An agent-based interaction-oriented shop floor to support emergent diagnosis

Abstract

The emerging production paradigms, potentiated by the advances in Information Technologies (IT), especially in web related standards and technologies as well as the progressive acceptance of the multiagent systems (MAS) concept and related technologies, envision collections of modules whose individual and collective function adapts and evolves ensuring the fitness and adequacy of the shop floor in tackling profitable but volatile business opportunities. Despite the richness of the interactions and the effort set in modeling them, their potential to favor fault propagation and interference, in these complex environments, has been ignored from a diagnostic point of view. To avoid corrupting the distributed nature of the system any diagnostic method/tool should necessarily adapt and evolve. This implies that the diagnostic model should emerge in system rather than being imposed. In the present paper the authors contend that there is added value in further considering interactions and modeling the network effect of interactions for the purpose of diagnosing the system. In this context, an agent-based architecture is proposed to support an emergent diagnostic model.

Current status and advancement of cyber-physical systems in manufacturing

“…This led to Service Oriented Architectures (SoA), where Rockwell Automation [11] and Schneider Electric [12] developed interesting solutions. In later years a great deal of work has been carried out by academia [13,14], which has consolidated this approach. In 2011 the first self-organising assembly system was demonstrated at FESTO in Germany, this approach being based on Agent Oriented Architectures (AoA).…”

“…It ran with a multi-agent control setup (Agent-oriented Architecture), could be reconfigured on-the-fly, and consisted of modules self-configured thanks to their embedded controllers. The MiniProd system relied on many years research [14,47] and the following developments:…”

Developments in integration of advanced monitoring systems

“…A multi-agent distributed diagnostic framework operating based on a Bayesian algorithm was also proposed [197]. An attempt to build agent-based interaction-oriented shop floor systems to support emergent diagnosis is another example [198].…”

Context and implications of learning in Evolvable Production Systems

“…An implementation of a multi-agent production systems based on the EPS concept is presented in [20]. In this architecture each shop-floor module is abstracted by a generic mechatronic agent.…”