“Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning
Cyclic voltammetry (CV) is a technique for determining the electrochemical properties of the electrode, and electrolyte in electrochemical systems. However, it is sensitive to various feature, and the correlation between them is not fully explained hitherto. An artificial neural network (ANN) was em...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Chemical Engineering Journal Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666821123001059 |
| _version_ | 1797388657746771968 |
|---|---|
| author | Adisa Jarubenjaluk Pannapha Kullattanapratep Apinporn Pornpipattanasiri Kulpavee Jitapunkul Pawin Iamprasertkun |
| author_facet | Adisa Jarubenjaluk Pannapha Kullattanapratep Apinporn Pornpipattanasiri Kulpavee Jitapunkul Pawin Iamprasertkun |
| author_sort | Adisa Jarubenjaluk |
| collection | DOAJ |
| description | Cyclic voltammetry (CV) is a technique for determining the electrochemical properties of the electrode, and electrolyte in electrochemical systems. However, it is sensitive to various feature, and the correlation between them is not fully explained hitherto. An artificial neural network (ANN) was employed to create a CVs prediction for further explain the electrochemical properties in “water-in-salt” electrolyte e.g., scan rate, electrolyte concentration, and potential window. The electrochemical assistant software based on the developed model are then present (namely “Crypton 1.0″ beta version). The designed network architecture consists of two hidden layers with fixed number of neurons in the latter to reduce the calculation burden for loop training. Five-fold cross validation and single loop training with a variation of hidden neurons in the first hidden layer from 1 to 20 neurons were applied to generalize the prediction. The training was performed in batches corresponding to positive scan, negative scan, and full cycle scan to achieve comprehensive models. The final predictions are the product of averaged models with coefficient of determination (R2) over 0.98 for each scanning characteristic. Interestingly, the prediction for wide potential windows showed superior accuracy comparable with the CV from experimental measurement. In addition, the electrochemical stability window has been investigated, and found to be increased along with the electrolyte concentration explaining the concepts of using “water-in-salt” electrolyte. This work covers the understanding of electrochemistry and the model development via ANN for software development. Therefore, our work could be an alternative approach to reduce the experimental burden in the future development of electrochemical applications. |
| first_indexed | 2024-03-08T22:43:59Z |
| format | Article |
| id | doaj.art-16056defe2654b32a88da95924762871 |
| institution | Directory Open Access Journal |
| issn | 2666-8211 |
| language | English |
| last_indexed | 2024-03-08T22:43:59Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Chemical Engineering Journal Advances |
| spelling | doaj.art-16056defe2654b32a88da959247628712023-12-17T06:42:16ZengElsevierChemical Engineering Journal Advances2666-82112023-11-0116100548“Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learningAdisa Jarubenjaluk0Pannapha Kullattanapratep1Apinporn Pornpipattanasiri2Kulpavee Jitapunkul3Pawin Iamprasertkun4School of Bio-Chemical Engineering and Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Bio-Chemical Engineering and Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Bio-Chemical Engineering and Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandCorresponding authors.; School of Bio-Chemical Engineering and Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandCorresponding authors.; School of Bio-Chemical Engineering and Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandCyclic voltammetry (CV) is a technique for determining the electrochemical properties of the electrode, and electrolyte in electrochemical systems. However, it is sensitive to various feature, and the correlation between them is not fully explained hitherto. An artificial neural network (ANN) was employed to create a CVs prediction for further explain the electrochemical properties in “water-in-salt” electrolyte e.g., scan rate, electrolyte concentration, and potential window. The electrochemical assistant software based on the developed model are then present (namely “Crypton 1.0″ beta version). The designed network architecture consists of two hidden layers with fixed number of neurons in the latter to reduce the calculation burden for loop training. Five-fold cross validation and single loop training with a variation of hidden neurons in the first hidden layer from 1 to 20 neurons were applied to generalize the prediction. The training was performed in batches corresponding to positive scan, negative scan, and full cycle scan to achieve comprehensive models. The final predictions are the product of averaged models with coefficient of determination (R2) over 0.98 for each scanning characteristic. Interestingly, the prediction for wide potential windows showed superior accuracy comparable with the CV from experimental measurement. In addition, the electrochemical stability window has been investigated, and found to be increased along with the electrolyte concentration explaining the concepts of using “water-in-salt” electrolyte. This work covers the understanding of electrochemistry and the model development via ANN for software development. Therefore, our work could be an alternative approach to reduce the experimental burden in the future development of electrochemical applications.http://www.sciencedirect.com/science/article/pii/S2666821123001059CryptonMachine learningEnergy storageArtificial neural networkCyclic voltammetryActivated carbon |
| spellingShingle | Adisa Jarubenjaluk Pannapha Kullattanapratep Apinporn Pornpipattanasiri Kulpavee Jitapunkul Pawin Iamprasertkun “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning Chemical Engineering Journal Advances Crypton Machine learning Energy storage Artificial neural network Cyclic voltammetry Activated carbon |
| title | “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| title_full | “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| title_fullStr | “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| title_full_unstemmed | “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| title_short | “Crypton 1.0”: Accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| title_sort | crypton 1 0 accurate cyclic voltammetry forecasting of activated carbon electrode with machine learning |
| topic | Crypton Machine learning Energy storage Artificial neural network Cyclic voltammetry Activated carbon |
| url | http://www.sciencedirect.com/science/article/pii/S2666821123001059 |
| work_keys_str_mv | AT adisajarubenjaluk crypton10accuratecyclicvoltammetryforecastingofactivatedcarbonelectrodewithmachinelearning AT pannaphakullattanapratep crypton10accuratecyclicvoltammetryforecastingofactivatedcarbonelectrodewithmachinelearning AT apinpornpornpipattanasiri crypton10accuratecyclicvoltammetryforecastingofactivatedcarbonelectrodewithmachinelearning AT kulpaveejitapunkul crypton10accuratecyclicvoltammetryforecastingofactivatedcarbonelectrodewithmachinelearning AT pawiniamprasertkun crypton10accuratecyclicvoltammetryforecastingofactivatedcarbonelectrodewithmachinelearning |