Mining electric shovels are essential equipment for intermittent and semi-continuous extraction of solid resources in open-pit mines. As the demand for increased mining efficiency continues to rise, ensuring the reliability and safety of these machines becomes paramount. Digital twins, as a critical tool for structural performance monitoring, not only facilitate the analysis of dynamic characteristics but also help mitigate fatigue failure during operation. To address the real-time requirements of digital twin models, this paper introduces a model reduction approach that integrates proper orthogonal decomposition with radial basis functions (POD-RBF) for shape-performance integrated digital twins. A case study on the performance prediction of the front-end working device of a specific mining electric shovel demonstrates the advantages of the proposed method in terms of both computational accuracy and efficiency compared to traditional finite element models. The results indicate that the proposed approach significantly enhances the online computational efficiency of digital twin models while maintaining high accuracy.