Customer-oriented architecture refinement in multi-criteria synthesis of large-scale system architectures

Designing complex system architectures involves analysing tradeoffs between multiple conflicting decision criteria to find a solution which best matches the preferences of the customer. This is usually done in the engineering characteristic (decision criteria) space, but the customer is generally more interested in higher-level characteristics. For example, the engineering characteristic "modularity" is not of direct interest to a customer, but it is related to their concern "through-life costs", since modular systems can be upgraded more easily. The relationships between customer and engineering concerns are many-to-many making it difficult to relate the two sets of priorities. This paper proposes an integrated system architecture synthesis framework, which aims to maximise customer satisfaction by using their preferences directly to refine a set of candidate architectures. The novelty of the research relates to the translation from customer preferences to decision criteria limits on a parallel coordinates plot. This automated flow facilitates rapid re-synthesis of "best" architectures following a change in customer preferences. The time saved allows customers to investigate a wider range of concerns and gain a better understanding of how their priorities influence the solution set. The approach is presented on a case study of a control system for a pressurized water reactor.