Self-Learning Production Systems: Adapter Reference Architecture

Abstract

To face globalization challenges, today manufacturing companies require 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, and improving system performances and throughput. Today industrial monitoring and control solutions give only a partial view of the production systems status, what compromises the accurate assessment of the system. In this scenario, integrating monitoring and control solutions for secondary processes into shop floor core systems guarantees a comprehensive overview on the entire system and its related processes since it provides access to a greater amount of information than before. The research currently done under the scope of Self-Learning Production Systems (SLPS) tries to fill this gap by providing a new and integrated way for developing monitoring and control solutions. This paper introduces the research background and describes the generic SLPS architecture and focus on the Adapter component responsible for adapting the system according to current context information. The proposed Adapter architecture and its core components are introduced as well as the generic Adaptation Process, i.e., its “modus operandi” to face context changes. Finally, one of three distinct business-case scenarios is presented to demonstrate the applicability of the envisioned reference architecture and Adapter solution into an industrial context as well as its behavior and adaptive ability along system lifecycle.