Work in Progress: AI-Powered Engineering-Bridging Theory and Practice

2025-02-06

AI Summary

This paper addresses the low efficiency in requirements quality assessment and test specification generation within systems engineering. We propose a generative AI approach grounded in large language models (LLMs), integrating INCOSE’s “good requirements” criteria, prompt engineering, and rule-guided fine-tuning to construct an interpretable requirements quality diagnostic framework. The framework concurrently accomplishes three tasks: (1) defect identification and root-cause attribution (92% accuracy, >85% explanation consistency); (2) automated classification of functional versus non-functional requirements; and (3) generation of ISO/IEC/IEEE 29148-compliant test specification drafts. Employing a mixed quantitative–qualitative methodology—combining engineer annotations with multi-dimensional human evaluation—we establish, for the first time, an explainable, closed-loop AI support system for requirements defect analysis. Results demonstrate significant improvements in requirements engineering automation and pedagogical effectiveness, while uncovering critical constraints regarding AI safety, ethics, and human–AI collaboration in domain-specific practice.

Technology Category

• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This paper explores how generative AI can help automate and improve key steps in systems engineering. It examines AI's ability to analyze system requirements based on INCOSE's "good requirement" criteria, identifying well-formed and poorly written requirements. The AI does not just classify requirements but also explains why some do not meet the standards. By comparing AI assessments with those of experienced engineers, the study evaluates the accuracy and reliability of AI in identifying quality issues. Additionally, it explores AI's ability to classify functional and non-functional requirements and generate test specifications based on these classifications. Through both quantitative and qualitative analysis, the research aims to assess AI's potential to streamline engineering processes and improve learning outcomes. It also highlights the challenges and limitations of AI, ensuring its safe and ethical use in professional and academic settings.

Problem

• AI automates systems engineering processes
• AI evaluates and classifies system requirements
• AI enhances engineering accuracy and learning

Innovation

• Generative AI automates systems engineering steps
• AI analyzes and explains system requirements quality
• AI classifies requirements and generates test specifications