| 학회 |
한국화학공학회 |
| 학술대회 |
2008년 봄 (04/23 ~ 04/25, 제주ICC) |
| 권호 |
14권 1호, p.172 |
| 발표분야 |
공정시스템 |
| 제목 |
Data Analysis and Ecological Mapping in An Industrial Plant |
| 초록 |
Biological processes have different behavior patterns depending on the influent loads, temperature, the activity of microorganisms and so on. It has been known that a combination of several models can provide a suitable approach in such case. In the present study, a framework of generative topographic mapping (GTM) was developed for elucidating and diagnosing multiple process status of an industrial plant. This process diagnosis maps the data set to the visualized latent space and predicts the advanced nitrogen and phosphorous removal performances through high-dimensional mapping. The results from an industrial plant demonstrate that a high-dimensional nonlinear mapping extracts the operation stability of a biological wastewater treatment process from data set, can identify subtypes of microbiological status and improve the interpretability of the nutrient removal performances. It shows to explain how it can be used to support decision-making in ecosystem and is very efficient to execute corrective actions well in ecosystem for optimizing enhanced biological nutrient removal before a dangerous situation occurs. |
| 저자 |
유창규1, B. Ushayanan2, 김현주3, 김영황4, 이인범4
|
| 소속 |
1경희대, 2Anna Univ., 3India, 4포항공과대 |
| 키워드 |
Advanced nutrient removal; High-dimensional mapping; Generative topographic mapping(GTM); Industrial ecosystem; Process status
|
| E-Mail |
|
| 원문파일 |
초록 보기 |
