Modeling the gasification process in producing raw gases and solids using machine learning techniques in combination with optimization algorithms

被引:0
作者
Xiao, Yuanyuan [1 ]
机构
[1] Shandong Huayu Univ Technol, Sch Informat Engn, Dezhou 253000, Shandong, Peoples R China
关键词
Gasification process; Extra trees regressor; Optimizations algorithm; FLUIDIZED-BED GASIFICATION; BIOMASS GASIFICATION; STEAM GASIFICATION; PILOT-SCALE; SYNGAS PRODUCTION; HYDROGEN-PRODUCTION; AIR GASIFICATION; PERFORMANCE; GASIFIER; QUALITY;
D O I
10.1007/s41939-024-00647-5
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The research deals with the development of artificial intelligence models for the prediction of biomass gasification systems to achieve better efficiency and reliability. Conserve environmental health, different input data for the modeling of gasification output materials are used, such as gases and solids, and reduce reliance on fossil fuel supplies. It adopted the development of hybrid frameworks that coupled an Extra Tree Regressor (ET) model with two optimization algorithms, namely Equilibrium Slime Mold Algorithm (ESMA) and Manta Ray Foraging Optimization (MRFO). The dataset from 312 experiments found in the literature was employed for the simulation of the gasification process. The obtained result manifested that the ETES hybrid model had an excellent fitness accuracy with R2 = 0.99 and RMSE = 0.0694 for gas yield (GY) and R2 = 0.986 and RMSE = 6.943 for char yield (CY) during the training phase, respectively. These results confirm that the hybrid models can remarkably improve the prediction of both syngas and char from gasification processes. The implications of this research are overwhelming, as it would render a reliable tool for operational management in gasification processes, contributing to the production of clean fuel and supporting sustainable development. This might allow, after further refinement, additional research, and experimentation on these models to increase their precision and applicability for a wide range of gasification scenarios.
引用
收藏
页数:22
相关论文
共 50 条
[31]   Data-based modeling of an industrial flotation column using classic and intelligent machine learning algorithms [J].
Zarie, Majid ;
Jahedsaravani, Ali ;
Massinaei, Mohammad .
CANADIAN METALLURGICAL QUARTERLY, 2025,
[32]   Building energy modeling (BEM) using clustering algorithms and semi-supervised machine learning approaches [J].
Naganathan, Hariharan ;
Chong, Wai Oswald ;
Chen, Xuewen .
AUTOMATION IN CONSTRUCTION, 2016, 72 :187-194
[33]   Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques [J].
Escarate, Pedro ;
Farias, Gonzalo ;
Naranjo, Paulina ;
Pablo Zoffoli, Juan .
SENSORS, 2022, 22 (16)
[34]   Predictive modeling for 14-day unplanned hospital readmission risk by using machine learning algorithms [J].
Lo, Yu-Tai ;
Liao, Jay Chie-hen ;
Chen, Mei-Hua ;
Chang, Chia-Ming ;
Li, Cheng-Te .
BMC MEDICAL INFORMATICS AND DECISION MAKING, 2021, 21 (01)
[35]   Evaluation of different machine learning algorithms for LULC classification in heterogeneous landscape by using remote sensing and GIS techniques [J].
Pokhariya, Hemant Singh ;
Singh, D. P. ;
Prakash, Rishi .
ENGINEERING RESEARCH EXPRESS, 2023, 5 (04)
[36]   Influence of optimization techniques on machine learning algorithms: compressive behaviour of additively manufactured poly lactic acid (PLA) for structural applications [J].
Veeman, Dhinakaran ;
Vellaisamy, Murugan ;
Ponnusamy, Pradeep Castro ;
Subramaniyan, Mohan Kumar ;
Vijayakumar, M. D. ;
Guo, Lei .
PROGRESS IN ADDITIVE MANUFACTURING, 2025, 10 (04) :2613-2630
[37]   Qualitative and quantitative assessment of apple quality using bulk optical properties in combination with machine learning and chemometrics techniques [J].
Tian, Kai ;
Zhu, Weijie ;
Wang, Minjie ;
Chen, Ting ;
Li, Fuqi ;
Xie, Jianchao ;
Peng, Yumeng ;
Sun, Tong ;
Zhou, Guoquan ;
Hu, Dong .
LWT-FOOD SCIENCE AND TECHNOLOGY, 2024, 211
[38]   Optimization of a pyrolysis furnace using multi-jet arrays through numerical and machine learning techniques [J].
Wu, Wenchang ;
Zhang, Menghui ;
Wang, Yifei ;
Zhao, Liang ;
Dong, Hui ;
Zhang, Jiyu .
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2023, 214
[39]   Predicting axial compression capacity of CFDST columns and design optimization using advanced machine learning techniques [J].
Nguyen, Thuy-Anh ;
Ly, Hai-Bang .
STRUCTURES, 2024, 59
[40]   Habitat suitability modeling of dominant weed in canola (Brassica napus) fields using machine learning techniques [J].
Dastres, Emran ;
Sarvestani, Ghazal Shafiee ;
Edalat, Mohsen ;
Pourghasemi, Hamid Reza .
WEED SCIENCE, 2025, 73