Strategies for digital twin calibration, including trajectory selection and limited budget for parameter measurements, are studied. A framework combining a reinforcement learning controller, recurrent parameter estimator, and budgeted query policy is proposed. Training on optimized trajectories achieves high accuracy with limited queries.
The news is relevant to modeling practice as efficient calibration of digital twins is critical for their accuracy and practical use in system management.
Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.
