Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network
In this study, response surface methodology (RSM) and artificial neural network (ANN) were used to optimize Terminalia catappa L. kernel oil (TCKO) yield. Solvent extraction method was used for the oil extraction, with n-hexane as the extracting solvent. The highest oil yield was obtained at 55 °C,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2020-01-01
|
| Series: | Artificial Intelligence in Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721720300064 |
| _version_ | 1818333101592412160 |
|---|---|
| author | Chinedu Matthew Agu Matthew Chukwudi Menkiti Ekwe Bassey Ekwe Albert Chibuzor Agulanna |
| author_facet | Chinedu Matthew Agu Matthew Chukwudi Menkiti Ekwe Bassey Ekwe Albert Chibuzor Agulanna |
| author_sort | Chinedu Matthew Agu |
| collection | DOAJ |
| description | In this study, response surface methodology (RSM) and artificial neural network (ANN) were used to optimize Terminalia catappa L. kernel oil (TCKO) yield. Solvent extraction method was used for the oil extraction, with n-hexane as the extracting solvent. The highest oil yield was obtained at 55 °C, 150 min, and 0.5 mm. The physicochemical properties of the TCKO were determined using standard methods. Gas chromatographic (GC) analysis and Fourier Transform Infrared (FTIR) were respectively, used to determine the fatty acid composition and prevalent functional groups in TCKO. At optimum conditions of temperature, particle size and extraction time, the RSM predicted oil yield was 62.92%, which was validated as 60.34%, whereas ANN predicted yield was 60.39%, which was validated as 60.40%. The results of the physicochemical characterization of TCKO showed that the dielectric strength (DS), viscosity, flash and pour points values were 30.61 KV, 20.29 mm2 s−1, 260 °C, and 3 °C, respectively. Physicochemical characterization and FTIR results of TCKO indicated its potential industrial application, especially as transformer fluid. Fatty acids compositions result indicated that the oil was highly unsaturated; while XRD results of Terminalia catappa L. kernel (TCK) samples obtained, both before and after extraction, showed difference in their peaks and corresponding intensities, due to the damage effect of solvent. Finally, the obtained optimization results indicated that ANN was a better and more effective tool than RSM, due to its higher R2 and lower RMS values. |
| first_indexed | 2024-12-13T13:46:17Z |
| format | Article |
| id | doaj.art-de0304b0c2c84688b7f0525780ab160f |
| institution | Directory Open Access Journal |
| issn | 2589-7217 |
| language | English |
| last_indexed | 2024-12-13T13:46:17Z |
| publishDate | 2020-01-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Agriculture |
| spelling | doaj.art-de0304b0c2c84688b7f0525780ab160f2022-12-21T23:43:25ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172020-01-014111Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural networkChinedu Matthew Agu0Matthew Chukwudi Menkiti1Ekwe Bassey Ekwe2Albert Chibuzor Agulanna3Chemical Engineering Department, Nnamdi Azikiwe University, Awka, Nigeria; Corresponding author.Chemical Engineering Department, Nnamdi Azikiwe University, Awka, NigeriaMechanical Engineering Department, Gregory University, Uturu, NigeriaMaterials and Energy Technology Department, Projects Development Institute (PRODA), Emene Industrial Area, Enugu, NigeriaIn this study, response surface methodology (RSM) and artificial neural network (ANN) were used to optimize Terminalia catappa L. kernel oil (TCKO) yield. Solvent extraction method was used for the oil extraction, with n-hexane as the extracting solvent. The highest oil yield was obtained at 55 °C, 150 min, and 0.5 mm. The physicochemical properties of the TCKO were determined using standard methods. Gas chromatographic (GC) analysis and Fourier Transform Infrared (FTIR) were respectively, used to determine the fatty acid composition and prevalent functional groups in TCKO. At optimum conditions of temperature, particle size and extraction time, the RSM predicted oil yield was 62.92%, which was validated as 60.34%, whereas ANN predicted yield was 60.39%, which was validated as 60.40%. The results of the physicochemical characterization of TCKO showed that the dielectric strength (DS), viscosity, flash and pour points values were 30.61 KV, 20.29 mm2 s−1, 260 °C, and 3 °C, respectively. Physicochemical characterization and FTIR results of TCKO indicated its potential industrial application, especially as transformer fluid. Fatty acids compositions result indicated that the oil was highly unsaturated; while XRD results of Terminalia catappa L. kernel (TCK) samples obtained, both before and after extraction, showed difference in their peaks and corresponding intensities, due to the damage effect of solvent. Finally, the obtained optimization results indicated that ANN was a better and more effective tool than RSM, due to its higher R2 and lower RMS values.http://www.sciencedirect.com/science/article/pii/S2589721720300064Response surface methodologyArtificial neural networkOptimizationTerminalia catappa L. kernel |
| spellingShingle | Chinedu Matthew Agu Matthew Chukwudi Menkiti Ekwe Bassey Ekwe Albert Chibuzor Agulanna Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network Artificial Intelligence in Agriculture Response surface methodology Artificial neural network Optimization Terminalia catappa L. kernel |
| title | Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network |
| title_full | Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network |
| title_fullStr | Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network |
| title_full_unstemmed | Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network |
| title_short | Modeling and optimization of Terminalia catappa L. kernel oil extraction using response surface methodology and artificial neural network |
| title_sort | modeling and optimization of terminalia catappa l kernel oil extraction using response surface methodology and artificial neural network |
| topic | Response surface methodology Artificial neural network Optimization Terminalia catappa L. kernel |
| url | http://www.sciencedirect.com/science/article/pii/S2589721720300064 |
| work_keys_str_mv | AT chinedumatthewagu modelingandoptimizationofterminaliacatappalkerneloilextractionusingresponsesurfacemethodologyandartificialneuralnetwork AT matthewchukwudimenkiti modelingandoptimizationofterminaliacatappalkerneloilextractionusingresponsesurfacemethodologyandartificialneuralnetwork AT ekwebasseyekwe modelingandoptimizationofterminaliacatappalkerneloilextractionusingresponsesurfacemethodologyandartificialneuralnetwork AT albertchibuzoragulanna modelingandoptimizationofterminaliacatappalkerneloilextractionusingresponsesurfacemethodologyandartificialneuralnetwork |