低炭素熱延鋼板の小サンプル機械学習予測におけるドメイン知識に基づく特徴量エンジニアリング
Domain-Knowledge-Guided Feature Engineering for Small-Sample Machine Learning Prediction of Mechanical Properties in Low-Carbon Hot-Rolled Steel Strips (原題)
Saurabh Tiwari, Hyoju Ahn, Jongwon Lee, Nokeun Park
🤖 gxceed AI 要約
日本語
本研究は、低炭素鋼の機械的特性予測において、冶金学的知識に基づく特徴量エンジニアリングが小データ条件下での予測精度を向上させるかを検証した。300サンプルから5つの物理的記述子を導出し、XGBoostとRandom Forestで評価した結果、特徴量エンジニアリングにより予測精度が向上し、特に伸びで改善が見られた。学習曲線分析では中間的な訓練データサイズでサンプル効率がわずかに向上した。
English
This study investigates whether metallurgy-informed feature engineering improves machine learning prediction of mechanical properties in low-carbon steel under small-data conditions. Using 300 samples and five physically meaningful descriptors, XGBoost and Random Forest models showed improved accuracy, especially for elongation, with a 10.3% increase in explained variance for XGBoost. Learning curve analysis indicated modest sample efficiency gains at intermediate training sizes.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の鉄鋼業界はカーボンニュートラルに向けた低炭素鋼の開発が進んでおり、本研究成果は製造プロセスの効率化や品質管理に応用できる可能性がある。ただし、直接的なGX規制対応や開示要件への関連性は薄い。
In the global GX context
Globally, the steel industry is under pressure to decarbonize, and improving prediction of low-carbon steel properties can support more efficient production and reduce waste. However, this paper does not directly address climate disclosure or transition finance, limiting its direct relevance to GX scholarship.
👥 読者別の含意
🔬研究者:Provides a practical example of domain-informed feature engineering for small-sample ML in materials science, relevant for researchers in manufacturing AI.
🏢実務担当者:Steel manufacturers can use these methods to improve quality control and reduce production costs, but no direct GX compliance implications.
📄 Abstract（原文）
Industrial steel property prediction is often constrained by limited labelled data, reducing the effectiveness of conventional machine learning models. This study investigated whether metallurgy-informed feature engineering enhances predictive performance under small-data conditions. A representative set of 300 samples from an industrial low-carbon hot-rolled steel strip dataset (C: 0.02–0.06 wt%; Mn: 0.17–0.38 wt%) was used to derive five physically meaningful descriptors: carbon equivalent (CE), nitrogen-to-aluminum ratio (N/Al), microalloying efficiency index (MEI), thermal processing parameter (TPP), and solid solution strengthening index (SSSI). These descriptors were combined with the original 17 compositional and processing variables to create a 22-feature dataset. Random Forest (RF) and Extreme Gradient Boosting (XGBoost) models were evaluated on an independent 60-sample test set using 5-fold cross-validation. Feature engineering improved the prediction accuracy, with the greatest gain observed for elongation. For XGBoost, the mean percentage error decreased from 3.23% to 3.05%, whereas the test-set R2 increased from 0.4935 to 0.5444, representing a 10.3% improvement in the explained variance. For the yield strength, the Random Forest method increased the R2 from 0.4744 to 0.4861. Permutation importance and partial dependence analyses identified MEI and TPP as the six most influential predictors across all targets, confirming that the engineered descriptors provide complementary metallurgical information. Learning curve analysis showed slightly higher cross-validation R2 values at intermediate training sizes (n = 125–175), indicating modestly improved sample efficiency. These findings establish domain-informed feature engineering as an interpretable and practical strategy for improving machine learning in data-limited steel manufacturing processes.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3390/met16080933first seen 2026-08-23 04:47:20
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。