Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes
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, limi...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Clean Technologies |
Subjects: | |
Online Access: | https://www.mdpi.com/2571-8797/4/4/75 |
_version_ | 1797460833125531648 |
---|---|
author | Inioluwa Christianah Afolabi Emmanuel I. Epelle Burcu Gunes Fatih Güleç Jude A. Okolie |
author_facet | Inioluwa Christianah Afolabi Emmanuel I. Epelle Burcu Gunes Fatih Güleç Jude A. Okolie |
author_sort | Inioluwa Christianah Afolabi |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-09T17:11:48Z |
format | Article |
id | doaj.art-cd2a1e98c9de4c78b70be06b1d556e96 |
institution | Directory Open Access Journal |
issn | 2571-8797 |
language | English |
last_indexed | 2024-03-09T17:11:48Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Clean Technologies |
spelling | doaj.art-cd2a1e98c9de4c78b70be06b1d556e962023-11-24T14:04:42ZengMDPI AGClean Technologies2571-87972022-11-01441227124110.3390/cleantechnol4040075Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass ClassesInioluwa Christianah Afolabi0Emmanuel I. Epelle1Burcu Gunes2Fatih Güleç3Jude A. Okolie4Department of Pure and Applied Chemistry, Ladoke Akintola University of Technology, Ogbomoso P.M.B. 4000, NigeriaSchool of Computing, Engineering & Physical Sciences, University of the West of Scotland, Paisley PA1 2BE, UKSchool of Biotechnology and DCU Water Institute, Dublin City University, Glasnevin, D09 NA55 Dublin, IrelandAdvanced Materials Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG7 2RD, UKSt. Peter’s College Muenster, Box 40, Muenster, SK S0K 2Y0, CanadaHigher 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.https://www.mdpi.com/2571-8797/4/4/75machine learningbiomasshigher heating valuebiofuelartificial neural network |
spellingShingle | Inioluwa Christianah Afolabi Emmanuel I. Epelle Burcu Gunes Fatih Güleç Jude A. Okolie Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes Clean Technologies machine learning biomass higher heating value biofuel artificial neural network |
title | Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes |
title_full | Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes |
title_fullStr | Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes |
title_full_unstemmed | Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes |
title_short | Data-Driven Machine Learning Approach for Predicting the Higher Heating Value of Different Biomass Classes |
title_sort | data driven machine learning approach for predicting the higher heating value of different biomass classes |
topic | machine learning biomass higher heating value biofuel artificial neural network |
url | https://www.mdpi.com/2571-8797/4/4/75 |
work_keys_str_mv | AT inioluwachristianahafolabi datadrivenmachinelearningapproachforpredictingthehigherheatingvalueofdifferentbiomassclasses AT emmanueliepelle datadrivenmachinelearningapproachforpredictingthehigherheatingvalueofdifferentbiomassclasses AT burcugunes datadrivenmachinelearningapproachforpredictingthehigherheatingvalueofdifferentbiomassclasses AT fatihgulec datadrivenmachinelearningapproachforpredictingthehigherheatingvalueofdifferentbiomassclasses AT judeaokolie datadrivenmachinelearningapproachforpredictingthehigherheatingvalueofdifferentbiomassclasses |