Atomistic Simulation Guided Convolutional Neural Networks for Thermal Modeling of Friction Stir Welding

• URL: http://arxiv.org/abs/2512.21344v1
• Date: Mon, 15 Dec 2025 16:41:42 GMT
• Title: Atomistic Simulation Guided Convolutional Neural Networks for Thermal Modeling of Friction Stir Welding
• Authors: Akshansh Mishra,
• Abstract summary: Molecular dynamics simulations were performed using LAMMPS to model aluminum friction stir welding at the atomic scale.<n>A two-dimensional convolutional neural network was developed to predict temperature directly from the spatially resolved atomistic data.
• Score: 0.33842793760651557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate prediction of temperature evolution is essential for understanding thermomechanical behavior in friction stir welding. In this study, molecular dynamics simulations were performed using LAMMPS to model aluminum friction stir welding at the atomic scale, capturing material flow, plastic deformation, and heat generation during tool plunge, traverse, and retraction. Atomic positions and velocities were extracted from simulation trajectories and transformed into physics based two dimensional spatial grids. These grids represent local height variation, velocity components, velocity magnitude, and atomic density, preserving spatial correlations within the weld zone. A two-dimensional convolutional neural network was developed to predict temperature directly from the spatially resolved atomistic data. Hyperparameter optimization was carried out to determine an appropriate network configuration. The trained model demonstrates strong predictive capability, achieving a coefficient of determination R square of 0.9439, a root mean square error of 14.94 K, and a mean absolute error of 11.58 K on unseen test data. Class Activation Map analysis indicates that the model assigns higher importance to regions near the tool material interface, which are associated with intense deformation and heat generation in the molecular dynamics simulations. The results show that spatial learning from atomistic simulation data can accurately reproduce temperature trends in friction stir welding while remaining consistent with physical deformation and flow mechanisms observed at the atomic scale.

Related papers

• Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves [39.92721695835137]
  A physics-constrained Gaussian Process regression framework is developed for predicting shocked material states along the Hugoniot curve.<n>The framework reproduces the Hugoniot curve with satisfactory accuracy while also quantifying the uncertainty in the predictions.
  arXiv  Detail & Related papers  (2026-01-10T18:54:24Z)
• Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport [41.94295877935867]
  Local-Global Convolutional Neural Network (LGCNN) approach is introduced.<n>Model is first systematically analyzed based on random input fields.<n>Then, the model is trained on a handful of cut-outs from a real-world Classical map of the Munich region in Germany.
  arXiv  Detail & Related papers  (2025-07-08T15:06:15Z)
• Thermal state preparation by repeated interactions at and beyond the Lindblad limit [41.94295877935867]
  We study the nature of thermalization dynamics and the associated preparation (simulation) time under the repeated interaction protocol.<n>We observe a Mpemba-like effect: Starting from a maximally mixed state, thermalization to an intermediate-temperature state takes longer than to a lower-temperature one.
  arXiv  Detail & Related papers  (2025-06-13T18:34:49Z)
• Physics-based machine learning for mantle convection simulations [2.4608654148475235]
  We propose a machine learning approach that predicts creeping flow velocities as a function of temperature while conserving mass.<n>A finite-volume solver then uses the predicted velocities to advect and diffuse the temperature field to the next time-step, enabling autoregressive rollout at inference.<n>Overall, our model is up to 89 times faster than the numerical solver.
  arXiv  Detail & Related papers  (2025-05-21T21:47:43Z)
• Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning [46.67399627400437]
  This research confronts the challenge of substantial physical equation discrepancies in the generation of physical fields through trained models.<n>A physical field generation model, named HMT-PF, is developed based on the hybrid Mamba-Transformer architecture.
  arXiv  Detail & Related papers  (2025-05-16T14:40:56Z)
• Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials [6.6716708904054896]
  Atomic transport underpins the performance of materials in technologies such as energy storage and electronics.<n>We introduce LiFlow, a generative framework to accelerate MD simulations for crystalline materials.<n>We benchmark LiFlow on a dataset comprising 25-ps trajectories of lithium diffusion across 4,186 SSE candidates at four temperatures.
  arXiv  Detail & Related papers  (2024-10-02T12:16:46Z)
• Physics-Informed Machine Learning Towards A Real-Time Spacecraft Thermal Simulator [15.313871831214902]
  The PIML model or hybrid model presented here consists of a neural network which predicts reduced nodalizations given on-orbit thermal load conditions. We compare the computational performance and accuracy of the hybrid model to a data-driven neural net model, and a high-fidelity finite-difference model of a prototype Earth-orbiting small spacecraft. The PIML based active nodalization approach provides significantly better generalization than the neural net model and coarse mesh model, while reducing computing cost by up to 1.7x compared to the high-fidelity model.
  arXiv  Detail & Related papers  (2024-07-08T16:38:52Z)
• Event-Based Simulation of Stochastic Memristive Devices for Neuromorphic Computing [41.66366715982197]
  We build a general model of memristors suitable for the simulation of event-based systems. We extend an existing general model of memristors to an event-driven setting. We demonstrate an approach for fitting the parameters of the event-based model to the drift model.
  arXiv  Detail & Related papers  (2024-06-14T13:17:19Z)
• Accurate melting point prediction through autonomous physics-informed learning [52.217497897835344]
  We present an algorithm for computing melting points by autonomously learning from coexistence simulations in the NPT ensemble. We demonstrate how incorporating physical models of the solid-liquid coexistence evolution enhances the algorithm's accuracy and enables optimal decision-making.
  arXiv  Detail & Related papers  (2023-06-23T07:53:09Z)
• Reduced Order Probabilistic Emulation for Physics-Based Thermosphere Models [0.0]
  This work aims to employ a probabilistic machine learning (ML) method to create an efficient surrogate for the Thermosphere Ionosphere Electrodynamics Circulation General Model (TIE-GCM) We show that across the available data, TIE-GCM ROPE has similar error to previous linear approaches while improving storm-time modeling. We also conduct a satellite propagation study for the significant November 2003 storm which shows that TIE-GCM ROPE can capture the position resulting from TIE-GCM density with 5 km bias.
  arXiv  Detail & Related papers  (2022-11-08T17:36:37Z)
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-B\'{e}nard convection [0.0]
  Two-dimensional turbulent Rayleigh-B'enard convection flow at Prandtl number $rm Pr=7$ and Rayleigh number $rm Ra=107$. Two recurrent neural networks are applied for the temporal advancement of flow data in the reduced latent data space. Convolutional autoencoder with 12 hidden layers is able to reduce the dimensionality of the turbulence data to about 0.2 % of their original size.
  arXiv  Detail & Related papers  (2022-02-26T12:39:19Z)

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.