Study on the influence of carbide slag fly ash composite material on the compressive strength and corrosion resistance of low-carbon UHPC
炭化カルシウムスラグ・フライアッシュ複合材料が低炭素UHPCの圧縮強度と耐食性に及ぼす影響の研究 (AI 翻訳)
Haozhe Pan
🤖 gxceed AI 要約
日本語
本研究は、炭化カルシウムスラグとフライアッシュを複合した低炭素超高強度コンクリート（UHPC）の圧縮強度と耐食性を予測するため、改良型ディープニューラルネットワークを提案する。226のデータセットを用い、主成分分析による重み付けと教師あり対比学習によりモデル性能を向上。その結果、RMSEとMAEが従来比でそれぞれ最大41%および44%改善した。この枠組みは、要求強度に応じた配合設計の最適化を可能にする。
English
This study proposes an improved deep neural network to predict compressive strength and corrosion resistance of low-carbon ultra-high-performance concrete (UHPC) using carbide slag fly ash composites. Using 226 datasets, PCA weighting and supervised contrastive learning improve model performance, achieving up to 41% and 44% reduction in RMSE and MAE. The framework enables data-driven optimization of mix proportions for specific strength requirements.
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
日本では、カーボンニュートラルに向けセメント産業の脱炭素が急務。低炭素UHPCは建設分野のScope 3排出削減に寄与する可能性があり、本手法は材料設計の効率化を通じて間接的にGXに貢献する。
In the global GX context
Globally, the cement industry is under pressure to decarbonize. Low-carbon UHPC reduces embodied carbon in construction. This AI-driven optimization method advances material efficiency, which is relevant to climate disclosure frameworks (e.g., TCFD, ISSB) focusing on Scope 3 emissions from building materials.
👥 読者別の含意
🔬研究者:Demonstrates AI-driven optimization for low-carbon concrete design, offering a methodology for predicting mechanical and durability properties.
🏢実務担当者:Provides a data-driven approach to optimize UHPC mix designs for reduced carbon footprint and improved performance, applicable to precast and ready-mix concrete producers.
🏛政策担当者:Highlights potential of AI in advancing low-carbon construction materials, supporting policies for embodied carbon reduction in building codes.
📄 Abstract（原文）
An improved deep neural network algorithm is proposed to predict the compressive strength and corrosion resistance of low-carbon ultra-high-performance concrete (UHPC) using carbide slag fly ash composite materials, and optimize the mix design. Firstly, 226 sets of sample datasets were collected from UHPC compressive strength and corrosion resistance test data, and preprocessed. Using principal component analysis weighting method to assign weights to input variables, randomly select some data as training and testing sets. Secondly, an improved deep neural network model is constructed by introducing weighted cross entropy loss to reduce class imbalance, and supervised contrastive learning is designed to enhance the model's feature extraction capability. Use Matlab software to train the model and analyze the prediction results. Empirical evaluations demonstrate that the optimized deep neural network architecture exhibits superior predictive performance and enhanced robustness when benchmarked against its predecessor. Specifically, the model achieves a 17.11% and 41.04% reduction in root mean square error (RMSE) values, coupled with corresponding decreases of 28.35% and 44.25% in mean absolute error (MAE) metrics. The proposed computational framework demonstrates exceptional predictive capacity for both mechanical (compressive strength) and durability (corrosion resistance) properties of ultra-high-performance concrete (UHPC) formulated with carbide slag-fly ash composites. This advancement enables data-driven optimization of mixture proportions tailored to specific strength requirements, thereby establishing a theoretical foundation for rational design of advanced cementitious composites.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.65102/is20261098first seen 2026-06-17 05:08:29 · last seen 2026-06-17 07:12:14
🔔 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。