Thermodynamics Guided Machine Learning Models for CO₂ desublimation temperature prediction
熱力学に基づく機械学習モデルによるCO₂脱昇華温度予測 (AI 翻訳)
Ganti Srikanth, 𝑏 𝑎, G. Sudheer, 𝑐∗
🤖 gxceed AI 要約
日本語
CO₂脱昇華温度（CDDT）は極低温炭素回収や天然ガス処理に重要。本研究はPeng-Robinson状態方程式による熱力学モデル、4種の機械学習手法、物理情報ハイブリッドML（PI-HML）を統合した3層アプローチを提案。PI-HMLは平衡条件やクラウジウス-クラペイロン則を学習に組み込み、高精度な予測を実現。
English
This paper presents a three-tier study for predicting CO₂ desublimation temperature (CDDT) critical for cryogenic carbon capture and gas processing. It compares a thermodynamic model (Peng-Robinson EoS), standalone ML methods (DT, GPM, ANFIS, GP), and a physics-informed hybrid ML (PI-HML) that embeds fugacity equilibrium and Clausius–Clapeyron constraints. PI-HML achieves superior accuracy and physical consistency.
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
日本はGX実現に向けCCUS技術の開発を推進しており、極低温分離法の効率化に資する本モデルは、国内の炭素回収プロジェクトや天然ガスプラントでの実装可能性を示唆する。
In the global GX context
As global CCUS deployment accelerates, accurate prediction of CO₂ solidification is vital for designing cryogenic capture systems and pipeline safety. This physics-informed ML framework offers a reproducible toolkit that can be integrated into broader carbon management infrastructures and aligned with TCFD/ISSB disclosure of capture efficiencies.
👥 読者別の含意
🔬研究者:Novel combination of thermodynamic constraints with ML for phase-change prediction, advancing physics-informed modeling approaches.
🏢実務担当者:Engineers in cryogenic carbon capture or gas processing can directly apply the PI-HML model for system design and operational optimization.
🏛政策担当者:Supports technical feasibility assessments for carbon capture projects, relevant for GX policy targets.
📄 Abstract（原文）
Accurate prediction of the carbon dioxide desublimation temperature (CDDT)—the threshold below which CO₂ transitions directly from vapor to solid phase—is critical for cryogenic carbon-capture systems, natural-gas processing, and pipeline safety. This paper presents a unified, three-tier study covering: a classical thermodynamic model based on the Peng–Robinson equation of state (PR EoS) solved via Lagrange’s analytically stable cubic solver; machine learning (ML) approaches including Decision Tree (DT), Gaussian Process Method (GPM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Genetic Programming (GP) applied to a consolidated dataset of 430 experimental measurements; and a physics-informed hybrid machine learning (PI-HML) framework that embeds fugacity equilibrium, Clausius–Clapeyron consistency, and monotonicity constraints directly into the learning objective. Together, these frameworks provide a complete, validated toolkit for managing CO₂ solidification in industrial cryogenic operations.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.52783/tjjpt.v47.i01.10439first seen 2026-05-06 00:00:34
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。