| 학회 |
한국공업화학회 |
| 학술대회 |
2020년 가을 (10/28 ~ 10/30, 광주 김대중컨벤션센터(Kimdaejung Convention Center)) |
| 권호 |
24권 1호 |
| 발표분야 |
포스터-전기화학 |
| 제목 |
The prediction and optimization for the capacitance of CAU-10-H/rGO supercapacitor by deep learning. |
| 초록 |
The supercapacitor has a high-capacity property that is able to store plenty of energy per unit volume and the capacitance is based on various values. This study aimed to investigate the effect of these variables on the capacitance and to predict the optimal value of the variables to predict a high figure of capacitance. Collected data by the experiments is applied to deep learning algorithm based on DNN (Deep Neural Network) to identify the interaction and the optimal value for volumetric capacitance between three variables, pore size, thickness, and charge rates. All data is pre-processed to prevent problems such as overfitting and time complexity, and improve the reliability of data prediction to predict results with higher accuracy. The accuracy prediction model based on DNN method for the design of supercapacitor with various factors can provide for the design of electrochemical charge storage devices in the future. |
| 저자 |
김성천1, 박제성2
|
| 소속 |
1The Univ. of Melbourne / 한국생산기술(연), 2한국생산기술(연) |
| 키워드 |
Deep learning; Supercapacitor; Metal-organic frameworks; Reduced graphene oxide
|
| E-Mail |
|
