Course Overview
This course examines the engineering principles underlying AI-enabled digital twins, with emphasis on hybrid modeling approaches, verification and validation, risk and uncertainty, and professional accountability. Through three applied case studies—bridge health monitoring, power system load forecasting, and industrial predictive maintenance—learners evaluate how AI-enhanced digital twins perform in real-world engineering contexts, including their benefits, limitations, and failure modes.
 

Upon completion of this course, participants will be able to:

1. Explain the fundamental concept of digital twins and their role in representing physical engineering systems throughout the asset lifecycle.
2. Differentiate traditional physics-based digital twins from AI-enabled digital twins, including the advantages, limitations, and appropriate use cases for hybrid modeling approaches.
3. Describe how artificial intelligence enhances digital twins, including pattern recognition, anomaly detection, forecasting, and adaptive model behavior.
4. Identify common engineering applications of AI-enabled digital twins across infrastructure, power systems, industrial facilities, and other engineered environments.
5. Apply verification and validation principles to assess the reliability, credibility, and limitations of AI-assisted digital twin outputs.
6. Recognize and evaluate sources of risk and uncertainty in AI-enabled digital twins, including probabilistic outputs, data limitations, model drift, and automation bias.
7. Assess common failure modes of AI-enabled digital twins and identify engineering strategies to mitigate their impact on safety, reliability, and decision-making.
8. Evaluate the impact of AI-enabled digital twins across the engineering lifecycle, including design, construction, operation, maintenance, capital planning, and end-of-life decisions.
9. Analyze applied case studies involving AI-enabled digital twins in bridge health monitoring, power system load forecasting, and industrial predictive maintenance to identify benefits, limitations, and lessons learned.
10. Apply professional engineering judgment to determine appropriate reliance on AI-enabled digital twin outputs and to resolve conflicts between data-driven insights and physical principles.
11. Interpret professional responsibility, ethical obligations, and regulatory considerations associated with the use of AI-enabled digital twins in engineering practice.
12. Communicate AI-assisted digital twin results transparently, including assumptions, uncertainty, and limitations, to stakeholders and decision-makers.