Towards adaptive flexibility in automation systems. Industrial control software based on normalized systems theory

Date: 27 June 2014

Venue: University of Antwerp, Hof van Liere, Elsschot & Greshamzaal - Prinsstraat 13B - 2000 Antwerp

PhD candidate: Dirk van der Linden

Principal investigator: Prof Herbert Peremans

Short description: PhD defense Dirk van der Linden - Faculty of Applied Economics

Abstract: Complex software systems typically have a modular structure, from which the modules are possibly developed in a distributed manner. These modules need to collaborate to fulfill their functional tasks. This implies that modules have an impact on other modules, via the coupling they need to collaborate.

Changes or extensions in such a system often cause an exponential increase of development, maintenance and test costs. Consequently, the integration of innovative ideas in the existing system is restrained. Over time, extensions become very expensive, it might even become 'cheaper' to re-write the system, in order to re-enable further extensions.

In the research group the Normalized Systems Theory is developed to enable the building of systems which are immune for this phenomenon. In other words, systems of which the impact (effort) of changes relates to the new functionality, not to the size of the existing system.

In this work the application of Normalized Systems Theory in the domain of automation systems was investigated. How should this theory be applied? What implications can be expected for typical development environments, architectures and existing industrial standards? Is it possible to introduce constraints on existing system in order to achieve a higher evolvability?

This research started from a number of reference models, i.e., three industrial standards and the Normalized Systems Elements, which are theoretic definitions of evolvable software building blocks. The results include software artifacts that comply both with the industrial standards and Normalized Systems Theory.

During the realization of a number of proof of concept systems various difficulties have cropped up, the solution of which has led to the definition of two additional theorems about instance traceability. Finally, a set of design rules is formulated that facilitates the implementation of Normalized Systems Theory in automation systems.