Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model
Due to the complexity of biochemical systems, the development of traditional phenomenological models is limited if the underlying mechanics are not entirely known. As an alternative, hybrid model frameworks, consisting of data-driven models complemented with first principles models like conservation...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Digital Chemical Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772508123000509 |
| _version_ | 1797394774478553088 |
|---|---|
| author | Juan D. Hoyos Mario A. Noriega Carlos A.M. Riascos |
| author_facet | Juan D. Hoyos Mario A. Noriega Carlos A.M. Riascos |
| author_sort | Juan D. Hoyos |
| collection | DOAJ |
| description | Due to the complexity of biochemical systems, the development of traditional phenomenological models is limited if the underlying mechanics are not entirely known. As an alternative, hybrid model frameworks, consisting of data-driven models complemented with first principles models like conservation law, are starting to be used for complex systems. In this work, a comparison of the modeling capabilities between a data-driven model and a hybrid model was developed. The enzymatic production of Galactooligosaccharides (GOS) with the effect of metallic ions was considered as case study. Compared with the experimental results, predictions from data-driven model achieve an R2 of 0.9188 in the best training fold, and the hybrid model an R2 of 0.9696 in the best training fold. Illogical predictions were avoided by including non-phenomenological first-principles constraints into the hybrid model. Finally, an optimization analysis was carried out to find the highest GOS productivity using the hybrid model, optimization results present a deviation of 5.99 % compared to the highest productivity found from experimental data. |
| first_indexed | 2024-03-09T00:24:33Z |
| format | Article |
| id | doaj.art-b46c35a4d40247b8bfeb59bd15d2e991 |
| institution | Directory Open Access Journal |
| issn | 2772-5081 |
| language | English |
| last_indexed | 2024-03-09T00:24:33Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Digital Chemical Engineering |
| spelling | doaj.art-b46c35a4d40247b8bfeb59bd15d2e9912023-12-12T04:37:13ZengElsevierDigital Chemical Engineering2772-50812023-12-019100132Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid modelJuan D. Hoyos0Mario A. Noriega1Carlos A.M. Riascos2Departamento de Ingeniería Química y Ambiental, Facultad de Ingeniería, Universidad Nacional de Colombia – Sede Bogotá, Bogotá 111321, ColombiaCorresponding author.; Departamento de Ingeniería Química y Ambiental, Facultad de Ingeniería, Universidad Nacional de Colombia – Sede Bogotá, Bogotá 111321, ColombiaDepartamento de Ingeniería Química y Ambiental, Facultad de Ingeniería, Universidad Nacional de Colombia – Sede Bogotá, Bogotá 111321, ColombiaDue to the complexity of biochemical systems, the development of traditional phenomenological models is limited if the underlying mechanics are not entirely known. As an alternative, hybrid model frameworks, consisting of data-driven models complemented with first principles models like conservation law, are starting to be used for complex systems. In this work, a comparison of the modeling capabilities between a data-driven model and a hybrid model was developed. The enzymatic production of Galactooligosaccharides (GOS) with the effect of metallic ions was considered as case study. Compared with the experimental results, predictions from data-driven model achieve an R2 of 0.9188 in the best training fold, and the hybrid model an R2 of 0.9696 in the best training fold. Illogical predictions were avoided by including non-phenomenological first-principles constraints into the hybrid model. Finally, an optimization analysis was carried out to find the highest GOS productivity using the hybrid model, optimization results present a deviation of 5.99 % compared to the highest productivity found from experimental data.http://www.sciencedirect.com/science/article/pii/S2772508123000509Hybrid modelingKinetic modelNeural networksGOS |
| spellingShingle | Juan D. Hoyos Mario A. Noriega Carlos A.M. Riascos Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model Digital Chemical Engineering Hybrid modeling Kinetic model Neural networks GOS |
| title | Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model |
| title_full | Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model |
| title_fullStr | Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model |
| title_full_unstemmed | Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model |
| title_short | Modeling and simulation of the enzymatic kinetics for the production of Galactooligosaccharides (GOS) using an Artificial Neural Network hybrid model |
| title_sort | modeling and simulation of the enzymatic kinetics for the production of galactooligosaccharides gos using an artificial neural network hybrid model |
| topic | Hybrid modeling Kinetic model Neural networks GOS |
| url | http://www.sciencedirect.com/science/article/pii/S2772508123000509 |
| work_keys_str_mv | AT juandhoyos modelingandsimulationoftheenzymatickineticsfortheproductionofgalactooligosaccharidesgosusinganartificialneuralnetworkhybridmodel AT marioanoriega modelingandsimulationoftheenzymatickineticsfortheproductionofgalactooligosaccharidesgosusinganartificialneuralnetworkhybridmodel AT carlosamriascos modelingandsimulationoftheenzymatickineticsfortheproductionofgalactooligosaccharidesgosusinganartificialneuralnetworkhybridmodel |