Using Machine Learning to Predict the Performance of Brazilian Biomasses on Chemical Looping Combustion
機械学習を用いたブラジル産バイオマスの化学ループ燃焼性能予測 (AI 翻訳)
Giovanny S. Oliveira, Antônio M. L. Bezerra, Domingos F. S. Souza, Carlos E. A. Padilha, J. Ruiz
🤖 gxceed AI 要約
日本語
本研究は、化学ループ燃焼（CLC）プロセスにおけるブラジル産バイオマスの性能を、機械学習（人工ニューラルネットワーク）で予測する。バイオマスの特性と燃料反応器温度を入力とし、炭素回収効率や全酸素要求量を高い精度（R²>0.973）で予測。揮発分が重要な因子であり、米殻とユーカリの特性がCLC性能に影響を与えた。実験による検証が今後の課題。
English
This study uses artificial neural networks to predict the performance of Brazilian biomasses in chemical looping combustion (CLC), a CCUS technology. Inputs include biomass characteristics and reactor temperature, accurately predicting carbon capture efficiency and oxygen demand (R²>0.973). Volatile matter was key; rice husks and eucalyptus showed distinct behaviors. Experimental validation is needed.
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
CCUSは日本のGX戦略の重要技術だが、本論文はブラジルのバイオマスに特化。日本の研究者は、同様のML手法を国内のバイオマスや廃棄物CLCに応用できる可能性がある。
In the global GX context
This paper advances CCUS modeling by applying machine learning to predict biomass performance in chemical looping combustion, relevant for global decarbonization, especially in biomass-rich regions. The methodology could be adapted for other feedstocks and reactor conditions.
👥 読者別の含意
🔬研究者:Machine learning approach for predicting CCUS performance from feedstock characteristics offers a methodological template for similar studies.
🏢実務担当者:May inform preliminary screening of biomass candidates for CLC projects, but experimental validation is still required.
📄 Abstract（原文）
Greenhouse gas (GHG) emissions are one of the leading environmental concerns faced nowadays. The chemical looping combustion (CLC) process is one of the main processes that aim for carbon capture, utilization, and storage (CCUS), allowing the generation of a high-purity CO2 stream that can be easily captured. Brazil has a wide variety of biomasses that could be applied to CLC, and the behavior of these biomasses can be predicted using machine learning algorithms. An artificial neural network (ANN) was created considering the biomass characteristics (proximate and ultimate analysis) and fuel reactor temperature as input data to assess their influence on CLC performance parameters (carbon capture efficiency, ηCC, and total oxygen demand, ΩT) and gas compositions. The characteristics of five Brazilian biomasses were considered in the constructed ANN to predict their behavior on CLC performance. The ANN presented a good data fit, with R2 achieving values higher than 0.973. Volatile matter played a crucial role in predicting the CLC performance parameters. Rice husks presented the smoothest results for ηCC and ΩT, while the CO2 composition was most affected by the eucalyptus characteristics. Experimental tests with all the biomasses should be carried out to provide a higher prediction capability of the algorithm.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/fire9040149first seen 2026-05-05 23:58:44
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。