随着四元数的广泛应用,大型四元数结构矩阵方程的求解成为科学计算的重要课题。针对四元数亚正定系统AX=B,在新自共轭正定和斜自共轭分裂迭代(new positive definite and skew-self-conjugate splitting,NPSS)基础上,通过引入双参数和...随着四元数的广泛应用,大型四元数结构矩阵方程的求解成为科学计算的重要课题。针对四元数亚正定系统AX=B,在新自共轭正定和斜自共轭分裂迭代(new positive definite and skew-self-conjugate splitting,NPSS)基础上,通过引入双参数和松弛加速技术,构建出两种新的混参分裂迭代格式,即非对称新自共轭正定和斜自共轭分裂迭代(asymmetric new positive definite and skew-self-conjugate splitting,ANPSS),以及超松弛非对称新自共轭正定和斜自共轭分裂迭代(successive over relaxation asymmetric new positive definite and skew-self-conjugate splitting,SANPSS),同时运用四元数矩阵特征值理论,证明了这两种迭代的收敛性,并给出相关参数的取值范围。采用四元数矩阵的复表示方法,在MATLAB环境下实现该系统的数值求解。数值算例表明,多参数的灵活选取,显示出所提混参分裂迭代相比NPSS迭代具有更高的收敛效率。展开更多
文摘随着四元数的广泛应用,大型四元数结构矩阵方程的求解成为科学计算的重要课题。针对四元数亚正定系统AX=B,在新自共轭正定和斜自共轭分裂迭代(new positive definite and skew-self-conjugate splitting,NPSS)基础上,通过引入双参数和松弛加速技术,构建出两种新的混参分裂迭代格式,即非对称新自共轭正定和斜自共轭分裂迭代(asymmetric new positive definite and skew-self-conjugate splitting,ANPSS),以及超松弛非对称新自共轭正定和斜自共轭分裂迭代(successive over relaxation asymmetric new positive definite and skew-self-conjugate splitting,SANPSS),同时运用四元数矩阵特征值理论,证明了这两种迭代的收敛性,并给出相关参数的取值范围。采用四元数矩阵的复表示方法,在MATLAB环境下实现该系统的数值求解。数值算例表明,多参数的灵活选取,显示出所提混参分裂迭代相比NPSS迭代具有更高的收敛效率。
基金Supported by the NSF of China (11071184)the NSF of Shanxi Province (20120110156)the Science and Technology Development Project of Higher Education in Shanxi (20101112)