Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors

• URL: http://arxiv.org/abs/2604.02139v1
• Date: Thu, 02 Apr 2026 15:12:24 GMT
• Title: Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors
• Abstract summary: This study investigates a fully data-driven framework for MHD state reconstruction.<n>SHallow REcurrent Decoder (SHRED) is a neural network architecture designed to reconstruct the full-temporal state.<n>SHRED achieves high reconstruction accuracy, generalization, and to magnetic field intensities, orientations, and temporal evolutions not seen during training.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Magnetohydrodynamic (MHD) phenomena play a pivotal role in the design and operation of nuclear fusion systems, where electrically conducting fluids (such as liquid metals or molten salts employed in reactor blankets) interact with magnetic fields of varying intensity and orientation, influencing the resulting flow dynamics. The numerical solution of MHD models entails the resolution of highly nonlinear, multiphysics systems of equations, which can become computationally demanding, particularly in multi-query, parametric, or real-time contexts. This study investigates a fully data-driven framework for MHD state reconstruction that integrates dimensionality reduction through Singular Value Decomposition (SVD) with the SHallow REcurrent Decoder (SHRED), a neural network architecture designed to reconstruct the full spatio-temporal state from sparse time-series measurements of selected observables, including previously unseen parametric configurations. The SHRED methodology is applied to a three-dimensional geometry representative of a portion of a WCLL blanket cell, in which lead-lithium flows around a water-cooled tube. Multiple magnetic field configurations are examined, including constant toroidal fields, combined toroidal-poloidal fields, and time-dependent magnetic fields. Across all considered scenarios, SHRED achieves high reconstruction accuracy, robustness, and generalization to magnetic field intensities, orientations, and temporal evolutions not seen during training. Notably, in the presence of time-varying magnetic fields, the model accurately infers the temporal evolution of the magnetic field itself using temperature measurements alone. Overall, the findings identify SHRED as a computationally efficient, data-driven, and flexible approach for MHD state reconstruction, with significant potential for real-time monitoring, diagnostics and control in fusion reactor systems.

Related papers

• Real-Time Monitoring of MHD Liquid Metal Flows with Shallow Recurrent Decoders [0.21108097398435333]
  State estimation in magnetohydrodynamic flows is critical for real-time monitoring of liquid metal blankets in tokamak fusion reactors.<n>This work investigates a data- driven Reduced Order Model framework to map sparse temperature measurements to the full thermo-hydraulic system's state.
  arXiv  Detail & Related papers  (2026-08-28T14:17:47Z)
• Virtual Temperature Sensors in Power Transformers Using Neural Ordinary Differential Equations [42.50242605797505]
  This paper develops a physics-aware Neural Ordinary Differential Equation framework for forecasting transformer thermal behavior.<n>A key contribution is the integration of simplified heat-transfer equations directly into the Neural ODE formulation.<n>The framework provides a standardized, physics-aware, and robust forecasting approach for heterogeneous transformer units.
  arXiv  Detail & Related papers  (2026-08-13T13:59:32Z)
• Surrogate models for nuclear fusion with parametric Shallow Recurrent Decoder Networks: applications to magnetohydrodynamics [0.0]
  This work investigates a data-driven framework for MHD state reconstruction.<n>SHRED is a neural network architecture designed to recover the full-temporal state from sparse time-series measurements.<n>Results show that SHRED accurately reconstructs the full MHD state even for magnetic field intensities not included in the training set.
  arXiv  Detail & Related papers  (2026-03-11T11:43:39Z)
• Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory [45.322818939044645]
  We aim to learn wavefunctions simulated by time-dependent density functional theory (TDDFT)<n>In real-time TDDFT, the electronic wavefunctions of a molecule evolve over time in response to an external excitation.<n>We propose OrbEvo, which learns to evolve the full electronic wavefunction coefficients across time steps.
  arXiv  Detail & Related papers  (2026-03-03T20:34:05Z)
• Gradient Networks for Universal Magnetic Modeling of Synchronous Machines [39.146761527401424]
  This paper presents a physics-informed neural network approach for dynamic modeling of saturable synchronous machines.<n>We introduce an architecture that incorporates gradient networks directly into the fundamental machine equations.<n>We validate the proposed approach using measured and finite-element method (FEM) datasets from a 5.6-kW permanent-magnet synchronous machine.
  arXiv  Detail & Related papers  (2026-02-16T17:28:42Z)
• Physics Aware Neural Networks: Denoising for Magnetic Navigation [3.624059602945058]
  Airborne systems face a key challenge in extracting geomagnetic field data: the aircraft itself induces magnetic noise.<n>We propose a framework based on two physics-based constraints: divergence-free vector field and E(3)equivariance.<n>Experiments show that embedding these constraints significantly improves predictive accuracy and physical plausibility, outperforming classical deep learning approaches.
  arXiv  Detail & Related papers  (2026-02-14T09:23:57Z)
• Magnetic field estimation using Gaussian process regression for interactive wireless power system design [6.102646086243458]
  Wireless power transfer with coupled resonators offers a promising solution for the seamless powering of electronic devices.<n>Interactive design approaches that visualize the magnetic field and power transfer efficiency can facilitate the understanding and exploration of these systems.<n>We introduce a machine learning approach using Gaussian Process Regression (GPR), demonstrating for the first time the rapid estimation of the entire magnetic field and power transfer efficiency for near-field coupled systems.
  arXiv  Detail & Related papers  (2025-10-22T06:26:38Z)
• Observation of Magnetic Devil's Staircase-Like Behavior in Quasiperiodic Qubit Lattices [55.2480439325792]
  devil's staircase (DS) phenomenon is a fractal response of magnetization to external fields.<n>We uncover a wealth of abrupt magnetic transitions driven by increasing external magnetic fields within a simple yet effective Ising-model framework.<n>Our results challenge the prevailing view that DS behavior is limited to periodic systems.
  arXiv  Detail & Related papers  (2025-07-24T21:39:06Z)
• Towards Efficient Parametric State Estimation in Circulating Fuel Reactors with Shallow Recurrent Decoder Networks [3.422016133670755]
  This paper considers as a test case the Molten Salt Fast Reactor (MSFR), a Generation-IV reactor concept, characterised by strong coupling between the neutronics and the thermal hydraulics.<n>The accurate reconstruction of every characteristic field in real-time makes this approach suitable for monitoring and control purposes in the framework of a reactor digital twin.
  arXiv  Detail & Related papers  (2025-03-11T21:32:28Z)
• Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal [46.348283638884425]
  This paper introduces a reverse Latent Evolution Model (rLEM) designed for temporal phase of forward beam dynamics. In this two-step self-supervised deep learning framework, we utilize a Conditional Autoencoder (CVAE) to project 6D space projections of a charged particle beam into a lower-dimensional latent distribution. We then autoregressively learn the inverse temporal dynamics in the latent space using a Long Short-Term Memory (LSTM) network.
  arXiv  Detail & Related papers  (2024-08-14T23:09:01Z)
• A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators [46.348283638884425]
  We propose a two-step unsupervised deep learning framework named as Latent Autoregressive Recurrent Model (CLARM) for learning dynamics of charged particles in accelerators. The CLARM can generate projections at various accelerator sampling modules by capturing and decoding the latent space representation. The results demonstrate that the generative and forecasting ability of the proposed approach is promising when tested against a variety of evaluation metrics.
  arXiv  Detail & Related papers  (2024-03-19T22:05:17Z)
• A machine-learning-based tool for last closed magnetic flux surface reconstruction on tokamak [58.42256764043771]
  Nuclear fusion power created by tokamak devices holds one of the most promising ways as a sustainable source of clean energy. One main challenge research field of tokamak is to predict the last closed magnetic flux surface (LCFS) determined by the interaction of the actuator coils and the internal tokamak plasma. We present a new machine learning model for reconstructing the LCFS from the Experimental Advanced Superconducting Tokamak (EAST) that learns automatically from the experimental data.
  arXiv  Detail & Related papers  (2022-07-12T17:15:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.