To address the challenge of real-time and global monitoring of the structural stress state of large port gantry cranes in complex working environments, this paper proposes a digital twin system framework covering the physical layer, data layer, model layer, and application layer, utilizing a container gantry crane as the case study. A multi-dimensional working condition space covering key working condition parameters such as lifting load and trolley position is designed, and a stress surrogate model based on the Radial Basis Function (RBF) neural network is constructed. This realizes a rapid mapping from low-dimensional operating parameters to high-dimensional full-field stress distributions. The surrogate model is integrated into the visualization platform, achieving real-time dynamic rendering and threshold exceedance warning of the stress of the key structures of the crane. The results show that the constructed surrogate model ensures the prediction accuracy (R² > 0.94) and achieves millisecond-level calculation response, demonstrating good real-time performance and reliability. It provides a reference for the digital monitoring of large-scale equipment.

Accurate assessment of cumulative fatigue damage in container gantry cranes under long-term cyclic loading is hindered by the inability of traditional single-model methods to capture real-time structural conditions. This paper proposes a digital twin-driven framework that fuses multi-source data for dynamic fatigue life prediction. The framework’s core is an improved Extended Hyper-Heuristic Neural Network (EHH-NN), which incorporates regularization optimization, a split node structure, and ANOVA-based function decomposition to model complex stress responses under limited training data. The improved model achieves a goodness of fit (R²) of 0.942 and a mean relative error of 4.4%, outperforming standard BP and LSTM models while maintaining a prediction time of 42 ms. A closed-loop correction mechanism driven by measured stress feedback is designed to dynamically adjust model outputs, and a prototype system integrating PLC-based data acquisition with Unity3D 2022.3 visualization is developed to demonstrate engineering applicability.