The Adapter module: A building block for Self-Learning Production Systems. (December 2015)

• Record Type: Journal Article
• Authors: Di Orio, Giovanni; Cândido, Gonçalo; Barata, José
• Is Part Of: Robotics and computer-integrated manufacturing. Volume 36(2015)
• Page Start: 25
• Page End: 35
• Publication Date: 2015-12
• Subjects: Agile manufacturing -- Intelligent scheduling -- Context awareness -- Data mining -- SOA; Robots, Industrial -- Periodicals; Computer integrated manufacturing systems -- Periodicals; Robotics -- Periodicals; Robots industriels -- Périodiques; Productique -- Périodiques; Robotique -- Périodiques; 670.285
• DOI: 10.1016/j.rcim.2014.12.007
• Languages: English
• ISSNs: 0736-5845

Abstract

Abstract: The manufacturing companies of today have changed radically over the course of the last 20 years and this trend certainly will continue. The increasing demand and the intense competition in market sharing are radically changing the way production systems are designed and products are manufactured pushing, in this way, the emergence of new manufacturing technologies and/or paradigms. This scenario encourages manufacturing companies to invest in new and more integrated monitoring and control solutions in order to optimize more and more their production processes to enable a faster fault detection, reducing down-times during production while improving system performances and throughput along time. In accordance with these needs, the research done under the scope of Self-Learning Production Systems (SLPS) tries to enhance the control together with other manufacturing activities (e.g. energy saving, maintenance, lifecycle optimization, etc.). The key assumption is that the integration of context awareness and data mining techniques with traditional monitoring and control solutions will reduce maintenance problems, production line downtimes and manufacturing operational costs while guaranteeing a more efficient management of the manufacturing resources. Abstract : Highlights: The Self-Learning Production System delivers productivity gains to manufacturing processes. Machine learning and context awareness to allow control systems to adapt their behavior. The reference architecture of a Self-Learning Production System has been proposed. The Self-Learning Production System Adapter component is presented. A prototype is presented to validate the concept, the feasibility and reliability of the SLPS.