Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling
In this study, modeling and optimization of Hydrothermal Carbonization (HTC) of Poultry litter were conducted to convert it into high-value materials. The aim was to understand the process and predict the effect of the influencing parameters on the product properties. The recovery of Inorganic Phosp...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024170302 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850249331618086912 |
|---|---|
| author | Abolfazl Shokri Mohammad Amin Larki Ahad Ghaemi |
| author_facet | Abolfazl Shokri Mohammad Amin Larki Ahad Ghaemi |
| author_sort | Abolfazl Shokri |
| collection | DOAJ |
| description | In this study, modeling and optimization of Hydrothermal Carbonization (HTC) of Poultry litter were conducted to convert it into high-value materials. The aim was to understand the process and predict the effect of the influencing parameters on the product properties. The recovery of Inorganic Phosphorous (IP) and Carbon (C) was regarded as the model's response, although temperature and reaction time were thought to be important variables. Response Surface Methodology (RSM) was used along with temperature and time data sets ranging from 150 to 300C and 30–480 min, respectively, to identify the parameters influencing the response, three-dimensional networks, and optimization. Next, Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were used to compare the results and improve the model fit. For these two neural networks, 7 neurons in two layers and 14 neurons in one layer were the ideal numbers. With fewer neurons and better accuracy and efficiency, the MLP model beat RBF with lower Mean Squared Error (MSE) values for both C (0.0015812 vs. 0.0037103) and IP (0.0014376 vs. 0.00623011) recovery and a higher R2 value (R2C recovery = 0.99742, R2IP recovery = 0.99816). These results demonstrate that MLP is a viable technique for maximizing resource recovery through HTC condition optimization, with potential uses in nutrient recycling and sustainable waste management. By examining the three-dimensional grids and obtained contours, it was found that temperature had a greater effect on the response, and the impact of time was more pronounced at lower temperatures. With increasing temperature and reaction time, C recovery decreased, while IP recovery increased. Furthermore, the optimal values for temperature and time were suggested to be 182.329 C and 427.746 min, respectively. The optimal product values under these conditions for C and IP recovery were obtained as 59.611 % and 29.114 mg/g, respectively. |
| format | Article |
| id | doaj-art-9d1b4a664dac4c199fdce3ac9757f30e |
| institution | OA Journals |
| issn | 2405-8440 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-9d1b4a664dac4c199fdce3ac9757f30e2025-08-20T01:58:31ZengElsevierHeliyon2405-84402024-12-011024e4099910.1016/j.heliyon.2024.e40999Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modelingAbolfazl Shokri0Mohammad Amin Larki1Ahad Ghaemi2School of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran, IranSchool of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran, IranCorresponding author.; School of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran, IranIn this study, modeling and optimization of Hydrothermal Carbonization (HTC) of Poultry litter were conducted to convert it into high-value materials. The aim was to understand the process and predict the effect of the influencing parameters on the product properties. The recovery of Inorganic Phosphorous (IP) and Carbon (C) was regarded as the model's response, although temperature and reaction time were thought to be important variables. Response Surface Methodology (RSM) was used along with temperature and time data sets ranging from 150 to 300C and 30–480 min, respectively, to identify the parameters influencing the response, three-dimensional networks, and optimization. Next, Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were used to compare the results and improve the model fit. For these two neural networks, 7 neurons in two layers and 14 neurons in one layer were the ideal numbers. With fewer neurons and better accuracy and efficiency, the MLP model beat RBF with lower Mean Squared Error (MSE) values for both C (0.0015812 vs. 0.0037103) and IP (0.0014376 vs. 0.00623011) recovery and a higher R2 value (R2C recovery = 0.99742, R2IP recovery = 0.99816). These results demonstrate that MLP is a viable technique for maximizing resource recovery through HTC condition optimization, with potential uses in nutrient recycling and sustainable waste management. By examining the three-dimensional grids and obtained contours, it was found that temperature had a greater effect on the response, and the impact of time was more pronounced at lower temperatures. With increasing temperature and reaction time, C recovery decreased, while IP recovery increased. Furthermore, the optimal values for temperature and time were suggested to be 182.329 C and 427.746 min, respectively. The optimal product values under these conditions for C and IP recovery were obtained as 59.611 % and 29.114 mg/g, respectively.http://www.sciencedirect.com/science/article/pii/S2405844024170302Hydrothermal carbonization (HTC)Poultry litter (PL)Hydrochar (HC)Artificial neural networks (ANN)Optimization |
| spellingShingle | Abolfazl Shokri Mohammad Amin Larki Ahad Ghaemi Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling Heliyon Hydrothermal carbonization (HTC) Poultry litter (PL) Hydrochar (HC) Artificial neural networks (ANN) Optimization |
| title | Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling |
| title_full | Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling |
| title_fullStr | Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling |
| title_full_unstemmed | Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling |
| title_short | Retrieval of carbon and inorganic phosphorus during hydrothermal carbonization: ANN and RSM modeling |
| title_sort | retrieval of carbon and inorganic phosphorus during hydrothermal carbonization ann and rsm modeling |
| topic | Hydrothermal carbonization (HTC) Poultry litter (PL) Hydrochar (HC) Artificial neural networks (ANN) Optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024170302 |
| work_keys_str_mv | AT abolfazlshokri retrievalofcarbonandinorganicphosphorusduringhydrothermalcarbonizationannandrsmmodeling AT mohammadaminlarki retrievalofcarbonandinorganicphosphorusduringhydrothermalcarbonizationannandrsmmodeling AT ahadghaemi retrievalofcarbonandinorganicphosphorusduringhydrothermalcarbonizationannandrsmmodeling |