IIoT and Digital Twin Technologies to Improve Energy Efficiency and Lower Carbon Footprint
エネルギー効率改善とカーボンフットプリント低減のためのIIoTおよびデジタルツイン技術 (AI 翻訳)
Thirunavukarasu Suryalakshmi, Gurumoorthy Yohanandhan Rajaa Vikhram
🤖 gxceed AI 要約
日本語
本論文は、産業用IIoTとデジタルツイン技術を組み合わせ、機械学習（k-meansクラスタリングと異常検知）を用いて工場のエネルギー効率を向上させる手法を提案。エアリーク検出に応用し、6.22 kWh/日の省エネと1.5トンのGHG削減を実証した。実用的な産業脱炭素化ソリューションとして評価できる。
English
This paper proposes a method combining IIoT and digital twin technologies with machine learning (k-means clustering and anomaly detection) to improve industrial energy efficiency. Applied to air leak detection, it achieves 6.22 kWh/day energy conservation and 1.5 ton GHG reduction. The approach offers a practical solution for industrial decarbonization.
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
日本の製造業では、グリーン成長戦略に基づきDXとGXの融合が推進されており、本論文のIIoT・デジタルツイン活用はその典型例。省エネ法やカーボンニュートラル目標に対応する現場レベルの施策として参考になる。
In the global GX context
This paper aligns with global Industry 4.0 trends and industrial decarbonization goals. It demonstrates how digital technologies can directly reduce operational emissions, relevant for TCFD/ISSB disclosures and energy management systems.
👥 読者別の含意
🔬研究者:Shows empirical application of ML and digital twin for energy efficiency; useful for researchers in industrial AI and sustainability.
🏢実務担当者:Provides a replicable case study for manufacturing teams seeking to integrate IIoT and digital twins for cost savings and emission reduction.
🏛政策担当者:Supports policies promoting smart manufacturing and digitalization for energy efficiency and GHG reduction.
📄 Abstract（原文）
The industrial carbon footprint refers to the total amount of greenhouse gas (GHG) emitted, expressed as carbon dioxide equivalent ( https://www.w3.org/1998/Math/MathML" display="inline"> CO 2 e), for the production of goods and services within a specified industrial sector. Reducing this carbon footprint through energy efficiency involves lowering energy consumption while decreasing GHG discharge related with energy production and use. Most standard energy management systems lack accuracy and scalability and are typically manually fine-tuned to operate optimally. Digital twin (DT) technology is used as a solution for real-time monitoring, building models, and prediction of future behavior, with the goal of improving energy efficiency. This approach supports better decision-making during manufacturing and promotes energy-efficient industrial practices. Carbon emissions are reduced through incorporation of Industrial Internet of Things (IIoT) and DT technologies into standard manufacturing processes. Machine learning algorithms such as data-driven k-means clustering with anomaly detection, are used to analyze data obtained from IIoT systems. DT, developed using the FlexSim software targets a sub-process involving air leak detection and localization in a belt cutter process with eight pneumatic cylinders and two air motors. This approach yields 6.22 kWh/day energy conservation and a 1.5 ton GHG discharge reduction through optimized air usage.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1201/9781003585534-16first seen 2026-07-18 05:55:11
🔔 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。