Traditional methods for requirement identification depend on the manual transformation of unstructured requirement texts into formal documents, a process that is both inefficient and prone to errors. Although requirement knowledge graphs offer structured representations, current named entity recognition and relation extraction techniques continue to face significant challenges in processing the specialized terminology and intricate sentence structures characteristic of the aerospace domain. To overcome these limitations, this study introduces a novel approach for constructing aerospace-specific requirement knowledge graphs using a large language model. The method first employs the GPT model for data augmentation, followed by BERTScore filtering to ensure data quality and consistency. An efficient continual learning based on token index encoding is then implemented, guiding the model to focus on key information and enhancing domain adaptability through fine-tuning of the Qwen2.5 (7B) model. Furthermore, a chain-of-thought reasoning framework is established for improved entity and relation recognition, coupled with a dynamic few-shot learning strategy that selects examples adaptively based on input characteristics. Experimental results validate the effectiveness of the proposed method, achieving F1 scores of 88.75% in NER and 89.48% in relation extraction tasks.

In the design of fluid systems, rapid iteration and simulation verification are essential, and reduced-order modeling techniques can significantly improve computational efficiency and accuracy. However, traditional Physics-Informed Neural Networks (PINNs) often face challenges such as vanishing or exploding gradients when learning flow field characteristics, limiting their ability to capture complex fluid dynamics. This study presents an enhanced reduced-order model (ROM): Physics-Informed Neural Networks based on Residual Networks (Res-PINNs). By integrating a Residual Network (ResNet) module into the PINN architecture, the proposed model improves training stability while preserving physical constraints. Additionally, the model’s ability to capture and learn flow field states is further enhanced by the design of a symmetric parallel neural network structure. To evaluate the effectiveness of the Res-PINNs model, two classic fluid dynamics problems—flow around a cylinder and Vortex-Induced Vibration (VIV)—were selected for comparative testing. The results demonstrate that the Res-PINNs model not only reconstructs flow field states with higher accuracy but also effectively addresses limitations of traditional PINN methods, such as vanishing gradients, exploding gradients, and insufficient learning capacity. Compared to existing approaches, the proposed Res-PINNs provide a more stable and efficient solution for deep learning-based reduced-order modeling in fluid system design.

Automatically generating accurate SysML models from natural-language requirements can substantially accelerate the adoption of Model-Based Systems Engineering (MBSE) in complex system development. However, using large language models (LLMs) to generate model code often fails to meet the strict syntactic constraints of formal modeling languages, and consistently ensuring semantic alignment between generated models and requirements remains challenging. To address these challenges, this paper presents MAS4SysML, a multi-agent collaborative framework for SysML v2 code generation that improves syntactic correctness and semantic consistency under a constrained repair budget. The framework decomposes a modeling task into hierarchical subtasks, formalizes them as structured task cards, and generates model code in a bottom-up manner. During generation, an official validation environment is used for syntax diagnostics; after completion, the framework verifies semantic consistency between the code and the task cards. If syntax or semantic validation fails, the framework iteratively repairs and revalidates the code within a predefined repair budget, guided by diagnostic feedback, until the validation criteria are satisfied or the budget is exhausted. To evaluate the proposed method, we construct a SysML v2 dataset spanning five core task types-requirements, use cases, structure, parametrics, and state machines-and conduct comparative experiments. Results show that MAS4SysML reduces the average syntax error rate to 2.63, increases semantic similarity to 0.91, and outperforms existing code-generation methods overall.

The reduced-order-model(ROM) method provides a strong support for the rapid iteration and simulation verification of supporting fluid system design. This study focuses on the problems of gradient disappearance or explosion and incomplete learning of flow field characteristics in the training process of PINN ROM. Based on PINN model, an innovative ROM Res-PINNs is proposed. By embedding ResNet module into PINN neural network structure, it strives to improve the training stability of the model while retaining physical knowledge. In addition, parallel network structure is added to the model to improve its perception and learning ability of flow field state.At last, in order to verify the validity of the proposed model, two classical fluid problems, the flow around a cylinder and Vortex-Induced Vibration(VIV), are selected to compare and verify the proposed Res-PINNs model. The results show that Res-PINNs can reconstruct the flow field state more accurately, effectively overcome the problems of gradient disappearance or explosion and poor learning ability of PINN model during training, and provide a new solution for the application of deep learning order reduction method in aerospace system modeling and simulation.