Enabling Digital Transformation in Aerospace: Automated Model Based Engineering

Model-based development (MBD) and testing are critical for airborne software compliance with DO-178C and its supplement DO-331, which specifically addresses model-based approaches for software levels A through D. Traditional manual methods for MBD and testing are time-consuming and prone to variability, impacting consistency, accuracy, and certification timelines as avionics systems grow in complexity. This paper presents an automation framework designed to align with DO-331 objectives by leveraging fine-tuned large language models (LLMs) to automate the generation of high-level textual requirements and low-level model-based requirements. From these, comprehensive test cases are automatically derived, covering normal, edge, mutant, and dynamic scenarios to ensure thorough validation of model behavior. Utilizing Boeing AI, the framework extracts requirements and key parameters from documentation, enabling automated specification analysis and test script generation that simulate real-world operational conditions. The approach supports rigorous verification of model artifacts, a core DO-331 objective, by systematically generating test cases that validate model correctness and robustness. Test effectiveness is measured by injecting single faults (mutants) into sample models and verifying that the generated tests detect these faults, providing a quantitative metric for coverage and test quality. This iterative process ensures comprehensive validation and supports safety assurance. By automating model-based test generation, the framework reduces manual effort, accelerates certification, and enhances consistency and accuracy. Its scalability addresses the increasing complexity of avionics software, improving reliability and safety while facilitating compliance with DO-331 and DO-178C standards.