Milling cutter wear states monitoring method based on deep neural network

Abstract

The invention relates to a milling cutter wear states monitoring method based on a deep neural network. The milling cutter wear states monitoring method based on the deep neural network comprises thefollowing steps of 1, collecting cutting force signals in machining process; 2, carrying out wavelet packet decomposition on collected cutting force signals by using 6-layer db 8 wavelet; and 3, using64 sub-energy bands as inputs of DNN network. Multiple DAEs are stacked layer by layer to form a DNN hidden layer structure, and fault information is extracted layer by layer through unsupervised learning layer by layer. After pre-training is completed, an output layer with a classification function is added, parameters of the DNN are finely adjusted by using a BP algorithm, and finally cutting tool wear states can be predicted. The milling cutter wear states monitoring method based on the deep neural network can be adopted without dependence on experience of signal processing experts, wear states of the milling cutter under different machining conditions can be rapidly and accurately recognized; and the milling cutter wear states monitoring method based on the deep neural network has thecharacteristics of being high in monitoring precision, adaptability and the like.

Description

technical field [0001] The invention belongs to the technical field of CNC machine tool wear detection, and more specifically relates to a method for monitoring the wear state of milling cutters based on a deep neural network. Background technique [0002] As an important part of advanced manufacturing technology, the intelligent online monitoring technology of tool status has become the subject of this research field in recent years; as the direct executor of the cutting process, the tool inevitably suffers from wear and damage during the cutting process of the workpiece Changes in tool state directly lead to increased cutting force, increased cutting temperature, increased workpiece surface roughness, workpiece size out of tolerance, cutting color change, and cutting chatter. Therefore, it is necessary to monitor the wear status of the tool. [0003] The intelligent monitoring technology of tool wear status refers to the data processing of various sensor signals detected i...

AI Technical Summary

Problems solved by technology

[0004] At present, the tool wear state monitoring technology has made great progress, but there is no monitoring method that can be applied to different processing conditions. The existing methods have ...

Images