gxceed
← 論文一覧に戻る

A novel BIM-AI-based framework towards data-driven value engineering optimization for circular economy in construction

建設における循環経済のためのデータ駆動型バリューエンジニアリング最適化に向けた新しいBIM-AIベースのフレームワーク (AI 翻訳)

Sachin Venu Jaya, V. Swarnakar, A. Acquaye, M. Khalfan, M. El Fadel

International Journal of Building Pathology and Adaptation📚 査読済 / ジャーナル2026-03-12#AI×ESG経営インパクト: コスト削減対象セクター: construction
DOI: 10.1108/ijbpa-07-2025-0183
原典: https://doi.org/10.1108/ijbpa-07-2025-0183

🤖 gxceed AI 要約

日本語

本研究は、BIMとAIを統合したフレームワークを開発し、建設におけるバリューエンジニアリング(VE)を強化する。材料最適化と資源管理に焦点を当て、循環経済(CE)の実現を目指す。PRISMAに基づく文献レビューとDelft Ladderアプローチを用い、デジタル技術をVEに統合する実践的なフレームワークを提案する。

English

This study develops an integrated BIM-AI framework to enhance value engineering in construction, focusing on material optimization and resource management for circular economy. Using PRISMA-based literature review and Delft Ladder approach, it proposes a practical framework that integrates digital technologies with VE to improve efficiency, reduce embodied carbon, and promote material reuse.

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

日本の建設業界では、SSBJやグリーン成長戦略に基づくカーボンニュートラルへの対応が急務。本フレームワークは、BIMとAIを活用した資材最適化により、建設分野のGX推進に貢献する可能性がある。

In the global GX context

Globally, the framework aligns with ISSB and TCFD disclosures by enabling data-driven decisions for embodied carbon reduction and circularity, offering practical tools for construction firms to meet sustainability targets.

👥 読者別の含意

🔬研究者:Provides a novel integration of BIM, AI, and VE for circular economy, offering a structured approach for further empirical validation.

🏢実務担当者:Offers construction professionals a practical framework to optimize materials, reduce costs, and improve sustainability using digital tools.

🏛政策担当者:Highlights the potential of digitalization in achieving circular economy goals and could inform policies promoting BIM and AI adoption in construction.

📄 Abstract(原文)

The study aims to develop an integrated framework to enhance the value engineering (VE) approach in construction by leveraging building information modeling (BIM) and artificial intelligence (AI). The framework focuses on material optimization and sustainable resource management while ensuring quality and cost-effectiveness to attain the circular economy (CE). A systematic literature review, guided by Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) method, is conducted to examine the applications of VE in construction. A mixed-method approach combines quantitative analysis, including keyword co-occurrence and clustering, with qualitative content analysis. The Delft Ladder approach is employed to structure the integration of VE with BIM and AI technologies, forming the foundation of the novel industrial practice-based framework. The study reveals significant potential for enhancing VE through digital transformation. Integrating BIM and AI with VE principles demonstrates improved efficiency in material optimization and reduction of environmental impacts. The proposed Framework promotes closed-loop systems in construction by enabling data-driven decision-making, improving resource efficiency and allowing stakeholders to adopt CE principles throughout the construction lifecycle. The framework offers construction professionals pragmatic solutions to mitigate embodied carbon, encourage material reuse and fulfill sustainability objectives. It tackles issues in conventional VE implementation by integrating digital technologies with CE procedures for efficient material management. This research introduces an innovative framework that uniquely integrates VE principles with BIM and AI functionalities, employing the reduce, reuse and recycle methodology. The framework can enhance value and minimize expenses through optimization and material efficiency to achieve both functionality and cost-effectiveness.

🔗 Provenance — このレコードを発見したソース

🔔 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。