Researchers have developed a new framework for adaptive digital twins that enhances their value in civil engineering applications. This approach utilizes dynamic Bayesian networks to model the interaction between physical and virtual systems, enabling online learning of state transition dynamics through Bayesian updates. The framework allows for a broader range of distributions than current methods and employs reinforcement learning to solve parametric Markov decision processes for precise dynamic policies. This leads to more personalized, robust, and cost-effective digital twins, as demonstrated in a case study on a railway bridge's structural health monitoring and maintenance planning. AI
IMPACT Enhances predictive capabilities and cost-effectiveness of digital twins in civil engineering applications.
RANK_REASON This is a research paper detailing a new framework and methodology for adaptive digital twins. [lever_c_demoted from research: ic=1 ai=1.0]
- Bayesian updates
- civil engineering
- digital twin
- Dynamic Bayesian Networks
- Maintenance Planning of Pitched Roofs in Current Buildings
- Marco Tezzele
- Markov decision processes
- railway bridge
- reinforcement learning
- Structural health monitoring
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
