Digital twin-enabled multi-agent control for energy-efficient wood drying in desiccant-assisted heat pump systems
デジタルツイン対応マルチエージェント制御による乾燥剤補助ヒートポンプシステムでのエネルギー効率的な木材乾燥 (AI 翻訳)
Kshitij Bhatta, Muhammad Waseem, Mingzhe Liu, Z. Yang, Zheng O’Neill, Qing Chang
🤖 gxceed AI 要約
日本語
本論文は、乾燥剤補助ヒートポンプ（DAHP）システムにおける木材乾燥のためのデジタルツイン・フレームワークを提案。高忠実度物理モデルとマルチエージェント強化学習（MARL）を組み合わせ、従来のボイラーベースと比較して総エネルギー消費を43.2%削減、乾燥期間を約8日短縮、炭素強度を最大94%低減する。MARLから抽出したヒューリスティックポリシーも同等の性能を示し、実用性を高めている。
English
This paper proposes a digital twin framework for wood drying in desiccant-assisted heat pump (DAHP) systems. Combining high-fidelity physics models with multi-agent reinforcement learning (MARL), it reduces total energy consumption by 43.2%, shortens drying time by about eight days, and cuts carbon intensity by up to 94% compared to a conventional boiler baseline. A heuristic policy distilled from MARL achieves comparable performance, enhancing deployability.
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、特に木材産業における省エネルギー化と脱炭素化に直接貢献する可能性がある。デジタルツインとAI制御の組み合わせは、日本の「スマートものづくり」政策やGX実現に向けた技術革新として注目される。
In the global GX context
This study demonstrates a concrete pathway to industrial decarbonization through digital twin and AI-driven control, aligning with global energy efficiency targets and smart manufacturing initiatives. The significant energy and carbon reductions offer a scalable model for hard-to-abate industrial sectors.
👥 読者別の含意
🔬研究者:Provides a novel integration of digital twin and MARL for complex industrial drying processes, offering a foundation for further research in learning-based control for energy-intensive manufacturing.
🏢実務担当者:The distilled heuristic policy offers an immediately actionable control strategy for wood drying facilities seeking substantial energy and carbon reductions.
📄 Abstract（原文）
Abstract This article presents a digital twin-enabled framework for modeling and control of wood drying in a Desiccant-Assisted Heat Pump (DAHP) system. The digital twin integrates high-fidelity physics-based models of the heat pump, kiln chamber, and wood moisture–stress behavior, capturing coupled heat and mass transfer processes critical to drying performance. Leveraging the digital twin as the environment, the drying process is cast as a Decentralized Markov Decision Process (Dec-MDP) and addressed through Multi-Agent Reinforcement Learning (MARL). The proposed approach reduces total site energy consumption by 43.2%, shortens drying duration by approximately eight days, and decreases carbon intensity by up to 94% relative to a conventional boiler-based baseline. To enhance interpretability and support industrial deployment, a heuristic policy distilled from the MARL control achieves comparable performance. By coupling digital twin modeling with advanced learning-based control, this study establishes a deployable pathway toward sustainable, energy-efficient, and high-quality wood drying, with broader implications for next-generation smart manufacturing and energy systems.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.1080/07373937.2026.2631672first seen 2026-05-06 00:10:02
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。