Geometric feature recognition for reverse engineering using neural networks

Abstract

Reverse engineering (RE) is a process to create computer aided design (CAD) models from the scanned data of a existing part acquired using 3D position scanners. This paper proposes a novel methodology for extracting geometric features directly from a set of 3D scanned points. It uses the concepts of feature-based technology and artificial neural networks (ANNs). The use of ANNs has enabled the development of a flexible feature-based RE application that can be trained to deal with various features. The following four main tasks were investigated and implemented: 1. Point data reduction module. 2. Edge detection module. 3. ANN-based feature recogniser. 4. Feature extraction modules. The approach was validated with a variety of real industrial components. The test results show that the developed feature-based RE application proved to be suitable for reconstructing prismatic features such as blocks, pockets, steps, slots, holes, and bosses, which are very common in mechanical engineering products. An example is presented to validate this approach.