In this paper, a novel ANN flood forecasting model is proposed. The ANN model is combined with traditional hydrological concepts and methods, taking the initial Antecedent Precipitation Index (api), rainfall, upstream...
详细信息
In this paper, a novel ANN flood forecasting model is proposed. The ANN model is combined with traditional hydrological concepts and methods, taking the initial Antecedent Precipitation Index (api), rainfall, upstream inflow and initial flow at the forecast river section as input of model, and flood flow forecast of the next time steps as output of the model. The distributed rainfall is realized as the input of the model. The simulation is processed by dividing the watershed into several rainfall-runoff processing units. Two hidden layers are used in the ANN, and the topology of ANN is optimized by connecting the hidden layer neurons only with the input which has physical conceptual causes. The topological structure of the proposed ANN model and its information transmission process are more consistent with the physical conception of rainfall-runoff, and the weight parameters of the model are reduced. The arithmetic moving-average algorithm is added to the output of the model to simulate the pondage action of the watershed. Satisfactory results have been achieved in the Mozitan and Xianghongdian reservoirs in the upper reaches of Pi river in Huaihe Basin, and the Fengman reservoir in the upper reach of Second Songhua river in Songhua basin in China.
With the aim of evaluating the effects of the selection of the wind turbulence model on the dynamic response of a semi-submersible floater supporting the DTU 10 MW RWT, we ran aero-hydro-servo-elastic simulations empl...
详细信息
With the aim of evaluating the effects of the selection of the wind turbulence model on the dynamic response of a semi-submersible floater supporting the DTU 10 MW RWT, we ran aero-hydro-servo-elastic simulations employing the OASIS code developed at IHCantabria. For each of the 4 sea states selected, apart from the reference case with only wave loads, we analysed 30 different realizations with coupled wind and wave loads for each of the 7 full-field turbulent winds generated by the turbulence simulator TurbSim: Kaimal and von Karman spectral models with three different turbulence classes each and the api turbulence model. From the resulting platform motions and mooring line dynamics, it can be concluded that the selection of the wind turbulence model is not trivial. At U-0 = 5.83 m/s, the obtained results show a high dependence on the turbulence class. However, as the wind speed increases and the wind turbine achieves the rated speed, the impact of the turbulence intensity is drastically reduced, and the design tension is dominated by the thrust force and thus by the vertical wind speed profile. The highest design tension of the windward mooring lines is obtained with the api model at U-0 = 8.75 m/s (at least 357 Tm).
暂无评论