---
title: "LM6-CastBench: A Geometry-Aware Simulation Dataset for Transient Thermal Prediction in LM6 Sand Casting"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00619v1"
permalink: "https://feed.astralor.com/items/itm_bd90ff3464a6168b55451c34"
published: "2026-10-31T04:39:06.000Z"
score: 56
channel: "ai"
tags: ["LM6-CastBench","Geometry-Aware Simulation Dataset","Transient Thermal Prediction","LM6 Sand Casting","Transient","Repeatedly"]
---

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

## 速览

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 geom…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_bd90ff3464a6168b55451c34