Intelligent tool wear identification based on optical scattering image and hybrid artificial intelligence techniques

Tool wear monitoring is crucial for an automated machining system to maintain consistent quality of machined parts and prevent damage to the parts during the machining operation. A vision-based approach is presented for tool wear identification in finish turning using an adaptive resonance theory (ART2) neural network embedded with fuzzy classifiers. The proposed approach is established upon the fact that the optical scattering image of a turned surface is related to the wear of the cutting tool. By applying the technique of the ART2 neural network embedded with fuzzy classifiers, the state of wear of the turning tool is determined from captured images obtained by laser scattering from the machined surfaces of the workpiece. This approach is not unlike the visual inspection of the surface of a machined workpiece to determine the state of wear of a cutting tool by an expert machinist. However, experimental results indicate that the conventional technique of measuring surface finish does not give values that correlate well with tool wear. On the other hand, the laser scattering image provides a good indication of the tool wear as it is not readily affected by buildup edge or cold-welded material, scratches and other disruptive defects on the turned surface as the tool wears. In this paper, the theory on the laser scattering image and the principle of tool wear identification are described. Based on the scattering images, the proposed approach can correctly identify the condition of ‘significant wear’ prior to the rapid tool wear stage for the cutting tool.