Mesh model feature surface extraction method and system based on error sorting

The invention provides a grid model feature surface extraction method and system based on error sorting, and the method comprises the steps: 1, carrying out the curved surface fitting of a seed surface of a machining simulation triangular grid model, and obtaining a fitting curved surface; 2, extending the fitting curved surface to a transition surface between the seed surfaces according to a growth algorithm of a single seed surface to obtain an overlapping region; and step 3, extracting a feature surface according to a priority order of each grid surface of the overlapping region belonging to different seed surfaces. Compared with the prior art, the method has the advantages that on the basis of the machining simulation triangular mesh model, a multi-seed-surface alternate growth algorithm is provided for extracting the feature surface, feature surface extraction of the machining simulation triangular mesh model is achieved, and a good foundation is laid for reconstructing a solid model from the mesh model.