http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
지류 수질관리에 의한 본류의 수질개선 효과에 관한 연구
박성천(Sung Chun Park),전진(Jin Jun),김해진(Hae Jin Kim) 한국수처리학회 1999 한국수처리학회지 Vol.7 No.2
This study aimed for improving the water quality in the main stream of the Youngsan river, and contributing the recovery of an aquatic ecosystem, and enlarging the utilization of water resources. The extent of water quality improvement was analyzed by investigating the effect of water quality improvement in the main stream according to water management of tributary. Predictions of the water quality were carried out by QUAL2E model in the middle stream of the river extending over 60㎞. 2001year was selected as target year. The extent of water quality improvement was estimated by three ways considering the extent of water management in each tributary and inflow rate of the clean water. The first, it was estimated by applying the extent of water quality management in each tributary of the study basin. The second, it was also estimated by applying inflow rate of the clean water. Finally, it was estimated by applying both of above at the same time. The results showed that the water quality has improved in total research area. But, it showed that the extent has leaved much to be desired in the upper reaches of the river(10∼19㎞). From the result, it was predicted that the water quality had over 3rd grade of water quality in total reach when the BOD concentration was managed below 7.0㎎/ℓ at tributary.
박성천 ( Sung Chun Park ),김동수 ( Dong Soo Kim ),홍성희 ( Sung Hee Hong ) 한국수처리학회 2004 한국수처리학회지 Vol.12 No.4
N/A It is essential that inflow prediction should be preceded and rainfall-runoff process must be made a model for doing the best suitable management of irrigation. But error can happen because of parameter estimation and uncertain assumption in model processing of nonlinear and complex Rainfall-Runoff process with time and space alternation. This study, rainfall-runoff modeling is applied by ANN(Artificial Neural Network) to improve these problems. And we developed real-time prediction theory to efficient management of dam. Learning algorithm to learn ANN modeling is generally applied by back propagation algorithm and then operated of Juam-Dam Basin, And inflow is predicted for 1-3 hours. Forecasting outcome is analysisted by Numerical performance indicators and graphical performance indicators as a result, the forecasting value is better than other algorithm.
강우-유출 예측모형 개발을 위한 자기조직화 이론의 적용
박성천(Park Sung Chun),진영훈(Jin Young Hoon),김용구(Kim Yong Gu) 대한토목학회 2006 대한토목학회논문집 B Vol.26 No.4B
본 연구에서는 강우의 시ㆍ공간적 분포의 불규칙한 변동성을 고려한 강우-유출예측모형을 위해 인공신경망(Artificial Neural Networks: ANNs)의 기법의 일종인 자기조직화(Self Organizing Map: SOM) 이론과 역전파 학습 알고리즘(Back Propagation Algorithm: BPA을 복합적으로 이용하였다. 기존의 인공신경망 연구에서 야기된 저ㆍ갈수기의 유출량에 대한 과대평가, 홍수기의 유출량에 대한 과소평가, 예측값이 연속적으로 선행 유출량을 나타내는 Persistence 현상을 해결하기 위하여 패턴분류 성능을 지닌 SOM 이론을 예측모형의 전처리 과정으로 이용하였다. 먼저, 본 연구에서 제안한 방법은 SOM에 의해 강우-유출 관계를 분류하고, SOM에 의한 분류에 따라 각각의 모형을 구성한다. 개별적으로 구축된 모형은 유출량의 예측을 위해 각각의 양상에 따라 분류된 자료를 이용한다. 결과적으로 본 연구에서 제안한 방법은 과거의 인공신경망의 일반적인 적용에 의한 결과보다 더 나은 예측능력을 보여주었으며, 더불어 유출량의 과소 및 과대추정과 Persistence 현상과 같은 문제점이 나타나지 않았다. The present study compositely applied the self-organizing map (SOM), which is a kind of artificial neural networks (ANNs), and the back propagation algorithm (BPA) for the rainfall-runoff prediction model taking account of the irregular variation of the spatiotemporal distribution of rainfall. To solve the problems from the previous studies on ANNs, such as the overestimation of low flow during the dry season, the underestimation of runoff during the flood season and the persistence phenomenon, in which the predicted values continuously represent the preceding runoffs, we introduced SOM theory for the preprocessing in the prediction model. The theory is known that it has the pattern classification ability. The method proposed in the present research initially includes the classification of the rainfall-runoff relationship using SOM and the construction of the respective models according to the classification by SOM. The individually constructed models used the data corresponding to the respectively classified patterns for the runoff prediction. Consequently, the method proposed in the present study resulted in the better prediction ability of runoff than that of the past research using the usual application of ANNs and, in addition, there were no such problems of the under/over-estimation of runoff and the persistence.
인공신경망 이론을 이용한 홍수유출 예측시스템 개발 : GUI_FFS 개발 및 적용
박성천(Park Sung-Chun),오창열(Oh Chang-Ryol),김동렬(Kim Dong-Ryeol),진영훈(Jin Young-Hoon) 대한토목학회 2006 대한토목학회논문집 B Vol.26 No.2B
본 연구에서는 영산강 유역의 본류를 대표하는 나주지점과 황룡강 유역을 대표하는 선암지점에 대하여 물리적인 매개변수를 이용하지 않는 인공신경망 이론을 이용하여 강우-유출 과정의 비선형 모형을 개발하였다. 본 연구결과 나주지점에서는 ANN_NJ_9 모형이 선암지점에서는 ANN_SA_9 모형이 강우-유출 특성을 가장 잘 반영하였다. 또한, 본 연구에서 개발한 GUI_FFS에 대하여 기 확보된 강우 및 유출량을 적용한 결과 실측치와 예측치 간에 0.98이상의 R²값을 보임으로서 향후 수자원 및 하천계획 수립과 그에 따른 운영 및 관리에 효율성을 더할 수 있을 것이라 판단된다. In the present study, a nonlinear model of rainfall-runoff process using Artficial Neural networks(ANNs) which have no consideration on the physical parameter for the basin was developed at Naju station which is the main stream of Yeongsan-river, and Sunam station which is the main stream of Hwangryong-river. The result from the model of ANN_NJ_9 at the Naju station revealed the best result of the rainfall-runoff process, while the model of ANN_SA_9 for the Sunam station. Also, GUl_FFS developed in the research showed the R² of more than 0.98 between the observed and predicted values using the rainfall and runoff in the respective stations. Therefore, the GUl_FFS might be expected that it can playa role for the high reliability to operate and manage the water resources and the design of river plan more efficiently in the future.