A CNC machine tool breakage detection system and method based on deep learning

Abstract

The invention belongs to the field of tool breakage intelligent detection and specifically discloses a deep-learning-based CNC machine tool cutting tool breakage detection system and method. The method comprises the steps of shooting a video of a cutting tool cutting a workpiece in the cutting process through an image data acquisition module; extracting an image in the video through an image datapretreatment module; conducting locating, cutting and normalization processing on the extracted image; receiving the processed image through an edge computing module integrating a broken tool discriminator; conducting forward reasoning through a pre-trained convolutional neural network to obtain a broken tool discrimination result; and implementing control over a machine tool according to the broken tool discrimination result through a machine tool alarm module. Through the deep-learning-based CNC machine tool cutting tool breakage detection system and method, the state of the cutting tool canbe automatically and accurately monitored in real time in the CNC material tool machining process. The deep-learning-based CNC machine tool cutting tool breakage detection method has the advantages of being high in automation degree, easy to implement, high in accuracy rate and the like.

Description

technical field [0001] The invention belongs to the field of intelligent detection of tool breakage, and more specifically relates to a system and method for detecting tool breakage of CNC machine tools based on deep learning. Background technique [0002] With the rapid popularization of CNC machine tools in the manufacturing industry, using intelligent methods to monitor, maintain the continuous and healthy operation of CNC machine tools, and improve the productivity of CNC machine tools has become an important topic in the field of intelligent manufacturing. Real-time detection of machine tool breakage is an important problem to be solved in CNC machining, especially in the production mode of "unmanned factory" or "one person with multiple machines", if the machine tool breaks, it needs to be found and replaced in time, otherwise it will be Destroy the workpiece currently being processed and the subsequent feeding, resulting in waste or defective products, seriously affec...

AI Technical Summary

Problems solved by technology

[0004] There are many types of automatic tool breakage detection technologies for CNC machine tools, which are mainly based on sensor signals such as probe displacement, cutting force changes, and power signal changes. They can achieve good detection results under limited conditions, but there are still complex sensor installations. , more easily affected by noise, and the detection accuracy is not high

Images