In the product design and manufacturing process, the effective management and representation of system requirements (SRs) are crucial for ensuring product quality and consistency. However, current methods are hindered by document ambiguity, weak requirement interdependencies, and limited semantic expressiveness in model-based systems engineering. To address these challenges, this paper proposes a prompt-driven integrated framework that synergizes large language models (LLMs) and knowledge graphs (KGs) to automate the visualization of SR text and structured knowledge extraction. Specifically, this paper introduces a template for information extraction tailored to arbitrary requirement documents, designed around five SysML-defined SR categories: functional requirements, interface requirements, performance requirements, physical requirements, and design constraints. By defining structured elements for each category and leveraging the GPT-4 model to extract key information from unstructured texts, the system can effectively extract and present the structured requirement information. Furthermore, the system constructs a knowledge graph to represent system requirements, visually illustrating the interdependencies and constraints between them. A case study applying this approach to Chapters 18–22 of the ‘Code for Design of Metro’ demonstrates the effectiveness of the proposed method in automating requirement representation, enhancing requirement traceability, and improving management. Moreover, a comparison of information extraction accuracy between GPT-4, GPT-3.5-turbo, BERT, and RoBERTa using the same dataset reveals that GPT-4 achieves an overall extraction accuracy of 84.76% compared to 79.05% for GPT-3.5-turbo and 59.05% for both BERT and RoBERTa. This proves the effectiveness of the proposed method in information extraction and provides a new technical pathway for intelligent requirement management.

Hydraulic generator design companies are always being exhorted to become more competitive by reducing the lead time and costs for their products for survival. Knowledge-based engineering technology is a rapidly developing technology with competitive advantage for design application to reduce time and cost in product development. This article addresses the structure of the hydraulic generator design system based on the knowledge-based engineering technology in detail. The system operates by creating a unified knowledge base to store the scattered knowledge among the whole life of the design process, which was contained in the expert’s brain and technical literature. It helps designers to make appropriate decisions by supplying necessary information at the right time through query and inference engine to represent the knowledge within the knowledge-based engineering application framework. It also integrates the analysis tools into one platform to help achieve global optimum solutions. Finally, an example of turbine-type selection was given to illustrate the operation process and prove its validity.

In the context of rapid product iteration, design conflicts arise from discrepancies in designers’ understanding of user needs, influenced by subjective preferences, behavioural stances, and other factors. This paper proposes a product conceptual design approach based on the design conflict perspective. First, user comments and design documents are collected. Natural language processing (NLP) methods, including cleaning, filtering, lexical segmentation, feature clustering, and sentiment analysis, are employed to identify design themes. The intuitionistic fuzzy sets (IFSs) and term frequency–inverse document frequency (TF-IDF) algorithms are then utilized to obtain evaluation matrices for the products from both users and designers. Subsequently, design conflicts between users and designers are calculated, and an optimal configuration for product conceptual design is determined through regression analysis and planning methods. Finally, the proposed method is validated using a mobile phone as a product example, and suggestions for product improvement are presented. The results indicate that considering design conflicts as a factor in product design and synthesizing designer and user product concepts enhance the accuracy and reliability of product conceptual design generation. The findings of this study offer new insights into the conceptual design configuration for product iteration.

This paper presents a DEA-MARS two-stage nonparametric model. It measures the distribution of the efficiency of the Information Technology (IT) investment in the equipment manufacturing industry and identifies the key factors that influence the efficiency of the IT investment. The measurement shows that there is comparatively large difference in the investment efficiency. The empirical research indicates that the Enterprise Scale, IT Strategy, and the interaction between the IT Training and the Application of Information System are the key factors that influence the input efficiency.

In this paper, the transmission process of the heald frame driven by the dobby is analyzed. The equivalent motion model of the dobby modulator, the eccentric mechanism, and the motion transmission unit are constructed. Then, based on the given movement characteristics of the heald frame, the mathematical model is built to achieve the cam pitch curve and the cam profile of the modulator. The numerical solution method for this is developed. The preparation of a mathematical model for the new concept of the solving cam profile based on the motion characteristics of heald frames is explained in this study. By setting a 11^th polynomial motion law of the heald frame, due to the inconsistency between the outward and return motion laws of the crank-rocker mechanism, an asymmetrical cam profile is obtained under the premise of ensuring that the heald frames ascending and descending motions are consistent. Through the kinematics simulation analysis, the correctness of the reverse process is verified.