A co-evolving diagnostic algorithm for evolvable production systems: A case of learning

With the systematic implantation and acceptance of IT in the shop-floor a wide range of Production Paradigms have emerged that exploring these technological novelties promise to revolutionize the way current plant floor operate and react to emerging opportunities and disturbances. With the increase of distributed and autonomous components that interact in the execution of processes current diagnostic approaches will soon be insufficient. While current system dynamics are complex and to a certain extent unpredictable the adoption of the next generation of approaches and technologies comes at the cost of an yet increased complexity. The peer to peer nature of the interactions and the evolving nature of the future systems' structure require a co-evolving regulatory mechanism that to a great deal has to be implemented under the scope of monitoring and diagnosis. In this article a diagnostic algorithm that has the ability to co-evolve with the remaining system, through learning and adaptation to the operational conditions, is presented and discussed.