Some Features of the construction of a family of atomic radial basis functions Plop r,a (x1,x2)
Abstract
A lot of methods for solving boundary value problems using arbitrary grids, such as SDI (scattered data interpolation) and SPH (smoothed particle hydrodynamics), use families of atomic radial basis functions that depend on parameters to improve the accuracy of calculations. Functions of this kind are commonly called "shape functions". When polynomials or polynomial splines are used as such functions, they are called "basis functions". The term "radial" means that the carrier of the function is a disk or layer. The term "atomic" means that the support of the function is limited, ie the function is finite. In most cases, the term "finite" is used in English-language publications. The article presents an algorithm for constructing such a function, which is the solution of the functional-differential equation
where - circle of radius r: , and . The function generated by this equation has two parameters: r and . Variation of these parameters allows to reduce the error in the calculations of the Poisson boundary value problem by several times. The theorem on the existence of such an unambiguous function is proved in the article. The proof of the theorem allows us to construct one-dimensional Fourier transform of this function in the form , where . Previously, function was calculated using its Taylor approximation (at ), and at – using the asymptotic Hankel approximation of the function . Thus in a circle of a point a fairly large error was found. Therefore, the calculation of the function in the range was carried out by Chebyshev approximation of this function in the range . Chebyshev coefficients (calculated in the Maple 18 system with an accuracy of 26 decimal digits) and the range were chosen by an experiment aimed at minimizing the overall error in calculating of the function . Thanks to the use of the Chebyshev approximation, the obtained function has more than twice less error than calculated by the previous algorithm. Arbitrary value of the function is calculated using a six-point Aitken scheme, which can be considered (to some extent) a smoothing filter. The use of Aitken's six-point scheme introduces an error equal to 6% of the total function calculation error , but helps to save a lot of time in the formation of ARBF in solving boundary value problems using the method of collocation.
Downloads
References
/References
Edward J. Kanza, PhD. Motivation for using radial basis functions to solve PDEs // Lawrence Livermore National Laboratory and Embry-Riddle Aeronatical University – August 24, 1999. [in English]
G. R. Liu Mesh Free Methods. Moving beyond the Finite Element Method. – London: CRC Press. – 2003. – 693 p. [in English]
V. M. Kolodyazhnyi, V. A. Rvachev, Finite functions generated by the Laplace operator // Reports of the NAS of Ukraine. – № 4. – 2004. – P. 17-22. [in Ukrainian]
А. М. Budylin Fourier series and integrals. – L.: SPbSU. – 2002. – 127 p. [in Russian]
А. А. Karatsuba Fundamentals of Analytical Number Theory.– М.: Nauka, – 1983.–239 p. [in Russian]
L. I. Ronkin Introduction to the theory of entire functions of many variables – М.: Nauka, 1971. – 430 p. [in Russian]
V. I. Smirnov The course of higher mathematics: In 4 volumes. T. 2. – М.: Nauka. – 1974. – 655 p. [in Russian]
V. M. Kolodyazhnyi, V. A. Rvachev Atomic functions: Generalization to the multivariable case and promising applications // Cybernetics and Systems Analysis. – 43, N 6. – 2007. – P. 893-911. [in English]
I. I. Lyashko, V. L. Makarov, A. A. Skorobohatʹko Методы вычислений (Численный анализ. Методы решения задач математической физики) / – К.: Vyshcha shkola, 1977. – 400 p. [in Russian]
M. Abramovitz, I. Stegun Handbook of Mathematical Functions With Formulas, Graphs, and Mathematical Tables: per. from English. / – М.: Nauka, 1979. – 832 p. [in Russian]
B. A. Popov, G. C. Tesler Calculation of functions on a computer. Handbook / – К.: Naukova dumka – 1984. – 600 p. [in Russian]
Kanza E. J., PhD. Motivation for using radial basis functions to solve PDEs // Lawrence Livermore National Laboratory and Embry-Riddle Aeronautical University – August 24, 1999.
Liu G. R. Mesh Free Methods. Moving beyond the Finite Element Method. – London: CRC Press. – 2003. – 693 p.
Колодяжний В. М., Рвачов В. О. Фінітні функції, що породжені оператором Лапласа // Доповіді НАН України. – № 4. – 2004. – С. 17-22.
Будылин А. М. Ряды и интегралы Фурье. – Л.: СПбГУ. – 2002. – 127 с.
Карацуба А. А. Основы аналитической теории чисел.– М.: Наука. – 1983.–239 с.
Ронкин Л. И. Введение в теорию целых функций многих переменных – М.: Наука, 1971. – 430 с.
Смирнов В. И. Курс высшей математики: В 4-х томах. Т. 2. – М.: Наука. – 1974. – 655 с.
Kolodyazhnyi V. M. and Rvachev V. A. Atomic functions: Generalization to the multivariable case and promising applications // Cybernetics and Systems Analysis. – 43, N 6. – 2007. – С. 893-911.
Ляшко И. И., Макаров В. Л., Скоробогатько А. А. Методы вычислений (Численный анализ. Методы решения задач математической физики) / – К.: Вища школа, 1977. – 400 с.
Абрамовитц М., Стиган И. Справочник по специальным функциям с формулами, графиками и математическими таблицами: пер. с англ. / – М.: Наука, 1979. – 832 с.
Попов Б. А., Теслер Г. С. Вычисление функций на ЭВМ. Справочник / – К.: Наукова думка – 1984. – 600 с.
