Tool Wear Monitoring Based On The Processed Surface Texture Image

Tool wear monitoring based on the processed surface texture image is the method that synthesized visual and texture analysis technique to monitor tool wear condition. The visual characteristic of processed surface texture image under different tool wear conditions was investigated for achieving the goal of tool wear condition monitoring.The forming process of surface texture, the morphology and image characteristics of processed surface texture were analyzed, the factors that influencing processed surface texture were compared, the rationality of tool wear monitoring method based on processed surface texture was explained.On the basis of practical processed surface image, the methods of gray level transformation, image enhancement, image segmentation, mathematical morphology operations and region labeling for binary image were studied, and the corresponding algorithm was completed. The four statistics such as second order moment, contrast, correlation, entropy which were used as tool wear features were extracted from gray-level co-occurrence matrix, and analyzed the state of processed surface texture. Accumulation area based on pixel space projection method, connected region integer based on image segmentation, binary image area, and accumulation area based on the sum of image data column was presented as tool wear features.On the basis of practical processed surface image, processed surface texture image was studied, it was analyzed by gray-level co-occurrence matrix method, pixel space projection method, connected region labeling method, area statistics method based on binary image, the method of column sum of image data. The results indicated that with tool wear increasing, second order moment, accumulation area connected region integer based on open operation and edge detection increased. Correlation and entropy, binary image area obtained based on corrosion operation, open operation and Sobel operation, the accumulation area obtained byimage column sum decreased, so these image features could be used as evaluation standards for tool wear, it provided effective way for tool wear monitoring.