Get Started
Home
Topics
Search
Library
Research questionHow can we reconstruct full reactor states from sparse, noisy temperatures despite limited sensor dynamics and model mismatch?A few temperature measurements do not directly reveal the reactor’s unobserved fields, especially when sensors are placed in regions with little temporal variation. Estimates can also be distorted when the numerical fluid-dynamics model and experimental measurements disagree.
AI
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II ReactorThe evidence concerns a fluid-dynamics model of the TRIGA Mark II research reactor, synthetic temperatures generated by that model, and experimental temperatures recorded during a previous campaign. The source applies Shallow Recurrent Decoder networks and reports synthetic average relative error below 4% and experimental temperature RMSE of 1.52 K, compared with 1.85 K for the CFD model.research paper · Sep 4, 2026
Related questions
How can we estimate a strongly coupled reactor’s full internal state from three noisy external measurements across operating and accident scenarios?How can offline traffic speed fields be reconstructed from sparse fixed sensors without smoothing sharp LWR transitions or costly decomposition training?How can symbolic regression recover stoichiometric dynamics from noisy data without violating physical laws?How reliably can sparse PDE discovery recover phase-ordering dynamics from limited, noisy spatiotemporal data?