Turning tool wear state monitoring method based on metric learning

Abstract

A turning tool wear state monitoring method based on metric learning comprises the steps: preprocessing a collected tool wear image and then randomly dividing the image into a training set and a testset in proportion, wherein the training set and the test set are each divided into a support set and a test sample set; establishing a non-parameterized neural network model structure, wherein the non-parameterized neural network model structure comprises a feature extraction network, a distance metric function and an action mechanism; initializing weight, deviation and learning rate parameters ofthe feature extraction network model, and constructing an activation function; taking a cosine distance function as a distance metric function, wherein the Attention mechanism uses a softmax layer structure, and the Attention mechanism uses a softmax layer structure; calculating the current cross entropy loss by using forward propagation, and calculating the gradient of the current cross entropyloss through backward propagation; optimizing the weight and the deviation by operating a gradient descent method; and finally predicting, classifying and distinguishing the test set by using the learning parameters of the network model, and outputting the prediction accuracy. The method has the characteristics of simple algorithm implementation, error correction, high tool wear state classification accuracy, short operation time, strong real-time performance and the like.

Description

technical field [0001] The invention relates to the field of machinery, in particular to a method for monitoring the wear state of a turning tool based on metric learning. Background technique [0002] According to statistics, the failures caused by tool problems accounted for 22.4% of the total failures. In actual production, workers judge the wear state of tools based on their own experience, such as the number and processing time of workpieces, and the surface quality of workpieces. and machining noise and chip formation. There will be some problems: the tool is changed before its service life, which will increase the cost of the prop; the tool is changed only after the tool is seriously worn, which will affect the machining accuracy of the workpiece, and even damage the workpiece and the machine tool. It is necessary to apply intelligent tool wear status monitoring technology. [0003] At present, the tool wear state monitoring technology is mainly divided into: tool w...

AI Technical Summary

Problems solved by technology

[0005] In response to the above problems, the object of the present invention is to provide a method for extracting tool wear features in images and better measuring the similarity between feature vectors by adding a feature extraction network and an attention mechanism on the basis of a mathematical model of metric learning Combining the forward propagation and backward propagation of the neural network, the improved model has the way of neural network thinking to solve the problems of high algorithm complexity, real-time identification and low accuracy of turning processing based on metric learning Tool wear status monitoring method

Images