An Intelligent and Automatic System Design Approach for Complex Equipment Conceptual Design
Systems Engineering · 30.07.2026
DOI: 10.1002/sys.70085 ↗Kurz gefasst
Fachartikel in der Zeitschrift Systems Engineering, online erschienen am 30.07.2026. Verfasst von Wenqiang Yuan und 6 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben.
Abstract (Originalsprache)
Addressing the challenges of transforming natural language requirements and the lengthy design cycles inherent in complex systems such as aerial bomb guidance control systems, this study proposes an automated system design method based on large language models (LLMs) and knowledge graphs (KGs). A novel instruction framework, REQUIRE, is proposed to guide the transformation of unstructured natural language requirements into a structured function ontology using an LLM. Subsequently, automatic mapping from the function ontology to a component ontology is achieved through KG‐based semantic reasoning. Finally, an optimized module combination generation algorithm is utilized to swiftly generate component‐level design solutions, and the performance of these solutions is evaluated using a comprehensive performance scoring model. Experimental results demonstrate that, compared with traditional methods, this approach can generate system design solutions that meet the specified requirements more expeditiously, thus providing a novel approach for the intelligent design of complex systems.
Zitieren
APA
Yuan, W., Wang, K., Li, W., Luo, W., Chen, J., Lu, J., & Niu, B. (2026). An Intelligent and Automatic System Design Approach for Complex Equipment Conceptual Design. Systems Engineering. https://doi.org/10.1002/sys.70085
Vancouver
Yuan W, Wang K, Li W, Luo W, Chen J, Lu J, et al. An Intelligent and Automatic System Design Approach for Complex Equipment Conceptual Design. Systems Engineering. 2026. doi:10.1002/sys.70085
BibTeX
@article{Yuan2026,
author = {Yuan, Wenqiang and Wang, Kaidi and Li, Wenlong and Luo, Weifeng and Chen, Jiawen and Lu, Jianfeng and Niu, Biao},
title = {An Intelligent and Automatic System Design Approach for Complex Equipment Conceptual Design},
journal = {Systems Engineering},
year = {2026},
doi = {10.1002/sys.70085}
}
EUVIMED