Model Based Systems Engineering (MBSE) plays a pivotal role in managing the development of increasingly sophisticated automotive systems. As vehicles incorporate more software driven and safety critical functionalities, the need for efficient methods to capture, analyze, and validate system requirements has become paramount. Traditional MBSE practices, which often involve manual handling of requirement documents, can be time-consuming and prone to misinterpretation or omission. This paper explores how Artificial Intelligence (AI), particularly Machine Learning (ML) and Natural Language Processing (NLP), can be used to streamline and enhance the requirements engineering phase within an MBSE framework. We propose a methodology that uses NLP to automatically extract structured requirements from natural language documents and applies ML algorithms to support classification, traceability, and early-stage validation tasks. To demonstrate the viability of this approach, we present a case study centered on an Advanced Driver Assistance System (ADAS), showcasing how AI tools can reduce development time, improve requirement clarity, and identify inconsistencies at early stages of design. The results suggest that AI integration improves efficiency and enhances the robustness of automotive system models. This study outlines key advantages and implementation challenges, offering insight into how AI can complement MBSE processes. Finally, we discuss areas for future research, including the development of domain-specific AI models, integration with existing modeling tools, and the establishment of standard evaluation metrics for AI assisted systems engineering.
Veera Venkata Krishnarjun Rao - (Thu,) studied this question.