SELF-LEARNING

Self-Learning – Reliable Self-Learning Production Systems Based on Context Aware Services

Objective

The strategic objective is to strengthen EU leadership in production technologies in the global marketplace by developing innovative self-learning solutions to enable tight integration of control & maintenance of production systems. The project will develop highly reliable and secure service-based self-learning solutions aiming at that integration. The Methodology addressing organisational aspects of such a radical change in production systems, within extended enterprise concept, applying lean principles will be elaborated. Approaches based on SOA principles, using distributed networked embedded services in device space, are the most appropriate for implementation of such self-learning solutions. The main obstacles to fully utilize the opportunities offered by service-based self-learning systems are problems related to reliability, availability, interoperability and security & trust of diverse SW services. Context awareness, providing information about the processes & equipment and circumstances under which the services operate and allowing them to react accordingly, is a promising holistic approach to assure needed self-learning adaptation to changes in processes and equipment states and, on the other hand, Quality of Services needed for such self-learning production systems. The project will develop context models and self-learning context extractor, self-learning adapter for control, maintenance and parameter identification, as well as SOA based infrastructure including security & trust framework and an agent based middleware introduced in the service structure. The project will be driven by three industrial application scenarios from 3 industrial partners, where self-learning components and SOA infrastructure for integrated control and maintenance will be applied for machine tools, FMS and assembly lines in discrete manufacturing. The proposed approach will lead to maintenance costs reduction of 12%, and to an increase by 10% of Overall Equipment Effectiveness