{"title":"Skill-and-Knowledge Sharing HUB-CI model for resilient production systems","authors":"Praditya Ajidarma , Shimon Y. Nof","doi":"10.1016/j.ijpe.2025.109681","DOIUrl":null,"url":null,"abstract":"<div><div>The use of innovative technologies and the integration of efficient human-robot interaction have had a significant influence on all facets of modern manufacturing. While automation has advanced, numerous tasks still depend on human operators due to their superior dexterity and reasoning abilities. Augmented reality (AR) has emerged as a critical enabler, enhancing the skills of less-experienced workers, improving operational resilience, and enabling rapid adaptation to disruptions. This study presents a novel skill-and-knowledge-sharing paradigm for manufacturing systems. The architecture, called HUB-CI (a hub for collaborative intelligence), facilitates an efficient learning protocol. The model uses quantified learning curves to evaluate operator performance over time and incorporates AR-driven skill and knowledge sharing to reduce response times, optimize scheduling makespan, and improve resilience metrics such as system stability, adaptability, and recovery speed under disruptive conditions. Numerical experiments reveal that HUB-CI significantly decreases response times and improves scheduling makespan by up to 20.52 % after 500 iterations, (p-value <0.01) and achieves consistent performance gains under disruptive conditions, due to its ability to maintain makespan robustness within 5 % of the non-disrupted baseline. In more stable environments with converging agent skill levels, the model sustains strong performance, demonstrating its versatility. By integrating quantified learning curves with four core resilience metrics—adaptability, collaboration and visibility, robustness, and sustainability—HUB-CI enables adaptive task allocation and real-time collaboration, offering a substantial advancement in cyber-collaborative production systems.</div></div>","PeriodicalId":14287,"journal":{"name":"International Journal of Production Economics","volume":"287 ","pages":"Article 109681"},"PeriodicalIF":10.0000,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Production Economics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925527325001665","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}
引用次数: 0
Abstract
The use of innovative technologies and the integration of efficient human-robot interaction have had a significant influence on all facets of modern manufacturing. While automation has advanced, numerous tasks still depend on human operators due to their superior dexterity and reasoning abilities. Augmented reality (AR) has emerged as a critical enabler, enhancing the skills of less-experienced workers, improving operational resilience, and enabling rapid adaptation to disruptions. This study presents a novel skill-and-knowledge-sharing paradigm for manufacturing systems. The architecture, called HUB-CI (a hub for collaborative intelligence), facilitates an efficient learning protocol. The model uses quantified learning curves to evaluate operator performance over time and incorporates AR-driven skill and knowledge sharing to reduce response times, optimize scheduling makespan, and improve resilience metrics such as system stability, adaptability, and recovery speed under disruptive conditions. Numerical experiments reveal that HUB-CI significantly decreases response times and improves scheduling makespan by up to 20.52 % after 500 iterations, (p-value <0.01) and achieves consistent performance gains under disruptive conditions, due to its ability to maintain makespan robustness within 5 % of the non-disrupted baseline. In more stable environments with converging agent skill levels, the model sustains strong performance, demonstrating its versatility. By integrating quantified learning curves with four core resilience metrics—adaptability, collaboration and visibility, robustness, and sustainability—HUB-CI enables adaptive task allocation and real-time collaboration, offering a substantial advancement in cyber-collaborative production systems.
期刊介绍:
The International Journal of Production Economics focuses on the interface between engineering and management. It covers all aspects of manufacturing and process industries, as well as production in general. The journal is interdisciplinary, considering activities throughout the product life cycle and material flow cycle. It aims to disseminate knowledge for improving industrial practice and strengthening the theoretical base for decision making. The journal serves as a forum for exchanging ideas and presenting new developments in theory and application, combining academic standards with practical value for industrial applications.