低炭素・資源効率的生産のための高豊度希土類永久磁石のデータ駆動設計
Data-driven design of high-abundance rare earth permanent magnets for low-carbon and resource-efficient production (原題)
Yuxuan Wu, Qianqian Wang, Qihan Zhang, Shen Zhao, Qiangfeng Li, Dehai Wu, Fang Wu, Hongdong Yu, Lu Wang
🤖 gxceed AI 要約
日本語
再生可能エネルギーやEVに不可欠な希土類磁石の持続可能な設計を目指し、346件の実験データと機械学習（MLP）を用いて磁気特性を高精度に予測。SHAP解析でNdの影響を確認し、多目的最適化によりコストと上流GWPを両立するCeリッチ組成を選定した。
English
This study develops a data-driven framework for sustainable design of rare-earth permanent magnets, using 346 experimental samples and MLP models to predict magnetic properties with high accuracy. SHAP analysis identifies Nd as key, and multi-objective optimization selects a Ce-rich composition balancing performance, cost, and upstream GWP.
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EV・再生可能エネルギー産業にとって磁石の資源安定供給は重要であり、本手法は材料開発の効率化と脱炭素評価を統合する点で、製造業のGX戦略に示唆を与える。
In the global GX context
This work contributes to global efforts on critical materials and low-carbon supply chains, offering a template for integrating ML-based design with environmental impact assessment, relevant to ISSB-aligned disclosure of resource efficiency.
👥 読者別の含意
🔬研究者:Interpretable ML combined with multi-objective optimization offers a robust method for sustainable materials design.
🏢実務担当者:Provides a data-driven approach to reduce material cost and carbon footprint in magnet production, aiding sustainability reporting.
🏛政策担当者:Highlights the importance of resource-efficient materials for clean energy transitions, informing critical mineral policies.
📄 Abstract（原文）
Rare-earth permanent magnets are essential for renewable energy and electric vehicle technologies, but their dependence on critical rare-earth elements raises concerns regarding resource security, cost, and environmental impact. Here, we develop an integrated data-driven framework for the sustainable design of high-abundance rare-earth permanent magnets. A dataset containing 346 experimental samples was constructed to establish composition–property relationships for Br, Hcj, and (BH)max. Eight machine learning (ML) algorithms were compared, and the multi-layer perceptron (MLP) model exhibited the most balanced overall performance after model refinement. The optimized MLP achieved testing R2 values of 0.979, 0.901, and 0.955 for Br, Hcj, and (BH)max, respectively, and repeated five-fold cross-validation supported its robustness. SHapley Additive exPlanations analysis indicated that Nd exerted the strongest statistical influence on the predicted magnetic properties, while Ce and La also contributed through nonlinear composition-property associations. The optimized MLP model was subsequently integrated with non-dominated sorting genetic algorithm II and Technique for Order Preference by Similarity to Ideal Solution to balance predicted (BH)max, material cost, and a composition-related upstream global warming potential (GWP) indicator. The selected Ce-rich candidate achieved a predicted (BH)max of 35.16 MGOe, an estimated material cost of 4.78 $/kg, and a GWP indicator of 16.41 kg CO2-eq/kg. These results demonstrate the potential of interpretable ML combined with multi-objective optimization for screening resource-efficient permanent-magnet compositions.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.20517/jmi.2026.31first seen 2026-08-29 04:40:22
🔔 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。