Research On Monitoring Method Of Wear State Of Micro-milling Tool

In recent years,precision parts have been widely used in various industries.This requirement has driven the development of precision machining and micro-milling processing.Micro-milling processing refers to a milling processing method in which the diameter of the milling tool is less than one millimeter and the feature size of the workpiece to be processed is between one micron and one millimeter.Due to the advantages of high machining accuracy,diversity of machining materials,and ability to machine complex threedimensional surfaces,micro-milling has been widely used in all walks of life.However,with the sharp reduction in the size of the tool and the workpiece,compared with traditional milling,the micro-milling cutter is more prone to wear and has a more obvious impact on the accuracy of the processed workpiece.Therefore,the development of micro-milling processing technology is restricted by the wear of micro-milling cutters.Only by accurately monitoring the wear state of micro-milling cutters can the tools be replaced in time and high-precision parts can be processed.Therefore,the monitoring of tools is very important.This paper takes the identification of tool wear status in the micro-milling process as the research object,and builds a micro-milling tool wear status monitoring platform using tool vibration signals as monitoring signals is developed.Based on this platform,this paper establishes a corresponding relationship between the wear status of the micro-milling tool and the monitored characteristics.This correspondence is based on vibration signals.The main research of the full text is as follows:(1)Use the three cutting parameters of depth of cut,spindle speed and feed rate to conduct a micro-milling tool wear state experiment.The first task of this experiment is to collect signals that are closely related to the wear state.The signal used in this paper is the vibration signal of the micro-milling cutter,and it is collected under different processing conditions and different wear conditions of the micro-milling cutter.Choose an appropriate signal analysis and processing method,and perform a series of processing on the vibration signals collected by the micro-milling tool during the cutting of the workpiece.For example,time domain analysis method and frequency domain analysis method,and the time domain features and frequency domain features are extracted respectively.(2)Aiming at the problem of high dimensionality of the input sample,the feature parameters are extracted through three dimensionality reduction methods: principal component analysis(PCA),linear discriminant analysis(LDA),and supervised local preserving projection(SLPP),and The comparison shows that the low-dimensional feature parameters extracted based on PCA can better identify the wear status of subsequent micro-milling cutters.Finally,the optimal feature vector group extracted by PCA is used as the input of the subsequent recognition model.(3)The method of combining the standard particle swarm optimization algorithm(PSO)with dynamic inertia weight and the BP neural network is used to identify the wear status of the micro milling cutter.The test samples are input into the standard PSO-BP neural network of the trained dynamic inertia weight,and the wear status of the micro-milling cutter is determined through the output of the classifier.At the same time,compared with the traditional BP neural network classification model and other classification models,it proves that the standard PSO-BP neural network classification model of dynamic inertia weight has higher classification accuracy.Experimental research shows that the standard PSO-BP neural network method based on PCA and dynamic inertia weights in this paper.For the recognition of the wear status of micro-milling tools,not only the recognition speed has been significantly improved,but more importantly,the accuracy of the recognition is greatly improved.This has very important practical significance for monitoring the wear status of micro-milling cutters in the actual production process of micro-milling processing.