A Multi Agent System architecture to implement Collaborative Learning for social industrial assets

Abstract

The ‘Industrial Internet of Things’ aims to connect industrial assets with one another and benefit from the data that is generated, and shared, among these assets. In recent years, the extensive instrumentation of machines and the advancements in Information Communication Technologies are re-shaping the role of assets in our industrial systems. An emerging concept here is that of ‘social assets’: assets that collaborate with each other in order to improve system optimisation. Cyber-Physical Systems (CPSs) are formed by embedding the assets with computers, or microcontrollers, which run real-time decision-making algorithms over the data originating from the asset. These are known as the ‘Digital Twins’ of the assets, and form the backbone of social assets. It is essential to have an architecture which enables a seamless integration of these technological advances for an industry. This paper proposes a Multi Agent System (MAS) architecture for collaborative learning, and presents the findings of an implementation of this architecture for a prognostics problem. Collaboration among assets is performed by calculating inter-asset similarity during operating condition to identify ‘friends’ and sharing operational data within these clusters of friends. The architecture described in this paper also presents a generic model for the Digital Twins of assets. Prognostics is demonstrated for the C-MAPSS turbofan engine degradation simulated data-set (Saxena and Goebel (2008)).