Summary
This paper presents a machine learning surrogate model for predicting quench protection heater delay in high-field Nb₃Sn accelerator magnets, addressing computational challenges inherent in traditional numerical simulations. The neural network model, trained on a dataset spanning relevant heater designs and cable parameters, achieves near-perfect accuracy (R² = 0.9996) whilst reducing computation time to under 1 second, offering a practical tool for magnet designers without requiring investment in complex numerical modelling infrastructure.
UK applicability
This work is not applicable to UK farming systems, soil health, nutrient density, or food production. The research concerns superconducting magnet engineering for particle accelerators and is tangential to the Pulse Brain catalogue's scope.
Key measures
Heater delay (milliseconds); mean absolute error; R-squared coefficient; neural network simulation time; comparison against 1D numerical simulations
Outcomes reported
The study developed and validated a machine learning-based surrogate model using a dataset of heater delay simulations for Nb₃Sn accelerator magnets. The neural network model predicts heater delay with high accuracy (mean absolute error 0.063 ms, R² = 0.9996) using only 7 input parameters, with computation time under 1 second.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.