A closed-loop design approach based on the combination of knowledge graph and digital twin: a high-speed train bogie case study

Abstract

With the increasing complexity of industrial products, data-complete closed-loop feedback design throughout the product lifecycle has become a research frontier in the field of modern intelligent manufacturing. However, the accuracy and efficiency of optimization iterations in existing design methods are hindered by inconsistent formats and semantics of multi-source data, difficulties in dynamically updating model parameters, and challenges in mapping associations between models and data. To address the above issues, this paper proposes a closed-loop design approach based on the combination of knowledge graph (KG) and digital twin (DT). Firstly, the DT model is divided into three dimensions, namely information model, mechanism model and field model, based on metamodel theory, and adopts a unified paradigm expression to improve the generality among models. Then, a multi-dimensional information mapping mechanism based on KG is proposed. It uses KG as an information exchange mediator between physical data and DT models, regulates the interaction of heterogeneous data from multiple sources, and realizes data transmission and mapping between models. On this basis, the DT model parameters are corrected in combination with the querying and reasoning capabilities of the KG to form a continuous feedback knowledge update loop and an enhanced closed-loop design process. Finally, a case study is conducted in the design of high-speed train bogie. The results show that the modification accuracy of the model’s low-order modal frequency is improved to 97.79%, and the maximum stress, lightweight and safety indexes are improved by 14.96%, 13.81% and 2.82%, respectively. Comparative experiments on the next generation bogie show that the iterations of the method have a positive effect, with the stiffness performance improving by up to 17.79% at critical locations.