Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties
Abstract Globally, the provision of energy is becoming an absolute necessity. Biomass resources are abundant and have been described as a potential alternative source of energy. However, it is important to assess the fuel characteristics of the various available biomass sources. Soft computing techn...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-11-01
|
| Series: | Bioresources and Bioprocessing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40643-020-00350-6 |
| _version_ | 1818965939338608640 |
|---|---|
| author | Jibril Abdulsalam Abiodun Ismail Lawal Ramadimetja Lizah Setsepu Moshood Onifade Samson Bada |
| author_facet | Jibril Abdulsalam Abiodun Ismail Lawal Ramadimetja Lizah Setsepu Moshood Onifade Samson Bada |
| author_sort | Jibril Abdulsalam |
| collection | DOAJ |
| description | Abstract Globally, the provision of energy is becoming an absolute necessity. Biomass resources are abundant and have been described as a potential alternative source of energy. However, it is important to assess the fuel characteristics of the various available biomass sources. Soft computing techniques are presented in this study to predict the mass yield (MY), energy yield (EY), and higher heating value (HHV) of hydrothermally carbonized biomass using Gene Expression Programming (GEP), multiple-input single output-artificial neural network (MISO-ANN), and Multilinear regression (MLR). The three techniques were compared using statistical performance metrics. The coefficient of determination (R 2), mean absolute error (MAE) and mean bias error (MBE) were used to evaluate the performance of the models. The MISO-ANN with 5-10 to 10-1 and 5-15-15-1 network architectures provided the most satisfactory performance of the three proposed models (R 2 = 0.976, 0.955, 0.996; MAE = 2.24, 2.11, 0.93; MBE = 0.16, 0.37, 0.12) for MY, EY and HHV, respectively. The GEP technique’s ability to predict hydrochar properties based on the input parameters was found to be satisfactory, while MLR provided an unsatisfactory predictive model. Sensitivity analysis was conducted, and the analysis revealed that volatile matter (VM) and temperature (Temp) have more influence on the MY, EY, and HHV. |
| first_indexed | 2024-12-20T13:24:58Z |
| format | Article |
| id | doaj.art-a00a2cb6e7b8499ca7378f87ea0fac4a |
| institution | Directory Open Access Journal |
| issn | 2197-4365 |
| language | English |
| last_indexed | 2024-12-20T13:24:58Z |
| publishDate | 2020-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Bioresources and Bioprocessing |
| spelling | doaj.art-a00a2cb6e7b8499ca7378f87ea0fac4a2022-12-21T19:39:18ZengSpringerOpenBioresources and Bioprocessing2197-43652020-11-017112210.1186/s40643-020-00350-6Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical propertiesJibril Abdulsalam0Abiodun Ismail Lawal1Ramadimetja Lizah Setsepu2Moshood Onifade3Samson Bada4DSI/NRF Clean Coal Technology Research Group, School of Chemical and Metallurgical Engineering, Faculty of Engineering and the Built Environment, University of the WitwatersrandDepartment of Energy Resources Engineering, Inha University Yong-Hyun DongDSI/NRF Clean Coal Technology Research Group, School of Chemical and Metallurgical Engineering, Faculty of Engineering and the Built Environment, University of the WitwatersrandDepartment of Mining and Metallurgical Engineering, University of NamibiaDSI/NRF Clean Coal Technology Research Group, School of Chemical and Metallurgical Engineering, Faculty of Engineering and the Built Environment, University of the WitwatersrandAbstract Globally, the provision of energy is becoming an absolute necessity. Biomass resources are abundant and have been described as a potential alternative source of energy. However, it is important to assess the fuel characteristics of the various available biomass sources. Soft computing techniques are presented in this study to predict the mass yield (MY), energy yield (EY), and higher heating value (HHV) of hydrothermally carbonized biomass using Gene Expression Programming (GEP), multiple-input single output-artificial neural network (MISO-ANN), and Multilinear regression (MLR). The three techniques were compared using statistical performance metrics. The coefficient of determination (R 2), mean absolute error (MAE) and mean bias error (MBE) were used to evaluate the performance of the models. The MISO-ANN with 5-10 to 10-1 and 5-15-15-1 network architectures provided the most satisfactory performance of the three proposed models (R 2 = 0.976, 0.955, 0.996; MAE = 2.24, 2.11, 0.93; MBE = 0.16, 0.37, 0.12) for MY, EY and HHV, respectively. The GEP technique’s ability to predict hydrochar properties based on the input parameters was found to be satisfactory, while MLR provided an unsatisfactory predictive model. Sensitivity analysis was conducted, and the analysis revealed that volatile matter (VM) and temperature (Temp) have more influence on the MY, EY, and HHV.https://doi.org/10.1186/s40643-020-00350-6Artificial neural networkBiomassGene expression programmingHigher heating valueHydrocharsHydrothermal carbonization |
| spellingShingle | Jibril Abdulsalam Abiodun Ismail Lawal Ramadimetja Lizah Setsepu Moshood Onifade Samson Bada Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties Bioresources and Bioprocessing Artificial neural network Biomass Gene expression programming Higher heating value Hydrochars Hydrothermal carbonization |
| title | Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| title_full | Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| title_fullStr | Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| title_full_unstemmed | Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| title_short | Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| title_sort | application of gene expression programming artificial neural network and multilinear regression in predicting hydrochar physicochemical properties |
| topic | Artificial neural network Biomass Gene expression programming Higher heating value Hydrochars Hydrothermal carbonization |
| url | https://doi.org/10.1186/s40643-020-00350-6 |
| work_keys_str_mv | AT jibrilabdulsalam applicationofgeneexpressionprogrammingartificialneuralnetworkandmultilinearregressioninpredictinghydrocharphysicochemicalproperties AT abiodunismaillawal applicationofgeneexpressionprogrammingartificialneuralnetworkandmultilinearregressioninpredictinghydrocharphysicochemicalproperties AT ramadimetjalizahsetsepu applicationofgeneexpressionprogrammingartificialneuralnetworkandmultilinearregressioninpredictinghydrocharphysicochemicalproperties AT moshoodonifade applicationofgeneexpressionprogrammingartificialneuralnetworkandmultilinearregressioninpredictinghydrocharphysicochemicalproperties AT samsonbada applicationofgeneexpressionprogrammingartificialneuralnetworkandmultilinearregressioninpredictinghydrocharphysicochemicalproperties |