Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge
Sewage sludge hydrochars (SSHs), which are produced by hydrothermal carbonization (HTC), offer a high calorific value to be applied as a biofuel. However, HTC is a complex processand the properties of the resulting product depend heavily on the process conditions and feedstock composition. In this w...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/11/3000 |
| _version_ | 1797533075874250752 |
|---|---|
| author | Theodoros N. Kapetanakis Ioannis O. Vardiambasis Christos D. Nikolopoulos Antonios I. Konstantaras Trinh Kieu Trang Duy Anh Khuong Toshiki Tsubota Ramazan Keyikoglu Alireza Khataee Dimitrios Kalderis |
| author_facet | Theodoros N. Kapetanakis Ioannis O. Vardiambasis Christos D. Nikolopoulos Antonios I. Konstantaras Trinh Kieu Trang Duy Anh Khuong Toshiki Tsubota Ramazan Keyikoglu Alireza Khataee Dimitrios Kalderis |
| author_sort | Theodoros N. Kapetanakis |
| collection | DOAJ |
| description | Sewage sludge hydrochars (SSHs), which are produced by hydrothermal carbonization (HTC), offer a high calorific value to be applied as a biofuel. However, HTC is a complex processand the properties of the resulting product depend heavily on the process conditions and feedstock composition. In this work, we have applied artificial neural networks (ANNs) to contribute to the production of tailored SSHs for a specific application and with optimum properties. We collected data from the published literature covering the years 2014–2021, which was then fed into different ANN models where the input data (HTC temperature, process time, and the elemental content of hydrochars) were used to predict output parameters (higher heating value, (HHV) and solid yield (%)). The proposed ANN models were successful in accurately predicting both HHV and contents of C and H. While the model NN<sub>1</sub> (based on C, H, O content) exhibited HHV predicting performance with R<sup>2</sup> = 0.974, another model, NN<sub>2</sub>, was also able to predict HHV with R<sup>2</sup> = 0.936 using only C and H as input. Moreover, the inverse model of NN<sub>3</sub> (based on H, O content, and HHV) could predict C content with an R<sup>2</sup> of 0.939. |
| first_indexed | 2024-03-10T11:09:25Z |
| format | Article |
| id | doaj.art-857d8d6fcea640488f8210716f08aebc |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T11:09:25Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-857d8d6fcea640488f8210716f08aebc2023-11-21T20:52:26ZengMDPI AGEnergies1996-10732021-05-011411300010.3390/en14113000Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage SludgeTheodoros N. Kapetanakis0Ioannis O. Vardiambasis1Christos D. Nikolopoulos2Antonios I. Konstantaras3Trinh Kieu Trang4Duy Anh Khuong5Toshiki Tsubota6Ramazan Keyikoglu7Alireza Khataee8Dimitrios Kalderis9Department of Electronic Engineering, Hellenic Mediterranean University, Chania, 73100 Crete, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, Chania, 73100 Crete, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, Chania, 73100 Crete, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, Chania, 73100 Crete, GreeceApplied Chemistry Course, Department of Engineering, Kyushu Institute of Technology, Graduate School of Engineering, 1-1 Sensuicho, Tobata-ku, Kitakyushu 804-8550, JapanApplied Chemistry Course, Department of Engineering, Kyushu Institute of Technology, Graduate School of Engineering, 1-1 Sensuicho, Tobata-ku, Kitakyushu 804-8550, JapanDepartment of Applied Chemistry, Faculty of Engineering, Kyushu Institute of Technology, 1-1 Sensuicho, Tobata-ku, Kitakyushu 804-8550, JapanDepartment of Environmental Engineering, Gebze Technical University, 41400 Gebze, TurkeyDepartment of Environmental Engineering, Gebze Technical University, 41400 Gebze, TurkeyDepartment of Electronic Engineering, Hellenic Mediterranean University, Chania, 73100 Crete, GreeceSewage sludge hydrochars (SSHs), which are produced by hydrothermal carbonization (HTC), offer a high calorific value to be applied as a biofuel. However, HTC is a complex processand the properties of the resulting product depend heavily on the process conditions and feedstock composition. In this work, we have applied artificial neural networks (ANNs) to contribute to the production of tailored SSHs for a specific application and with optimum properties. We collected data from the published literature covering the years 2014–2021, which was then fed into different ANN models where the input data (HTC temperature, process time, and the elemental content of hydrochars) were used to predict output parameters (higher heating value, (HHV) and solid yield (%)). The proposed ANN models were successful in accurately predicting both HHV and contents of C and H. While the model NN<sub>1</sub> (based on C, H, O content) exhibited HHV predicting performance with R<sup>2</sup> = 0.974, another model, NN<sub>2</sub>, was also able to predict HHV with R<sup>2</sup> = 0.936 using only C and H as input. Moreover, the inverse model of NN<sub>3</sub> (based on H, O content, and HHV) could predict C content with an R<sup>2</sup> of 0.939.https://www.mdpi.com/1996-1073/14/11/3000sewage sludgehydrothermal carbonizationhydrocharartificial neural networksmachine learningwaste management |
| spellingShingle | Theodoros N. Kapetanakis Ioannis O. Vardiambasis Christos D. Nikolopoulos Antonios I. Konstantaras Trinh Kieu Trang Duy Anh Khuong Toshiki Tsubota Ramazan Keyikoglu Alireza Khataee Dimitrios Kalderis Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge Energies sewage sludge hydrothermal carbonization hydrochar artificial neural networks machine learning waste management |
| title | Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge |
| title_full | Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge |
| title_fullStr | Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge |
| title_full_unstemmed | Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge |
| title_short | Towards Engineered Hydrochars: Application of Artificial Neural Networks in the Hydrothermal Carbonization of Sewage Sludge |
| title_sort | towards engineered hydrochars application of artificial neural networks in the hydrothermal carbonization of sewage sludge |
| topic | sewage sludge hydrothermal carbonization hydrochar artificial neural networks machine learning waste management |
| url | https://www.mdpi.com/1996-1073/14/11/3000 |
| work_keys_str_mv | AT theodorosnkapetanakis towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT ioannisovardiambasis towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT christosdnikolopoulos towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT antoniosikonstantaras towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT trinhkieutrang towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT duyanhkhuong towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT toshikitsubota towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT ramazankeyikoglu towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT alirezakhataee towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge AT dimitrioskalderis towardsengineeredhydrocharsapplicationofartificialneuralnetworksinthehydrothermalcarbonizationofsewagesludge |