Variant generation of software-defined mechatronic systems in model-based systems engineering

Today's systems engineering is challenged by an increasing number of requirements aimed at smaller target audiences. This leads to a rise of variants to fulfill individual consumer demands. Because of the complexity introduced by the surge of software-defined mechatronic systems, deriving new variants manually is becoming increasingly difficult. As of today, however, there exist no well- established methods or tools to assist in variant generation. This article aims to fill this gap by presenting a novel approach that enables an automated, requirements-based variant generation. For this purpose, a variant meta-model capable of both storing and interconnecting physical parameters and qualitative criteria of system components is designed and translated into a machine-readable form. The resulting data model is described to be stored inside a multi-model database, allowing for the integration of past project data by using data mining techniques. Additionally, a variant generation algorithm with a strategy for targeted exploration of the variant solution space is presented. The complete approach is realized by implementing a demo application that includes both the multi-model database and a java application for algorithm execution. Our work is evaluated by benchmarks using a dataset with real-world components, indicating that requirements-conform variants can be generated in a reasonable time.