•  
  •  
 

Journal of System Simulation

Abstract

Abstract: The construction of accurate and highly real-time digital twin models in complex industrial setting presents several challenges. Traditional model construction approaches based only on mechanism or data show certain limitations. Therefore, this study is based on the idea of grey-box modeling, taking the cantilever structure within a boom-type roadheader as the object, and proposes a novel modeling approach that combines the characteristics of the mechanism model and introduces a self-attention mechanism. This method performs grayscale transformation on the original input and splices it with physical features to achieve organic fusion of mechanism information, which not only enhances the expressiveness and generalization of the twin model, but also improves training efficiency. Additionally, the introduction of a data model structure incorporating self-attention mechanisms enhances the model's capability to analyze temporal features, consequently augmenting the accuracy of the digital twin model. The effectiveness of this method has been validated through experiments, demonstrating a substantial improvement in modeling performance compared to traditional approaches. This advancement opens new possibilities for the design, operation, and maintenance of boom-type roadheaders.

First Page

1158

Last Page

1168

CLC

TP391.9

Recommended Citation

Zhang Wenjia, Zhang Heming. Research on Grey-box Modeling Method of Digital Twins for Cantilever Structure[J]. Journal of System Simulation, 2025, 37(5): 1158-1168.

Corresponding Author

Zhang Heming

DOI

10.16182/j.issn1004731x.joss.24-0040

Download

Share

COinS