About Workshop
This 3-day international mentor-led workshop introduces participants to the development of AI-enabled Digital Twins for predictive maintenance. The program progresses from fundamental Digital Twin concepts and industrial sensor monitoring to machine-learning-based fault prediction, equipment degradation analysis, RUL estimation, Explainable AI, and maintenance decision support.
Aim
To provide participants with practical knowledge of Digital Twin technology, industrial sensor analytics, machine learning, fault prediction, Remaining Useful Life (RUL), and Explainable AI for developing predictive maintenance solutions aligned with Industry 5.0.
What Participants Will Learn
- Understand Digital Twin concepts and architectures for Industry 5.0.
- Differentiate Digital Models, Digital Shadows, and Digital Twins.
- Analyze industrial sensor and machine-condition data.
- Develop machine-health indicators and equipment health states.
- Apply machine learning for fault detection and failure prediction.
- Perform feature engineering on multi-sensor industrial datasets.
- Estimate equipment failure probability and maintenance risk.
- Understand equipment degradation and Prognostics & Health Management.
- Develop models for Remaining Useful Life estimation.
- Apply Explainable AI using SHAP for maintenance predictions.
- Perform what-if maintenance scenario analysis.
- Integrate AI outputs into a Digital Twin workflow.
- Translate predictive results into human-centered maintenance decisions.
Structure
Day 1: Digital Twin Foundations & Machine Health Monitoring
- Industry 4.0 vs Industry 5.0
- Digital Model, Digital Shadow & Digital Twin
- Industrial IoT and sensor data
- Condition monitoring & machine-health indicators
- Data preprocessing and health-state mapping
- Digital Twin dashboard development
Hands-On: Build a sensor-based machine health Digital Twin
Day 2: AI-Based Fault Detection & Predictive Maintenance
- Predictive maintenance workflow
- Industrial feature engineering
- Fault classification & anomaly detection
- Random Forest and XGBoost
- Failure probability & risk scoring
- Model evaluation and Digital Twin integration
Hands-On: Develop an AI-powered fault prediction Digital Twin
Day 3: RUL, Explainable AI & Maintenance Decision Support
- Equipment degradation & PHM
- Remaining Useful Life estimation
- RUL regression models
- Explainable AI with SHAP
- What-if maintenance simulation
- Human-in-the-loop Industry 5.0 decisions
- Emerging trends in intelligent Digital Twins
Hands-On: Build an explainable RUL-aware maintenance decision Digital Twin
Tools
Google Colab | Python | Pandas | NumPy | Scikit-learn | XGBoost | SHAP | Plotly | Streamlit
Important Dates
Registration Ends
4:30 PM
Workshop Dates
2026-09-14
5:00 PM
5:00 PM
What You Will Gain
Outcomes
- Explain the role of Digital Twins in predictive maintenance.
- Process and visualize industrial sensor datasets.
- Build a basic machine-health Digital Twin.
- Identify abnormal and degrading equipment conditions.
- Develop ML-based fault prediction models.
- Calculate machine failure probabilities and risk levels.
- Estimate Remaining Useful Life of industrial equipment.
- Interpret predictive models using Explainable AI.
- Identify the major factors contributing to equipment degradation or failure.
- Compare different maintenance intervention scenarios.
- Generate explainable maintenance recommendations.
- Understand how predictive maintenance supports resilient, sustainable, and human-centric Industry 5.0 systems.
Who Should Attend
- Faculty Members & Academicians
- Researchers & Ph.D. Scholars
- Postdoctoral Researchers
- Industry Professionals
- Maintenance & Reliability Engineers
- Mechanical & Manufacturing Engineers
- Industrial & Production Engineers
- Automation and Control Professionals
- Industrial IoT / IIoT Professionals
- Data Scientists & AI/ML Professionals
- Digital Transformation & Smart Manufacturing Teams
- R&D Professionals
- Professionals interested in Digital Twins, Predictive Maintenance, PHM, Smart Manufacturing, and Industry 5.0