Upskilling for Quality 4.0: Competency Models and Micro-credentials for Smart Factories

Industry 4.0 has transformed manufacturing quality by incorporating AI, IoT, and big data for predictive maintenance and operational excellence in smart factories. However, while anomaly detection and maintenance prediction using technical solutions are well advanced, their alignment with workforce competency falls behind. In this paper, COMP-ANN (Competency & Micro-Credential ANN Framework) is introduced as a novel neural network framework integrating real-time IoT anomaly detection, micro-credentialing, and competency mapping in order to facilitate Quality 4.0 workforce development. COMP-ANN is demonstrated on the Smart Manufacturing IoT-Cloud Monitoring dataset to analyze and process sensor data for anomaly detection and maintenance prediction while mapping results to skill-based learning modules at the same time. Comparative evaluation with Isolation Forest, One-Class SVM, and LSTM demonstrates that COMP-ANN outperforms all baselines in Accuracy (98.54%), Precision (98.79%), Recall (98.28%), and F1-score (98.53%). The model holds excellent promise in bridging the gap between intelligent systems and human capital development through enabling scalable upskilling and operational resilience in digital manufacturing ecosystems.