Abrasive belt wear has an important impact on the dimensional accuracy and surface quality of parts. Accurate quantitative measurement of abrasive belt wear is an important basis for optimizing grinding process parameters, but also a very challenging task for abrasive belts with randomly distributed abrasive particles. In this paper, a quantitative method of determining wear state based on the life cycle surface images of the abrasive belt is proposed to evaluate its material removal ability in the grinding process. For blunted abrasive particles with extremely irregular shapes, TransUNet with a hybrid encoding of a CNN and transformer is adopted to obtain strong representation of complex features and high-precision segmentation boundaries. Three other U-net-based semantic segmentation networks are compared to prove the effectiveness of the trained TransUNet model. The number and area of blunted abrasive particles were calculated by connected domain and statistical methods. The proportion of worn abrasive particles and the wear area ratio when the service life of the abrasive belt is exhausted are about 74.29% and 3.06%, respectively.

Digital twins are digital representations of physical entities that enable real-time updates through data transmission between the physical and virtual domains. Based on a cloud–edge–device framework, this paper investigates methods for real-time data transmission, processing, and storage during the polishing process of a belt grinding robot. On this basis, a digital twin monitoring framework is constructed for blade-specific belt grinding robots. First, a virtual robot model was constructed using a joint modeling workflow in SolidWorks 2025 and 3ds Max 2025, incorporating a lightweight high-fidelity mesh processing algorithm based on the QEM method. Second, a data acquisition and transmission architecture was proposed for the belt grinding robot, enabling data reading, writing, and real-time monitoring during machining, as well as establishing a cloud–edge–device database. Finally, a cloud–edge–device digital twin monitoring framework for the blade belt grinding robot was developed, based on real-time monitoring of grinding process data. This work establishes a foundational data acquisition and visualization platform for the blade grinding robot, providing the necessary cyber-physical infrastructure, which future predictive models can develop and validate.