Modified Chebyshev Picard Iteration for Efficient Numerical Integration of Ordinary Differential Equations

摘要

Modified Chebyshev Picard Iteration (MCPI) is an iterative numerical method for approximating solutions of linear or non-linear Ordinary Differential Equations (ODEs) to obtain time histories of system state trajectories. Unlike other step-by-step differential equation solvers, like the Runge-Kutta family of numerical integrators, MCPI approximates long arcs of the state trajectory with an iterative path approximation approach, and is ideally suited to parallel computation. Orthogonal Chebyshev Polynomials are used as basis functions during each path iteration, and the integrations of the Picard iteration are then done analytically. The orthogonality of the Chebyshev basis functions mean that the least square approximations can be computed without a matrix inversion; the coefficients are conveniently computed robustly from discrete inner products. As a consequence of discrete sampling and weighting adopted for the inner product definition, the Runge phenomena errors that usually occur near the ends of the approximation intervals are significantly minimized. The MCPI algorithm utilizes a vector-matrix framework for computational efficiency. Additionally, all Chebyshev coefficients and integrand. function evaluations are independent, meaning they can be simultaneously computed in parallel for further' decreased computational cost. Over an order of magnitude speedup from traditional methods is achieved in serial processing, and an additional order of magnitude is achievable in parallel architectures. This paper presents a new MCPI library, a modular toolset designed to allow MCPI to be easily applied to a wide variety of ODE systems. Library users will not have to concern themselves with the underlying mathematics behind the MCPI method. Inputs are the boundary conditions of the dynamical system, the integrand function governing system behavior, and the desired time interval of integration,and the output is a time history of the system states over the interval of interest. Examples from the field of astrodynamics are presented to compare the output from the MCPI library to current state-of-practice numerical integration methods. It is shown that MCPI is capable of out-performing the state-of-practice in terms of computational cost and accuracy.