基于神经网络的襟翼舵升力系数预报

Lifting coefficient prediction of flap rudder using BP neural network

将BP神经网络应用于襟翼舵升力系数预报，分析了BP神经网络的非线性逼近能力．针对BP神经网络在训练中存在的学习速度慢、易于陷入局部最小等缺点，采用变学习率的BP算法加以改进．对襟翼舵升力系数进行预报，结果表明：预报值的精度明显高于由近似公式计算所得的值，采用BP神经网络对襟翼舵水动力性能进行预报是可行的，能够满足工程应用的要求．

BP neural network is applied in the lifting coefficient prediction of flap rudder. The non-linear approaching ability of BP neural network is analyzed. The variable learning rate of BP algorithm is adopted to mend the drawbacks that are common for BP neural network in training, for example, low learning rate, easy to get into the local minimum points. The lifting coefficient of flap rudder is predicted, the result shows that, compared with the value calculated by approximate formula, the value predicted by neural network has higher precision. So it is feasible to adopt BP neural network to predict the hydrodynamic performance of flap rudder, and it can also satisfy the need of engineering application.