Highly flexible manufacturing systems require continuous run-time (self-) optimization of processes with respect to diverse parameters, e.g., efficiency, availability, energy consumption etc. A promising approach for achieving (self-) optimization in manufacturing systems is the usage of the context sensitivity approach based on data streaming from high amount of sensors and other data sources. Cyber-physical systems play an important role as sources of information to achieve context sensitivity. Cyber-physical systems can be seen as complex intelligent sensors providing data needed to identify the current context under which the manufacturing system is operating. In this paper, it is demonstrated how context sensitivity can be used to realize a holistic solution for (self-) optimization of discrete flexible manufacturing systems, by making use of cyber-physical systems integrated in manufacturing systems/processes. A generic approach for context sensitivity, based on self-learning algorithms, is proposed aiming at a various manufacturing systems. The new solution encompasses run-time context extractor and optimizer. Based on the self-learning module both context extraction and optimizer are continuously learning and improving their performance. The solution is following Service Oriented Architecture principles. The generic solution is developed and then applied to two very different manufacturing processes.

The key idea of the work presented is to explore how a combination of advanced Ambient Intelligence (AmI) and Knowledge Management (KM) technologies can be used to assure a sustainable and safe use of Manufacturing and Assembly Lines (MAL) and their infrastructure over their life-cycle. The specific intention is to reduce the whole service-life operational costs and impact of MAL, providing new ways to monitor on-line Life-Cycle Parameters (LCP) of MAL and improved services to support MAL throughout its whole life-cycle. The paper presents a new system for effective life cycle management of complex MAL, including computation of LCP based on information obtained from AmI systems within MAL, and delivery of improved services around MAL.

During the last years (basically since 1999), the author and his research team are and have been involved in several research projects within the field of Product Life-Cycle Knowledge Management in the manufacturing domain. The key idea behind these projects is to develop means supporting the collection of all useful knowledge on product and process throughout the extended enterprise, all along the product Life-Cycle from Conception to Disposal and eventual Reuse. Keeping and re-using knowledge is of capital importance for the companies' competitivity to be used in continuous improvement of existing product/processes as well as in new developments. In a further step, the knowledge will then be developed into a means of fostering industrial innovations. Innovation is a critical factor in the success of manufacturing companies and it will mainly arise by combining ideas and feedback from all phases of the product life cycle.

Highly flexible manufacturing systems require continuous run-time (self-) optimization of processes with respect to various parameters, e.g. efficiency, availability, energy consumption etc. A promising approach for achieving (self-) optimization in manufacturing systems is the usage of the context sensitivity approach. Thereby the Cyber-Physical Systems play an important role as sources of information to achieve context sensitivity. In this paper it is demonstrated how context sensitivity can be used to realize a holistic solution for (self-) optimization of discrete flexible manufacturing systems, by making use of Cyber-Physical System integrated in manufacturing systems/processes. A generic approach for context sensitivity, based on self-learning algorithms, is proposed aiming at a various manufacturing systems. The new solution is propos encompassing run-time context extractor and optimizer. Based on the self-learning module both context extraction and optimizer are continuously learning and improving their performance. The solution is following Service Oriented Architecture principles. The generic solution is developed and then applied to two very different manufacturing processes. This paper proposes a holistic solution to achieve context sensitivity for Flexible Manufacturing Systems, whereby the knowledge created by applying the context sensitivity approach can be used for (self-) optimization of manufacturing processes.