Research On Cutting Tool Wear Condition Monitoring Based On Workpiece Surface Image

The cutting tool condition monitoring technology is very important to the automated production. Taking the turning as the research object in this paper, the tool wear condition monitoring experiment system was established based on the workpiece surface image. The principle of tool wear monitoring was analyzed based on the workpiece surface image. The characteristic extraction of workpiece surface image and recognition method of tool wear condition were theoretically analyzed and experimentally researched.The usual preprocessing method of image was researched, analyzed and collated based on workpiece surface image in this paper. The preprocessing method adapted to workpiece surface image was discovered. The foundation for realizing the image characteristic extraction about the tool wear condition monitoring was laid.The texture analysis method of the workpiece surface image was adopted. The characteristic of workpiece surface image was extracted and analyzed. The variation regularity of characteristic parameter with tool wear was obtained. The experimental result indicated that the change regularity of accumulation area S , inertia I at d =1,θ=90o, the tourist itinerary superiority measures RF 1, the short tourist itinerary superiority measure RF 2 and the tourist itinerary total percentage measure RF 5 atθ=0o, 45o, 90o and 135o were discovered with increasing of the cutting tool wear. The above characteristic parameters used to judge the cutting tool wear condition is effective.The fractal Brownian movement model was introduced to workpiece surface image analysis. The arithmetic of fractal dimension D was researched. Fractal dimension D was regarded as characteristic parameter used to judge cutting tool wear condition. The relationsbetween fractal dimension D and the cutting tool wear was analyzed. The experiment results indicate this method is suitable for the cutting tool wear condition monitoring.BP neural network model used to recognize the tool wear condition was established. The network was trained through the massive experimental data, the mapping from characteristic parameter of workpiece surface image to the cutting tool wear condition was realized. The result shows that this net could be used to recognize and judge cutting tool wear condition effectively.