Archives

  • Archives
  • >
  • Home

DOI : ,    Vol.12, No.4, 89 ~ 100, 2004
Title
Apply for a Juam Dam Inflow Forecasting of a Artificial Neural Network Theory
박성천 Sung Chun Park , 김동수 Dong Soo Kim , 홍성희 Sung Hee Hong
Abstract
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.
Key Words
Artificial Neural Network, back propagation algorithm, inflow prediction
pdf view PDF