Advanced Modelling of Full Characteristic Curve of Tubular Turbine Based on Back-Propagation Neural Network

For the comprehensive characteristics of hydro-turbine, it is generally grasped through full characteristic curve map hydro-turbine obtained from experiment. However, due to factors such as time cost, fund experimental difficulty and safety, results cannot hold onto each working condition hydro-turbine. And for specific conditions unknown conditions, linear interpolation needs be carried out existing results, which will have a certain hidden danger safe stable operation turbine. This paper uses advantages neural network predict overall space back-propagation under points. The show that method can effectively ensure accuracy guide more clearly, efficient