Cyber-Physical Systems integrate hardware with software in complex applications. To mitigate the complexity, engineers rely on model-based systems engineering approaches. Updates and function enhancements lead to frequently changing design constraints and objectives. These changes increase the need to rework and extend model artifacts of the system. This can cause quality degradation over time due to modeling errors, knowledge disparities, or a lack of guidelines. To enable efficient collaboration and reduce maintenance costs in model-based systems engineering, the industry needs a cost-efficient, scalable approach to monitor model quality. The work outlines a doctoral thesis investigating the potential of automated data-driven quality assessment strategies using model artifact history and model changes. We will extract metrics and model changes to establish quality feedback for system engineers. We aim to use manual model quality assessments to incorporate domain-specific expert knowledge into the automated strategy. The main goals are to lower the effort of model quality assessments, to provide practitioners with foresight on quality development, and to estimate task effort to improve model quality. 

Companies increasingly rely on Model-Based Systems Engineering to develop Cyber-Physical Systems such as cars, aircraft, or medical devices. The quality of engineering model artifacts is key to efficient collaboration in systems engineering with multi-tier supply chains. Ensuring model artifact quality and comprehensibility for practitioners is challenging. Manual reviews are time- and cost-intensive and subject to bias, whereas existing automated methods based on syntactical rules and model metrics are limited in scope. The paper presents work towards swift quality feedback to system engineers during modeling. The concept allows domain and project-specific context and is applicable to industry-size model artifacts. We implement a data-driven estimation that combines automated model metric extraction with expert quality assessments. We leverage the system model version history from an open-source miniature automotive demonstrator. We assess the model versions' comprehensibility and showcase a semi-automated pipeline to initiate a model quality estimator. We achieve an average accuracy of 0.94 with a random forest approach on our test data.