Intelligent system modeling using GenAI: A methodology for automated simulation model generation

Abstract

Generative AI (GenAI) has demonstrated remarkable capabilities in code generation, and its integration into model-based systems engineering for complex product modeling and simulation code generation can significantly enhance the efficiency of product design and modeling. In this study, we introduce a generative system modeling framework, offering a practical approach for the intelligent generation of simulation models for system physical properties. First, we fine-tune the language model used for simulation model generation on an existing library of simulation models and additional datasets generated through generative modeling. Subsequently, we employ BERT-based inference techniques, generative models, and integrated modeling and simulation languages to construct simulation models for system physical properties of products based on product design documents. Thereafter, we introduce evaluation metrics for the generated simulation models for system physical properties. Finally, we propose a validation and simulation framework for generated simulation models. Our proposed approach to simulation model generation presents the innovative concept of scalable templates for simulation models. Using these templates, GenAI generates simulation models for system physical properties through code completion. The experimental results demonstrate that, for mainstream open-source Transformer-based models, the quality of the simulation model is improved by 21.4% using the simulation model generation method proposed in this paper.