Image processing algorithm for detection, quantification and classification of microdefects in wire electric discharge machined precision finish cut surfaces

This study aims to create an image processing algorithm that categorises the wire electric discharge machine (WEDM) processed finish cut surfaces, based on surface microdefects. The algorithm also detects the defect locations and suggests alternate parameter settings for improving the surface integrity. The proposed automated analysis is more precise, efficient and repeatable compared to manual inspection. Also, the method can be used for automatic data generation to suggest parameter changes in closed loop systems. During the training phase, mean, standard deviation and defect area fraction of enhanced binary images are extracted and stored. The training dataset consists of 27 WEDM finish cut surface images with labels, ‘coarse’, ‘average’ and ‘smooth’. The trained model is capable of categorising any machined surface by detecting the microdefects. If the machined surface image is not classified as a smooth image, then alternate input parameter settings will be suggested by the model to minimise the microdefects. This is done based on the Euclidean distance between the current image datapoint and the nearest ‘smooth’ class datapoint.

A New Method for the Generation of Tool Paths for Finishing Near Net Shape Components

The CNC machining has been one of the most recurrent processes used for finishing NNS components. This paper presents a new method for the generation of tool paths for machining 3D NNS models. The proposed approach comprises two machining stages: rough cut and finish cut, and three types of cutting tools: ball-end mill, flat-end mill and fillet-end mill. The proposed tool path generation algorithm is based on: (1) approximation of the model surfaces by points using slice planes and visibility analysis, (2) accessibility analysis of the tool, (3) approximation error and tolerance evaluation, (4) collision analysis of tool and tool holder. The tools paths generated are exported as a CNC program. The implementation was carried out in C++ using the ACIS® geometric modeling kernel to support the required geometric operations. To prove the effectiveness of the system several models with variable geometric complexity were tested. The results have shown that the proposed system is effective and therefore can be used to generate the tool paths required for finishing 3D NNS components.