Factoring and Solving Linear Partial Differential Equations

The problem of factoring a linear partial differential operator is studied. An algorithm is designed which allows one to factor an operator when its symbol is separable, and if in addition the operator has enough right factors then it is completely reducible. Since finding the space of solutions of a completely reducible operator reduces to the same for its right factors, we apply this approach and execute a complete analysis of factoring and solving a second-order operator in two independent variables. Some results on factoring third-order operators are exhibited.AMS Subject Classifications: 35A25, 35C05, 35G05.     

Partial Differential Equations and Bivariate Orthogonal Polynomials

In 1929, S. Bochner identified the families of polynomials which are eigenfunctions of a second-order linear differential operator. What is the appropriate generalization of this result to bivariate polynomials? One approach, due to Krall and Sheffer in 1967 and pursued by others, is to determine which linear partial differential operators have orthogonal polynomial solutions with all the polynomials in the family of the same degree sharing the same eigenvalue. In fact, such an operator only determines a multi-dimensional eigenspace associated with each eigenvalue; it does not determine the individual polynomials, even up to a multiplicative constant. In contrast, our approach is to seek pairs of linear differential operators which have joint eigenfunctions that comprise a family of bivariate orthogonal polynomials. This approach entails the addition of some “normalizing" or “regularity" conditions which allow determination of a unique family of orthogonal polynomials. In this article we formulate and solve such a problem and show with the help of Mathematica that the only solutions are disk polynomials. Applications are given to product formulas and hypergroup measure algebras.     

Image Sequence Analysis via Partial Differential Equations

This article deals with the problem of restoring and motion segmenting noisy image sequences with a static background. Usually, motion segmentation and image restoration are considered separately in image sequence restoration. Moreover, motion segmentation is often noise sensitive. In this article, the motion segmentation and the image restoration parts are performed in a coupled way, allowing the motion segmentation part to positively influence the restoration part and vice-versa. This is the key of our approach that allows to deal simultaneously with the problem of restoration and motion segmentation. To this end, we propose a theoretically justified optimization problem that permits to take into account both requirements. The model is theoretically justified. Existence and unicity are proved in the space of bounded variations. A suitable numerical scheme based on half quadratic minimization is then proposed and its convergence and stability demonstrated. Experimental results obtained on noisy synthetic data and real images will illustrate the capabilities of this original and promising approach.     

图像放大的偏微分方程方法

在分析一些常见的图像放大方法的基础上,根据图像像素值特点及近期偏微分方程在图像处理中的应用,将图像的像素值看作是平面物体的温度;利用偏微分方程理论中的热传导数学模型,提出了基于一种新颖的热传导方程初边值问题的图像放大法;并根据其物理意义,设计相应的差分算法．实验证明,这是一种有效的图像放大方法．     

Root Images of Median Filters

Median filters are frequently used in signal analysis because of their smoothing properties and their insensitivity with respect to outliers in the data. Since median filters are nonlinear filters, the tools of linear theory are not applicable to them. One approach to deal with nonlinear filters consists in investigating their root images (fixed elements or signals transparent to the filter). Whereas for one-dimensional median filters the set of all root signals can be completely characterized, this is not true for higher dimensional filters.In 1989, Döhler stated a result on certain root images for two-dimensional median filters. Although Döhlers results are true for a wide class of median filters, his arguments were not correct and his assertions do not hold universally. In this paper we give a rigorous proof of Döhlers results. Moreover, his approach is generalized to the d-dimensional case.     

Rational Solutions of Riccati-like Partial Differential Equations

When factoring linear partial differential systems with a finite-dimensional solution space or analysing symmetries of nonlinear ODEs, we need to look for rational solutions of certain nonlinear PDEs. The nonlinear PDEs are called Riccati-like because they arise in a similar way as Riccati ODEs. In this paper we describe the structure of rational solutions of a Riccati-like system, and an algorithm for computing them. The algorithm is also applicable to finding all rational solutions of Lie’s system { ∂_xu + u² + a₁u + a₂v + a₃, ∂_yu + uv + b₁u + b₂v + b₃, ∂_xv + uv + c₁u + c₂v + c₃, ∂_yv + v² + d₁u + d₂v + d₃},where a₁, . . . , d₃are rational functions of x and y.     

Using Chebyshev Polynomials to Approximate Partial Differential Equations

This paper suggests a simple method based on a Chebyshev approximation at Chebyshev nodes to approximate partial differential equations (PDEs). It consists in determining the value function by using a set of nodes and basis functions. We provide two examples: pricing a European option and determining the best policy for shutting down a machine. The suggested method is flexible, easy to programme and efficient. It is also applicable in other fields, providing efficient solutions to complex systems of PDEs.     

偏微分方程的算子自定义小波解耦算法研究

利用小波算法求解偏微分方程最困难的问题是随着尺度的升高,系统方程的耦合度越来越高,极大降低了计算效率和精度.针对此问题提出了采用算子自定义小波的多尺度解耦算法,首先建立有限元多分辨空间和小波细化关系,提出偏微分方程的多尺度计算理论方法.在优化方案的基础上,提出算子自定义小波的构造方法及解耦条件.改进方法的突出优点在于根据工程问题的实际需要灵活构造具有期望特性的小波基.提出偏微分方程的多尺度算子自定义小波算法,充分利用算子自定义小波的嵌套逼近和尺度解耦特性,实现问题的高效求解.仿真结果表明,改进的算子自定义小波解耦算法具有计算效率高、精度高等特点.     

基于偏微分方程的隐式曲面光顺方法

提出隐式曲面的光顺问题．针对该问题,给出刻画隐式曲面光顺程度的能量模型,并将能量解释为关于隐函数的泛函．基于变分原理,构造出隐函数关于时间的偏微分方程。通过求解该方程得到隐函数序列,使得光顺能量逐渐变小,从而达到光顺隐式曲面的目的．另外．针对光顺问题提出的其它约束条件,如尽可能保持面积不变,保持原有的形状特征等,对模型进行修正．最后,给出方程的实用解法及实验结果。并作简单讨论．实验结果表明该方法通用、灵活、有效,而且程序易于实现．     

Neural Network Method for Solving Partial Differential Equations

A method is presented to solve partial differential equations (pde's) and its boundary and/or initial conditions by using neural networks. It uses the fact that multiple input, single output, single hidden layer feedforward networks with a linear output layer with no bias are capable of arbitrarily well approximating arbitrary functions and its derivatives, which is proven by a number of authors and well known in literature. Knowledge about the pde and its boundary and/or initial conditions is incorporated into the structures and the training sets of several neural networks. In this way we obtain networks of which some are specifically structured. To find the solution of the pde and its boundary and/or initial conditions we have to train all obtained networks simultaneously. Therefore we use an evolutionary algorithm to train the networks. We demonstrate the working of our method by applying it to two problems.     

Exponential Stability of Nonlinear Time-Varying Differential Equations and Partial Averaging

In this paper we formulate, within the Liapunov framework, a sufficient condition for exponential stability of a differential equation. This condition gives rise to a new averaging result referred to as “partial averaging”: exponential stability of a system , with α sufficiently large, is implied by exponential stability of a time-varying system . Date received: March 28, 2000. Date revised: March 7, 2001.     

偏微分方程的MATLAB数值解法及可视化

偏微分方程的数值解法在数值分析中占有很重要的地位,很多科学技术问题的数值计算包括了偏微分方程的数值解问题。在学习初等函数时,总是先画出它们的图形,因为图形能帮助了解函数的性质。而对于偏微分方程,画出它们的图形并不容易,尤其是没有解析解的偏微分方程,画图就显得更加不容易了。为了从偏微分方程的数学表达式中看出其所表达的图形、函数值与自变量之间的关系,通过MATLAB编程,数值求解了泊松方程,并将其结果可视化,给出了解析解与数值解的误差。     

Genetic Programming Approaches for Solving Elliptic Partial Differential Equations

In this paper, we propose a technique based on genetic programming (GP) for meshfree solution of elliptic partial differential equations. We employ the least-squares collocation principle to define an appropriate objective function, which is optimized using GP. Two approaches are presented for the repair of the symbolic expression for the field variables evolved by the GP algorithm to ensure that the governing equations as well as the boundary conditions are satisfied. In the case of problems defined on geometrically simple domains, we augment the solution evolved by GP with additional terms, such that the boundary conditions are satisfied by construction. To satisfy the boundary conditions for geometrically irregular domains, we combine the GP model with a radial basis function network. We improve the computational efficiency and accuracy of both techniques with gradient boosting, a technique originally developed by the machine learning community. Numerical studies are presented for operator problems on regular and irregular boundaries to illustrate the performance of the proposed algorithms.      

An Estimation Problem for Quasilinear Stochastic Partial Differential Equations

A problem of estimating a functional parameter (x) and functionals () based on observation of a solution u (t, x) of the stochastic partial differential equation is considered. The asymptotic problem setting, as the noise intensity 0, is investigated.     

偏微分方程在图像放大中的应用

本文提出基于偏微分方程的图像放大算法,利用扩散模型来消除放大图像的边缘锯齿化和细节模糊化。实验表明,该方法具有较好的实用性。     

High-Order Numerical Methods for Solving Time Fractional Partial Differential Equations

In this paper we introduce a new numerical method for solving time fractional partial differential equation. The time discretization is based on Diethelm’s method where the Hadamard finite-part integral is approximated by using the piecewise quadratic interpolation polynomials. The space discretization is based on the standard finite element method. The error estimates with the convergence order \(O(\tau ^{3-\alpha } + h^2), 0<\alpha <1\) are proved in detail by using the argument developed recently by Lv and Xu (SIAM J Sci Comput 38:A2699–A2724, 2016), where \(\tau \) and h denote the time and space step sizes, respectively. Numerical examples in both one- and two-dimensional cases are given.     

Removing Noise and Preserving Details with Relaxed Median Filters

In this paper, a median based filter called relaxed median filter is proposed. The filter is obtained by relaxing the order statistic for pixel substitution. Noise attenuation properties as well as edge and line preservation are analyzed statistically. The trade-off between noise elimination and detail preservation is widely analyzed. It is shown that relaxed median filters preserve details better than the standard median filter, and remove noise better than other median type filters.     

Spectral Approximation of Partial Differential Equations in Highly Distorted Domains

In this paper we discuss spectral approximations of the Poisson equation in deformed quadrilateral domains. High order polynomial approximations are used for both the solution and the representation of the geometry. Following an isoparametric approach, the four edges of the computational domain are first parametrized using high order polynomial interpolation. Transfinite interpolation is then used to construct the mapping from the square reference domain to the physical domain. Through a series of numerical examples we show the importance of representing the boundary of the domain in a careful way; the choice of interpolation points along the edges of the physical domain may significantly effect the overall discretization error. One way to ensure good interpolation points along an edge is based on the following criteria: (i)?the points should be on the exact curve; (ii)?the derivative of the exact curve and the interpolant should coincide at the internal points along the edge. Following this approach, we demonstrate that the discretization error for the Poisson problem may decay exponentially fast even when the boundary has low regularity.     

A System for Performance Evaluation of Partial Differential Equations Software

This paper describes a system to systematically compare the performance of various methods (software modules) for the numerical solution of partial differential equations. We discuss the general nature and large size of this performance evaluation problem and the data one obtains. The system meets certain design objectives that ensure a valid experiment: 1) precise definition of a particular measurement; 2) uniformity in defimition of variables entering the experiment; and 3) reproducibility of results. The ease of use of the system makes it possible to make the large sets of measurements necessary to obtain confidence in the results and its portability allows others to check or extend the measurements. The system has four parts: 1) semiautomatic generation of problems for experimental input; 2) the ELLPACK system for actually solving the equation; 3) a data management system to organize and access the experimental data; and 4) data analysis programs to extract graphical and statistical summaries from the data.