Many problems in engineering shape design involve eigenvalue optimizations.The relevant difficulty is that the eigenvalues are not continuously differentiable with respect to the density.In this paper,we are interested in the case of multi-density inhomogeneous materials which minimizes the least eigenvalue.With the finite element discretization,we propose a monotonically decreasing algorithm to solve the minimization problem.Some numerical examples are provided to illustrate the efficiency of the present algorithm as well as to demonstrate its availability for the case of more than two densities.As the computations are sensitive to the choice of the discretization mesh sizes,we adopt the refined mesh strategy,whose mesh grids are 25-times of the amount used in[S.Osher and F.Santosa,J.Comput.Phys.,171(2001),pp.272-288].We also show the significant reduction in computational cost with the fast convergence of this algorithm.
A finite difference method is introduced to solve the forward-backward heat equation in two space dimensions. In this procedure, the backward and forward difference scheme in two subdomains and a coarse-mesh second-order central difference scheme at the middle interface are used. Maximum norm error estimate for the procedure is derived. Then an iterative method based on domain decomposition is presented for the numerical scheme and the convergence of the given method is established. Then numerical experiments are presented to support the theoretical analysis.
