Real-Time Physiological Fatigue Prediction for Human-Robot Collaborative Manufacturing Using Wearable Sensor Fusion and Hybrid Deep Learning: An In Silico Digital Twin Study.

Human-robot collaboration (HRC) in modern manufacturing environments requires adaptive control strategies to ensure operator safety and ergonomic well-being. This research-oriented project framework addresses the critical challenge of operator physical exhaustion by modeling a real-time physiological fatigue prediction system. Utilizing wearable sensor fusion, the framework integrates multi-modal physiological signals, such as heart rate variability, electromyography, and galvanic skin response, to continuously monitor operator state. A hybrid deep learning architecture, combining convolutional neural networks for spatial feature extraction and recurrent neural networks for temporal sequence modeling, is designed to process these fused sensor streams. To validate the predictive performance without physical risk, an in silico digital twin environment is established, simulating realistic

human-robot collaborative assembly tasks. This digital twin serves as a high-fidelity virtual testbed, enabling the evaluation of the hybrid model's accuracy, latency, and robustness under varying workload conditions. The proposed methodology offers structured guidance for developing closed-loop robotic control systems that dynamically adjust collaborative robot behavior, such as speed and trajectory, based on predicted human fatigue levels, thereby enhancing both operational productivity and occupational safety.

Message: Hi FE, I need help with “Real-Time Physiological Fatigue Prediction for Human-Robot Collaborative Manufacturing Using Wearable Sensor Fusion and Hybrid Deep Learning: An In Silico Digital Twin Study.” in “Electrical Engineering”