A Deep Learning-based surrogate model for Severe Accidents in nuclear reactors using ASTEC

• URL: http://arxiv.org/abs/2607.04450v1
• Date: Sun, 05 Jul 2026 18:23:17 GMT
• Title: A Deep Learning-based surrogate model for Severe Accidents in nuclear reactors using ASTEC
• Abstract summary: Accident Source Term Evaluation Code (ASTEC) is a powerful tool to study the physics of Severe Accidents (SAs) in nuclear reactors.<n>SA simulators can take up to several days per simulation, making their use infeasible for real time applications.<n>We show how to speed up a SA simulator with a fast, Deep Learning based (DL) surrogate model (SM)
• Score: 42.9434097275489
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Integral codes like the Accident Source Term Evaluation Code (ASTEC) are powerful tools to study the physics of Severe Accidents (SAs) in nuclear reactors. Real time SA simulators can also be helpful in training operators of nuclear plants to react correctly to malfunctions. However, SA simulators can take up to several days per simulation, making their use infeasible for real time applications. In this work we show how to speed up a SA simulator with a fast, Deep Learning based (DL), surrogate model (SM). The SM is built as a combination of a dimensionality reduction stage, via an AutoEncoder, and a time-stepping stage, via a Neural Ordinary Differential Equation. The data on which the SM is trained are obtained from the ASTEC simulator, by sampling a set of operator actions for station blackout (SBO) and loss-of-coolant accidents (LOCA). The objective of the developed SM is to approximate multiple spatio-temporal fields for the thermal-hydraulic physics, core degradation, and fission product release modules in ASTEC's vessel domain. The SM predicts simultaneously around $80$ different physical variables (both scalar and fields), maintaining a stable autoregressive rollout up to $50$ thousand time steps. In addition, the AutoEncoder achieves a dimensionality reduction by a factor of over $300$, which allows the SM to predict up to $40$ hours of simulation in under a minute, both on CPU and GPU. This work is the first study of the capabilities and limits of DL based surrogate modeling in approximating the challenging, highly non-linear physics of ASTEC.

Related papers

• Machine Learning-Driven Chemical Reactor Network Modeling of the Sandia-D Flame [0.0]
  Turbulent combustion simulations are crucial for many scientific and engineering systems.<n>The equivalent reactor network (ERN) approach attempts to improve computational efficiency by replacing a multidimensional turbulent simulation with a series of much cheaper 0-D and 1-D chemical reactors.<n>In this work, we develop an automated machine-learning-assisted framework for constructing ERNs of the Sandia-D turbulent methane/air flame.
  arXiv  Detail & Related papers  (2026-06-01T22:52:12Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• A SISA-based Machine Unlearning Framework for Power Transformer Inter-Turn Short-Circuit Fault Localization [3.5962288595735896]
  This paper proposes a framework for power transformer inter-turn short-circuit fault (ITSCF) localization.<n>The SISA method partitions the training data into shards and slices, ensuring that the influence of each data point is isolated.<n>Experiments on simulated ITSCF conditions demonstrate that the proposed framework achieves almost identical diagnostic accuracy to full retraining.
  arXiv  Detail & Related papers  (2026-03-07T00:49:21Z)
• Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine [0.0]
  This paper contributes a distributed memory algorithm that achieves fast and scalable construction of predictive physics-based ROMs trained from sparse datasets of extremely large state dimension.<n>We focus on a real-world three-dimensional RDRE for which one millisecond of simulated physical time requires one million core hours on a supercomputer.
  arXiv  Detail & Related papers  (2024-07-13T20:17:41Z)
• Scientific Machine Learning Based Reduced-Order Models for Plasma Turbulence Simulations [0.0]
  This paper investigates non-intrusive Scientific Machine Learning (SciML) Reduced-Order Models (ROMs) for plasma turbulence simulations. We focus on Operator Inference (OpInf) to build low-cost physics-based ROMs from data for such simulations.
  arXiv  Detail & Related papers  (2024-01-11T15:20:06Z)
• Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management [64.17887333976593]
  Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. We use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization.
  arXiv  Detail & Related papers  (2022-06-21T20:38:13Z)
• DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting [71.50844437057555]
  We present DiSECt: the first differentiable simulator for cutting soft materials. The simulator augments the finite element method with a continuous contact model based on signed distance fields. We show that the simulator can be calibrated to match resultant forces and fields from a state-of-the-art commercial solver.
  arXiv  Detail & Related papers  (2022-03-19T07:27:19Z)
• Accelerating Part-Scale Simulation in Liquid Metal Jet Additive Manufacturing via Operator Learning [0.0]
  Part-scale predictions require many small-scale simulations. A model describing droplet coalescence for LMJ may include coupled incompressible fluid flow, heat transfer, and phase change equations. We apply an operator learning approach to learn a mapping between initial and final states of the droplet coalescence process.
  arXiv  Detail & Related papers  (2022-02-02T17:24:16Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)
• Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation [91.05073136215886]
  "Actor-Learner Distillation" transfers learning progress from a large capacity learner model to a small capacity actor model. We demonstrate in several challenging memory environments that using Actor-Learner Distillation recovers the clear sample-efficiency gains of the transformer learner model.
  arXiv  Detail & Related papers  (2021-04-04T17:56:34Z)

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.