A Stand-Alone Surrogate Model for Predicting Protection Heater Delays in Nb<sub>3</sub>Sn Accelerator Magnets

Quench is an irreversible transition where the magnet locally loses its superconducting properties and becomes resistive. Early quench detection and a prompt protection system response are essential to avoid conductor damage. One of the conventional methods for accelerator magnet quench protection is to place resistive heaters on the surface of the coils. The protection heaters are stainless steel strips which are powered with a voltage pulse from capacitor bank discharge. Current is passing through the heaters, generating heat due to the resistivity of the stainless steel. Heat is transferred to the cable by conduction. There is at least one layer of polyimide film and the cable insulation (impregnated glass fiber) between the heater and the superconducting cable. Heater delay is defined as the required time to reach the current sharing temperature in the cable after heater firing. Typically predicting the heater delay requires numerical simulations which are computationally somewhat challenging and require expertise and need of specific software. In this study, we are providing a fast and easily accessible surrogate model for predicting the heater delay in Nb<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>Sn magnets. Finite Element Method simulations with COMSOL Multiphysics are used for collecting the dataset and training a supervised artificial neural network algorithm. The model can be used for first estimations of heater delay in Nb<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>Sn accelerator magnets during their design phase. In future, the surrogate model could be also integrated with other quench protection design tools to accelerate the detailed protection design of future magnets.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Applied Superconductivity
Published
2024-12-30
DOI
https://doi.org/10.1109/tasc.2024.3523873
Citations
2
Primary Topic
Superconducting Materials and Applications
Type
article
Field-Weighted Citation Impact
0.37
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Stand-Alone Surrogate Model for Predicting Protection Heater Delays in Nb3Sn Accelerator Magnets

Hamed Milanchian, Tiina Salmi, Shahriar Bakrani Balani
2 citations
IEEE Transactions on Applied Superconductivity
Superconducting Materials and Applications
0.37
article

A Stand-Alone Surrogate Model for Predicting Protection Heater Delays in Nb3Sn Accelerator Magnets

Hamed Milanchian, Tiina Salmi, Shahriar Bakrani Balani
article en
2 citations

Abstract

Quench is an irreversible transition where the magnet locally loses its superconducting properties and becomes resistive. Early quench detection and a prompt protection system response are essential to avoid conductor damage. One of the conventional methods for accelerator magnet quench protection is to place resistive heaters on the surface of the coils. The protection heaters are stainless steel strips which are powered with a voltage pulse from capacitor bank discharge. Current is passing through the heaters, generating heat due to the resistivity of the stainless steel. Heat is transferred to the cable by conduction. There is at least one layer of polyimide film and the cable insulation (impregnated glass fiber) between the heater and the superconducting cable. Heater delay is defined as the required time to reach the current sharing temperature in the cable after heater firing. Typically predicting the heater delay requires numerical simulations which are computationally somewhat challenging and require expertise and need of specific software. In this study, we are providing a fast and easily accessible surrogate model for predicting the heater delay in Nb<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>Sn magnets. Finite Element Method simulations with COMSOL Multiphysics are used for collecting the dataset and training a supervised artificial neural network algorithm. The model can be used for first estimations of heater delay in Nb<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>Sn accelerator magnets during their design phase. In future, the surrogate model could be also integrated with other quench protection design tools to accelerate the detailed protection design of future magnets.

IEEE Transactions on Applied SuperconductivityVol. 35(5)
Tampere University (FI)
Affordable and clean energy
Openalex Percentile: Top 41%
Superconducting Materials and Applications
0.37
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.