A Mental Health-Integrated Digital Twin for Intelligent Equipment: Development and Validation with Multimodal Psychophysiological Data
Yungang DongAbstract
Objective
This study aimed to develop and validate a digital twin system for intelligent equipment operation that integrates real-time multimodal psychophysiological data. The objective was to create a holistic monitoring platform that supports both equipment health and operator mental well-being by assessing cognitive workload and emotional state alongside mechanical status.
Subjects and Methods
A prototype digital twin was developed, synchronizing real-time equipment sensor data with multimodal operator data: EEG for cognitive load, heart rate variability (HRV) for stress, and facial expression analysis. The system was tested with 25 operators performing standardized maintenance tasks over four weeks. Its alerts for predictive maintenance and psycho-physiological stress were validated against post-task self-reports and actual equipment diagnostics.
Results
The system successfully predicted 92% of mechanical anomalies with a 3.5-hour average lead time. Concurrently, it identified periods of high operator cognitive overload and negative emotional states with 85% accuracy compared to survey benchmarks. A significant correlation was found between specific psycho-physiological patterns and an increased probability of minor operational errors.
Conclusions
The developed digital twin effectively integrates equipment and human data, enabling a comprehensive approach to system health. It demonstrates significant potential for preemptive maintenance and, crucially, for safeguarding operator mental health and safety in human-machine collaborative environments.
Corresponding Author
Yungang Dong, Qingdao Huanghai University, Qingdao 266555, Shandong, China.