插值样条δ-序列求解非线性对流扩散方程

提出了一种用广义函数δ序列求解偏微分方程的数值方法.首先对一阶B样条函数N1(x)进行卷积得到四阶B样条函数N4(x),用N4(x)的线性组合构造出三次样条插值基函数;然后用样条插值基序列逼近δ函数,利用δ函数的性质构造插值样条δ序列,该δ序列具有对称、Riesz基和插值性质.以非线性对流扩散方程(伯格方程)为例,用插值样条δ序列离散该方程的空间形式,用四阶龙格库塔方法描述发展过程,取得了较好的精度.为减少计算量,加快插值函数的收敛速度,进一步提高求解精度,对δ序列进行了改进,对同一算例进行数值实验,结果表明,改进后的算法求解过程稳定发展,能够有效描述局部快速变化的情况.

A Partial Approximation Shepard Method Based on Cardinal Spline About Messy Data

With regards to Shepard method, in the paper, we present a better one based on partial approximation to fit messy data. In the method, partial cubic cardinal spline function is chosen as weight function (?)(x) in the Shepard formula which is (?)(x)∈C2 and has good attenuation characteristics. So the traditional Shepard method is improved and the better results can be achieved in practical applications.