The theoretical basis of ANN is function approximation, it USES a two - level feedforward neural network to approach arbitrary function to realize better power flow control.
径向基函数神经网络的理论基础是函数逼近，用一个两层的前向网络去逼近任意函数，以更好地进行潮流控制。
This is normal, and the arbitrary function all can approach with dividing section multinomials because can know from infinitesimal calculus.
这是正常的，因为从微积分可以知道，任一函数都可以用分段多项式来逼近。
应用推荐