Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes

被引:10
|
作者
Afolabi, Inioluwa Christianah [1 ]
Epelle, Emmanuel, I [2 ]
Gunes, Burcu [3 ,4 ]
Gulec, Fatih [5 ]
Okolie, Jude A. [6 ,7 ]
机构
[1] Ladoke Akintola Univ Technol, Dept Pure & Appl Chem, PMB 4000, Ogbomosho, Nigeria
[2] Univ West Scotland, Sch Comp Engn & Phys Sci, Paisley PA1 2BE, Renfrew, Scotland
[3] Dublin City Univ, Sch Biotechnol, Dublin D09 NA55, Ireland
[4] Dublin City Univ, DCU Water Inst, Dublin D09 NA55, Ireland
[5] Univ Nottingham, Adv Mat Res Grp, Fac Engn, Nottingham NG7 2RD, England
[6] St Peters Coll Muenster, Box 40, Muenster, SK SOK 2Y0, Canada
[7] Univ Oklahoma, Gallogly Coll Engn, Norman, OK 73019 USA
来源
CLEAN TECHNOLOGIES | 2022年 / 4卷 / 04期
关键词
machine learning; biomass; higher heating value; biofuel; artificial neural network; PROXIMATE ANALYSIS; GASIFICATION; ULTIMATE; FUELS; HHV;
D O I
10.3390/cleantechnol4040075
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Higher heating values (HHV) is a very useful parameter for assessing the design and large-scale operation of biomass-driven energy systems. HHV is conventionally measured experimentally with an adiabatic oxygen bomb calorimeter. This procedure is often time-consuming and expensive. Furthermore, limited access to the required facilities is the main bottleneck for researchers. Empirical linear and nonlinear models have initially been proposed to address these concerns. However, most of the models showed discrepancies with experimental results. Data-driven machine learning (ML) methods have also been adopted for HHV predictions due to their suitability for nonlinear problems. However, most ML correlations are based on proximate or ultimate analysis. In addition, the models are only applicable to either the originator biomass or one specific type. To address these shortcomings, a total of 227 biomass datasets based on four classes of biomass, including agricultural residue, industrial waste, energy crop, and woody biomass, were employed to develop and verify three different ML models, namely artificial neural network (ANN), decision tree (DT) and random forest (RF). The model incorporates proximate and ultimate analysis data and biomass as input features. RF model is identified as the most reliable because of its lowest mean absolute error (MAE) of 1.01 and mean squared error (MSE) of 1.87. The study findings can be used to predict HHV accurately without performing experiments.
引用
收藏
页码:1227 / 1241
页数:15
相关论文
共 50 条
  • [31] Applying feature selection and machine learning techniques to estimate the biomass higher heating value
    Abdollahi, Seyyed Amirreza
    Ranjbar, Seyyed Faramarz
    Jahromi, Dorsa Razeghi
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [32] Applying feature selection and machine learning techniques to estimate the biomass higher heating value
    Seyyed Amirreza Abdollahi
    Seyyed Faramarz Ranjbar
    Dorsa Razeghi Jahromi
    Scientific Reports, 13
  • [33] Approach to data-driven learning
    Markov, Z.
    International Workshop on Fundamentals of Artificial Intelligence Research, 1991,
  • [34] AN APPROACH TO DATA-DRIVEN LEARNING
    MARKOV, Z
    LECTURE NOTES IN ARTIFICIAL INTELLIGENCE, 1991, 535 : 127 - 140
  • [35] Predicting the solubility of hydrogen in hydrocarbon fractions: Advanced data-driven machine learning approach and equation of state
    Amar, Menad Nait
    Alqahtani, Fahd Mohamad
    Djema, Hakim
    Ourabah, Khaled
    Ghasemi, Mohammad
    JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS, 2023, 153
  • [36] Application of linear regression algorithm and stochastic gradient descent in a machine-learning environment for predicting biomass higher heating value
    Ighalo, Joshua O.
    Adeniyi, Adewale George
    Marques, Goncalo
    BIOFUELS BIOPRODUCTS & BIOREFINING-BIOFPR, 2020, 14 (06): : 1286 - 1295
  • [37] Interpretable machine-learning model with a collaborative game approach to predict yields and higher heating value of torrefied biomass
    Onsree, Thossaporn
    Tippayawong, Nakorn
    Phithakkitnukoon, Santi
    Lauterbach, Jochen
    ENERGY, 2022, 249
  • [38] Estimation of data-driven streamflow predicting models using machine learning methods
    Siddiqi T.A.
    Ashraf S.
    Khan S.A.
    Iqbal M.J.
    Arabian Journal of Geosciences, 2021, 14 (11)
  • [39] Predicting the state of charge and health of batteries using data-driven machine learning
    Man-Fai Ng
    Jin Zhao
    Qingyu Yan
    Gareth J. Conduit
    Zhi Wei Seh
    Nature Machine Intelligence, 2020, 2 : 161 - 170
  • [40] Predicting the state of charge and health of batteries using data-driven machine learning
    Ng, Man-Fai
    Zhao, Jin
    Yan, Qingyu
    Conduit, Gareth J.
    Seh, Zhi Wei
    NATURE MACHINE INTELLIGENCE, 2020, 2 (03) : 161 - 170