| 학회 | 한국화학공학회 |
| 학술대회 | 2004년 봄 (04/23 ~ 04/24, 공주대학교) |
| 권호 | 10권 1호, p.184 |
| 발표분야 | 공정시스템 |
| 제목 | Application of artificial neural networks to catalyst synthesis as a data mining technique |
| 초록 | Many researches are going on in the field of high-throughput experimentation (HTE) techniques in the framework of combinatorial catalysis. Some devices that make such HTE possible are already developed. However, the speedy progress of those experimental tools requires more diverse data mining methods. The objective of data mining is to find relationships between the input and output data obtained from experimentation. In this work, we investigate how artificial neural network (ANN) can be applied to combinatorial catalysis as a data mining technique. First, the relationship between catalytic performances and a broad spectrum of the catalyst elemental composition is derived using ANN. The derived model is then used to predict the maximum reactivity of multi-component catalysts, thereby accelerating the discovery of the optimum composition of catalysts. Acknowledgement This work was supported by the BK21 Project, the IMT 2000 (project number: 00015993) in 2003, and Center for Ultramicrochemical Process Systems sponsored by KOSEF. |
| 저자 | 박소희1, 성수환2, 박선원3 |
| 소속 | 1한국과학기술원 생명화학공학과, 2초미세화학공정센터, 3LG CHEM CRD(연) |
| 키워드 | combinatorial catalysis; neural network; data mining |
| 원문파일 | 초록 보기 |
