Model-Based Scenario Engineering Using Large Language Models for Vehicle Concept Development

Future-oriented requirements are difficult to capture during the early phases of vehicle concept development because conventional requirements engineering primarily considers current stakeholder needs and system environments. This paper proposes an evidence-based Model-Based Scenario Engineering approach that integrates Large Language Models (LLMs) into Model-Based Systems Engineering (MBSE) methodology to systematically incorporate future developments into early requirements engineering. The proposed method combines three complementary models: a stakeholder model, a system model, and a future scenario model. Scientific publications are analyzed by an LLM to extract evidence-based future descriptors, their characteristics, and candidate impact relationships. The extracted knowledge is stored in a structured knowledge layer before being linked to relevant model artifacts, thereby establishing end-to-end traceability from scientific evidence to system model elements. The approach is demonstrated using a case study on an electrified powertrain, illustrating how future developments can be systematically connected to user needs and vehicle requirements. The proposed framework contributes to early requirements engineering by enabling evidence-based, traceable, and model-integrated consideration of future developments while maintaining expert validation throughout the engineering process.