| Summary: | 碩士 === 國立中興大學 === 土木工程學系所 === 102 === Accuracy of the velocity measurements is related to the accuracy of discharge estimation, the practicality of the project design and planning, and the amount of losses caused by disasters. Because of many uncertainty conditions in Taiwan''s rivers, the velocity measuring technique still requires further improvement. In particular, due to the frequent flood disasters caused by the climate change, and the corresponding extreme rainfalls, the river velocity measurement becomes a challenge task. To avoid the exposure to the dangerous environment for the measuring persons, a large number of measured data is used for simulating the average velocity profile and finding the best model for the design and planning.
This study aims to compare the accuracy of the radial basis function artificial neural network (RBFN) and back propagation artificial neural network (BPN) for simulating the average velocity profiles. Both Yang (1998) and Lin’s (1999) experimental data were adopted for the artificial neural network training, validation and testing. The correlation coefficient (C.C) and the root mean square error (RMSE) were used to determine the effectiveness of the simulation and estimation.
|
|---|
