Journal article
AI-Driven Smart Manufacturing: Digital Twin and VR-Enabled Predictive Maintenance for Industrial Efficiency Optimization
Proceedings of ASME 2025 International Mechanical Engineering Congress and Exposition, IMECE 2025, v 7, V007T10A039
2025
Abstract
The advent of Industry 4.0 has driven the integration of artificial intelligence (AI), digital twin technology, and virtual reality (VR) into modern manufacturing ecosystems. This study presents an AI-enhanced digital twin framework for intelligent manufacturing monitoring, using real-world datasets and standardized repositories, with a focus on predictive maintenance and process optimization. The proposed system combines predictive analytics, synchronized simulation, and immersive VR training to deliver real-time insights supporting proactive decision-making. Key contributions include a multivariate time-series predictive maintenance model, a physics-aware digital twin, and human-in-the-loop VR training modules. A predictive maintenance model powered by AI and deep learning algorithms forecasts potential equipment failures based on historical anomaly detection and operational telemetry, significantly reducing unscheduled downtime. Experimental results demonstrate significant improvements in overall equipment effectiveness (OEE), defect reduction, and downtime minimization. Additionally, preliminary explainable AI analyses (SHAP and LIME) enhance interpretability and operator trust. The findings underscore the potential of integrated AI-digital twin-VR ecosystems as a scalable approach for next-generation smart manufacturing across domains such as aerospace, pharmaceuticals, and automotive production.
Metrics
1 Record Views
Details
- Title
- AI-Driven Smart Manufacturing: Digital Twin and VR-Enabled Predictive Maintenance for Industrial Efficiency Optimization
- Creators
- Yunshun Chiou - Drexel UniversityNijanthan Vasudevan - Drexel UniversityArjuna Karthikeyan Senthilvel Kavitha - Drexel UniversityTzu Liang Tseng - The University of Texas at El Paso
- Publication Details
- Proceedings of ASME 2025 International Mechanical Engineering Congress and Exposition, IMECE 2025, v 7, V007T10A039
- Conference
- ASME 2025 International Mechanical Engineering Congress and Exposition, IMECE 2025 (Memphis, Tennessee, United States, 16 Nov 2025–20 Nov 2025)
- Grant note
- State of New Jersey Department of Education (100004839)
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Scopus ID
- 2-s2.0-105036106073
- Other Identifier
- 991022180001104721