.png){kind=icon}
.png){kind=icon}
Return
Blockchain-secured multi-factory production with collaborative maintenance using Q learning-based optimisation approach
.png){kind=icon}
PRE
AI
DOI：10.1080/00207543.2021.2002968.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To quickly manufacture multi-variety and low-volume products, manufacturing factories are increasingly sharing resources on collaborative production networks. However, the reliability of communication between factories cannot be fully guaranteed using traditional centralised approaches. Emerging blockchain technology can solve this problem due to its characteristics such as decentralisation and security. In this context, an integrated optimisation problem of multi-factory production and blockchain-secured collaborative maintenance is studied in this paper. Two scenarios are introduced with respective Q learning-based solution frameworks to solve the integrated problem. In the simulation scenario, preventive maintenance (PM) with flexible time windows is integrated with multi-factory production scheduling for reducing the probability of machine failures, and an initial integrated optimisation scheme is obtained. To make it more realistic, inevitable failures are considered in the actual production scenario, and the proposed collaborative maintenance strategy is triggered. Specifically, a corrective maintenance (CM) strategy is carried out immediately on the failed machine in case of a failure, followed by the PM on machines of the same type as the failed machine in other factories and the rescheduling of unprocessed jobs. Through a series of numerical studies, the effectiveness of the proposed optimisation approach and maintenance strategy is validated, and some interesting managerial implications also rise.
Keywords:
Blockchain technology
multi-factory production
preventive maintenance
corrective maintenance
reinforcement learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.3
Papers:
1.1W
Citations:
3.7W