摘要
针对目前对水轮机特性曲线数据处理方法精度不高,不能真实地反映水力机组在过渡过程的流量特性和力矩特性的问题,利用BP神经网络与Matlab相结合,对水轮机综合特性曲线进行建模仿真。由已知综合特性曲线结合边界控制点经神经网络训练获得低效区的流量延拓、力矩延拓和导叶浆叶协联关系仿真曲面。BP神经网络模型大大提高了水轮机综合特性曲线数据处理效率与精度,是研究水轮机控制系统的一种新的非线性建模仿真模型。
Considering the precision of the present data treatment is not high, the real hydraulic flow and torque characteristics in the transient process can not be reflected, the BP neural network and Matlab models are combined and the hydro-turbine synthetic char- acteristic curves are simulated. From the known discrete data and constraint conditions, simulation surface of extent flow, extent torque are obtained and linked characteristics of guide vane and blade in low efficiency region are established. BP neural network model improves the efficiency and accuracy of the hydro-turbine synthetic characteristic curve treatment; it is a new model of nonlinear modeling and simulation model for doing research on the hydro-turbine control system.
出处
《中国农村水利水电》
北大核心
2010年第3期140-142,145,共4页
China Rural Water and Hydropower
关键词
BP神经网络
水轮机特性曲线
曲面延拓
MATLAB
建模仿真
BP neural network
hydro-turbine synthetic characteristic curve
surface extension
Matlab
modeling and simulation
