Construction of an Efficient Digital Twin Surrogate Model for Robotic Arms Based on Random Forest

The performance of robotic arms is crucial for industrial production. However, traditional simulation and detection methods are plagued with issues such as high computational complexity and low efficiency, failing to meet the high precision, high reliability, and high real time requirements of robotic arms. This study introduces digital twin technology and constructs a digital twin surrogate model based on the random forest algorithm to address the challenges in robotic arm simulation and detection. After establishing a 3D model of the robotic arm, multi-condition simulations were first carried out to obtain multi-dimensional data. Following data cleaning and normalization, grid search was used to determine the optimal hyperparameters of the random forest model, which was then compared with the support vector machine (SVM) model. The results demonstrate that the established model has significant advantages in terms of accuracy and stability. Its computational efficiency far surpasses that of traditional simulations, with prediction time only taking a few seconds, remarkably enhancing the feasibility and real-time performance of engineering applications. The research findings provide strong support for the structural optimization, operation and maintenance, and fault prevention of robotic arms.