cs.AIOct 31, 2026

LM6-CastBench: A Geometry-Aware Simulation Dataset for Transient Thermal Prediction in LM6 Sand Casting

Authors: Suhani Kolhatkar, Anand Khandekar

Organizations: COEP Technological University · Arcticturn Foundation

Abstract

Transient thermal fields during solidification connect casting process conditions and cooling behaviour to the formation of defect-prone regions in aluminum cast ings. Repeatedly solving this thermal problem across geometries and process conditions is computationally expensive, motivating data-driven surrogate models. However, existing machine-learning studies on casting thermal behaviour rely on study-specific simulation databases that do not support reproducible geometry-level benchmarking. We introduce LM6-CastBench, an open simulation dataset for geometry-aware learning of transient thermal fields in LM6 aluminum sand casting, combining three geometry families, ten variants per family, five pouring tempera tures, and three mould temperatures (450 geometry-process cases in total). Each case retains CAD geometry, unstructured mesh connectivity, spatial descriptors, process metadata, and time-resolved nodal temperatures. We benchmark a point wise MLP against a spatially structured U-Net under geometry-level data splits; the U-Net reduces temperature-field errors by a large margin, with the biggest gains on geometries with localized features and abrupt section changes. LM6-CastBench gives researchers a reproducible dataset and benchmark for geometry-aware surro gate modelling of casting thermal behaviour.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Feb 20, 2026

Stable Long-Horizon Spatiotemporal Prediction on Meshes Using Latent Multiscale Recurrent Graph Neural Networks

Accurate long-horizon prediction of spatiotemporal fields on complex geometries is a fundamental challenge in scientific machine learning, with applications such as additive manufacturing where temperature histories govern defect formation and mechanical properties. High-fidelity simulations are accurate but computationally costly, and despite recent advances, machine learning methods remain challenged by long-horizon temperature and gradient prediction. We propose a deep learning framework for predicting full temperature histories directly on meshes, conditioned on geometry and process parameters, while maintaining stability over thousands of time steps and generalizing across heterogeneous geometries. The framework adopts a temporal multiscale architecture composed of two coupled models operating at complementary time scales. Both models rely on a latent recurrent graph neural network to capture spatiotemporal dynamics on meshes, while a variational graph autoencoder provides a compact latent representation that reduces memory usage and improves training stability. Experiments on simulated powder bed fusion data demonstrate accurate and temporally stable long-horizon predictions across diverse geometries, outperforming existing baseline. Although evaluated in two dimensions, the framework is general and extensible to physics-driven systems with multiscale dynamics and to three-dimensional geometries.
Nov 16, 2026

ThermLeT: Transformer-based Temperature Prediction for 2.5D Chiplet Architecture

The drive toward heterogeneous 2.5D chiplet packages promises unmatched performance and customization, yet the resulting density amplifies thermal challenges. To facilitate rapid design space exploration, we present ThermLeT, a multimodal transformer-based, scale invariant surrogate that integrates power density maps, spatial coordinate embeddings, material properties and heat transfer rate to predict steady state temperature in 13 ms, about four orders of magnitude faster than conventional finite element solvers such as ANSYS. To train the transformer model, we also create a dataset of 6,221 chiplet layouts perturbed from three representative architectures. On a 150 sample test set, ThermLeT achieves an RMSE of 3.16°C and an MAE of 2.24°C, improving accuracy by 35% over ThermEDGe and by 71% over HotSpot, while running approximately 6x and 11x lower inference latencies respectively. Ablation studies confirm robust generalization to unseen floorplans. Code and dataset available at https://github.com/MicroSystemsDesignLab/ThermLeT
Jun 3, 2026

Reconstructing Unobservable Temperature Fields via Simulation-Aided Intelligent Sensing

Real-time monitoring of the temperature distribution within components and sub-structures is a challenging topic in many systems due to restrictions on feasible sensor locations. While machine learning (ML) proves a versatile tool in many applications, its adoption for high-resolution thermal monitoring is hindered by the availability of high-quality datasets for training. In this work, we propose a novel approach for generating datasets for industrial applications based on randomized physics-based simulations. We demonstrate the approach in a proof-of-concept hardware setup: A neural network (NN) trained only on such a synthetic dataset, is used to reconstruct the internal temperature field from sparse sensors embedded in the hardware. The NN-based reconstructions do not only outperform Kriging in robustness but also enable real-time inference, making the method suitable for online monitoring of otherwise unobservable thermal states.