Integration of Machine Learning Task Definition in Model-Based Systems Engineering using SysML

Abstract

In order to allow Systems Engineers to utilize data produced in cyber-physical systems (CPS), they have to cooperate with data-scientists for custom data-extraction, data-preparation, and/or data-transformation mechanisms. While interfaces in CPS systems might be generic, the data that is produced for custom application needs has to be transformed and merged in very specific ways, to allow systems engineers proper interpretation and insight-extraction. In order to enable efficient cooperation between systems engineers and data scientists, the systems engineers have to provide a fine-grained specification that (a) describes all parts of the CPS, (b) how they might interact, (c) what data is exchanged between them, and (d) how the data inter-relates. A data scientists can then iteratively (including further refinements of the specification) prepare the necessary custom machine-learning models and components. Therefore, this work introduces a method supporting the collaborative definition of machine learning tasks by leveraging model-based systems engineering in the formalization of the systems modeling language SysML. The method supports the identification and integration of various data sources, the required definition of semantic connections between data attributes and the definition of the data processing steps within the machine learning support. Integrating machine learning-specific properties in systems engineering techniques allows non-data scientists to define a machine learning problem, document knowledge on the data, and further supports data scientists to use the formalized knowledge as input for an implementation.