orthogonalize

And an error model to orthogonalize axes,rectify sensitivity and eliminate zeroshift,is presented.

然后，建立了与之对应的神经网络结构以实对转向误差模型参数的智能。

Firstly,the paper utilizes kernel principal component analysis method to realize reduce the dimension of the input vectors and orthogonalize the components of the input vectors.

先利用核元分析实变量的降维和去相关,然后运用小波神经网络建立预测模型。