THE SUPERCONVERGENT PATCH RECOVERY (SPR) AND ADAPTIVE FINITE-ELEMENT REFINEMENT

The error estimation processes which have been developed by the authors depend on the accuracy with which stresses (gradients) can be recovered. The recovery methods available currently, such as the L2 projection and averaging, are inaccurate and an improved process is needed. This paper presents a very much improved recovery process yielding superconvergent values throughout the domain. Details of this method, named the superconvergent patch recovery, are presented with test results showing its efficiency. Examples of adaptive, h-based refinement are given, showing high local and overall efficiency indices for error estimation.