通过与线性插值、多项式拟合法和神经网络逼近法的比较，可以明显看出用该神经网络算法的优越性。

Compared with linear inserting value and multinomial imitation method, it is obvious that NN has more advantages.

youdao

提出了线性插值法代替惯用的泽尼克多项式拟合用于表面的精磨。

Local interpolation model is used to replace Zernick polynomials for surface contour error fitting at the grinding stage.

youdao

汽蚀曲线绘制方法有传统的有手工绘法、多项式拟合法、非线性拟合法、三次样条插值法等。

Cavitation curve drawing method of the traditional hand-drawn method, polynomial fitting, non-linear fitting, cubic spline interpolation method.

youdao