Human-Centric Smart Manufacturing under Industry 5.0:IIoT-Enabled Machine Learning for Real-Time Fault Identification and Adaptive Workforce Scheduling

Abstract

This study addresses Industry 5.0's demand for human-machine collaboration and manufacturing resilience by developing machine learning models for rapid fault identification and adaptive personnel scheduling. When a production-line fault occurs, the proposed approach uses IIoT data to identify the fault category quickly, support targeted intervention, and facilitate the restoration of normal production. XGBoost achieved near-perfect fault identification accuracy in model evaluation and accuracy and recall of 1.0 in validation, significantly outperforming the Random Forest baseline. Analysis revealed that experienced operators increased product qualification rates by 15% but reduced output by 10% due to physical factors. Decision tree regression minimized scheduling errors with an MSE of 0.49 and an R2 of 0.83. These results demonstrate that integrating IIoT-driven rapid fault identification with intelligent staffing provides a practical basis for shortening the response cycle, improving recovery capability after disruptions, and strengthening the resilience of human-centric manufacturing systems.