Litcius/Paper detail

BCLH2Pro: A novel computational tools approach for hydrogen production prediction via machine learning in biomass chemical looping processes

Thanadol Tuntiwongwat, Sippawit Thammawiset, Thongchai Srinophakun, Chawalit Ngamcharussrivichai, Somboon Sukpancharoen

2024Energy and AI32 citationsDOIOpen Access PDF

Abstract

• BCLH2Pro: Novel ML tool predicts H 2 yield in biomass chemical looping processes. • CatBoost algorithm achieves over 98% accuracy in H 2 yield predictions. • SHAP analysis reveals key factors: carbon content, reducer temp, Fe 2 O 3 /Al 2 O 3 ratio. • User-friendly web interface optimizes BCLpro operational parameters. This study optimizes biomass chemical looping processes (BCLpro), a technique for converting biomass to energy, through machine learning (ML) for sustainable energy production. The study proposes an integrated Fe 2 O 3 -based ฺBCLpro combining steam gasification for H 2 production. Aspen Plus is used as the primary tool to generate extensive datasets covering 24 biomass types with 18 feature inputs in a supervised model. A methodology involving K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), Support Vector Machine (SVM), Random Forest (RF), and CatBoost (CB) algorithms was employed to predict H 2 yields in the BCLpro, utilizing 10-fold cross-validation for robust model evaluation. Findings highlight the CB algorithm's superior performance, achieving up to 98% predictive accuracy, with carbon content, reducer temperature, and Fe 2 O 3 /Al 2 O 3 mass ratio identified as crucial features. The algorithm has been developed into a user-friendly tool, BCLH2Pro, accessible via a web server. This tool is designed to assist in reducing costs, optimizing biomass selection, and planning operational conditions to maximize H 2 yield in BCLpro systems. Access to the tool can be obtained through the following link: http://bclh2pro.pythonanywhere.com/ .

Topics & Concepts

Computer scienceSupport vector machineMachine learningRandom forestGradient boostingBoosting (machine learning)Biomass (ecology)Feature selectionArtificial intelligenceProcess engineeringData miningEngineeringGeologyOceanographyChemical Looping and Thermochemical ProcessesThermochemical Biomass Conversion ProcessesAtmospheric and Environmental Gas Dynamics
BCLH2Pro: A novel computational tools approach for hydrogen production prediction via machine learning in biomass chemical looping processes | Litcius