Research on Anomaly Detection for Industrial Robots Based on Temporal Graph Neural Networks and Differential Privacy

To address the issue that differential privacy noise severely degrades the performance of federated learning in anomaly detection of industrial robots, this paper proposes a privacy-accuracy co-optimization mechanism.This mechanism constructs a Temporal Graph Neural Network (T-GNN) that integrates dynamic graph convolution and temporal attention to jointly encode the physical connections and statistical correlations of multiple joints in a robot, effectively modeling the spatiotemporal coupling relationship of multi-source heterogeneous sensor data.