5/2198/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:5:p:2198-:d:1604494

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().