scholarly journals Milling Tool Wear State Recognition by Vibration Signal Using a Stacked Generalization Ensemble Model

2019 ◽  
Vol 2019 ◽  
pp. 1-16
Author(s):  
Yang Hui ◽  
Xuesong Mei ◽  
Gedong Jiang ◽  
Tao Tao ◽  
Changyu Pei ◽  
...  
Keyword(s):  
Tool Wear ◽  
Frequency Domain ◽  
Recognition Accuracy ◽  
Milling Process ◽  
Ensemble Model ◽  
Vibration Signals ◽  
State Recognition ◽  
Model Based ◽  
Milling Tool ◽  
Accuracy And Stability

Milling tool wear state recognition plays an important role in controlling the quality of milled parts and reducing machine tool downtime. However, the characteristics of milling process limit the accuracy and stability of tool condition monitoring (TCM) employing vibration signals. To improve this problem, this paper explores the use of vibration signals as sensing approach for recognizing tool wear states during milling operation by using the stacked generalization (SG) ensemble model. In this study, vibration signals collected during the milling process are analyzed through the time domain, frequency domain, and time-frequency domain to extract signal features. The support vector machine recursive feature elimination (SVM-RFE) algorithm is used to select the main features which are most relevant to tool wear states. The SG ensemble model based on SVM, decision tree (DT), naive Bayes (NB), and SG ensemble strategy is constructed to recognize tool wear states. The proposed method is experimental verified, and the results show that the recognition accuracy of the established SG ensemble model is 98.74% and the overall G-mean and AUC evaluation value of the model is 0.98 and 0.98, respectively. In addition, compared with other ensemble models and single models, the SG ensemble model based on vibration signals has better recognition accuracy and stability than other models.

Research on Tool Wear Form in Micro Turn-Milling Process

2012 ◽  
Vol 184-185 ◽  
pp. 663-667 ◽  
Author(s):  
Lin Hui Zhao ◽  
Jian Cheng Zhang ◽  
Wei Su
Keyword(s):  
Tool Wear ◽  
Small Diameter ◽  
Milling Process ◽  
Milling Tool ◽  
Key Factor ◽  
Part Surface ◽  
End Mills ◽  
Series Of Experiments ◽  
Turn Milling ◽  
Wear Condition

In micro machining, turn-milling tool wear is a key factor for part surface quality. This paper carries on experiments on end mills wear in micro turn-milling machining, aiming to research the wear form and provide some reference data for developing wear standard of small diameter end mills. To measure wear condition of end mills, machine vision technique is utilized. This paper designs and sets up an online end mill wear measurement system for a micro turn-milling process center. With a series of experiments on small diameter end mills, wear conditions of different cutting positions are researched. Based on analysis of experiment data, wear characteristics and wear rule for micro turn-milling process are summarized in this paper.

Research on the Technique of Tool Wear Monitoring in Plunge Milling

2010 ◽  
Vol 426-427 ◽  
pp. 468-471
Author(s):  
Xu Da Qin ◽  
X.L. Ji ◽  
X. Yu ◽  
S. Hua ◽  
Wei Cheng Liu ◽  
...  
Keyword(s):  
Tool Wear ◽  
Cutting Condition ◽  
Mean Square ◽  
Tool Wear Monitoring ◽  
Plunge Milling ◽  
Vibration Signals ◽  
Bp Artificial Neural Network ◽  
Milling Tool ◽  
Wear Monitoring ◽  
The Mean

The technique of tool wear monitoring in plunge milling is studied. The mean of cutting force signals and the root mean square (RMS) of vibration signals are selected as characteristic quantities. The model between tool wear and the characteristic quantities is built using BP artificial neural network. The result of experiment shows that the module is fit for plunge milling wear’s testing under cutting condition, and it is helpful to monitoring plunge milling tool strong wear.

Experimental Study of Sound Signal for Tool Condition Monitoring in Micro Milling Processes

2008 ◽  
Author(s):  
Chia-Liang Yen ◽  
Ming-Chyuan Lu ◽  
Ching-Yuan Lin ◽  
Tin-Hong Chen
Keyword(s):  
Tool Wear ◽  
Frequency Domain ◽  
High Speed ◽  
Wear Test ◽  
Milling Process ◽  
Micro Milling ◽  
Tool Condition ◽  
Audible Sound ◽  
End Mills ◽  
Speed Up

The audible sound signals obtained in micro-milling processes are analyzed in the time and frequency domain for the tool wear and breakage monitoring. Micro end-mills of φ 700 μm are implemented in the tool wear test, along with a high speed spindle with speed up to 60000 rpm. The audible sound signals and vibration signals for different tool conditions were collected simultaneously in the cutting. After transferring data from time domain to the frequency domain, as well as the Wavelet coefficients, the capability of audible sound signals in detecting the tool condition for the micro milling process was evaluated.

State Recognition Technology and Application on Milling Tool Wear

2007 ◽  
Vol 10-12 ◽  
pp. 869-873
Author(s):  
Chuang Wen Xu ◽  
Hua Ling Chen ◽  
Z. Liu
Keyword(s):  
Time Series ◽  
Cluster Analysis ◽  
Tool Wear ◽  
Time Series Analysis ◽  
Autocorrelation Function ◽  
Feature Vector ◽  
Fuzzy Cluster ◽  
Fuzzy Cluster Analysis ◽  
State Recognition ◽  
Milling Tool

A new method of state recognition of milling tool wear was presented based on time series analysis and fuzzy cluster analysis. After calculating, verifying liberation signal of tool state, and analyzing cutoff property, trailing property, periodicity of the sample autocorrelation function and partial autocorrelation function as well as estimating parameter of model. It can be decided that dynamic data serial is suit AR(p) (autoregression) model. Taking p equal to 12 as a feature vector extraction, based on the fuzzy cluster analysis the similarity relation between the feature vector of the tool working state and the sample feature vector was obtained. Working state of tool wear was determined according to the similarity relation of feature vector. This method was used to recognize initial wear state, normal wear state and acute wear state of milling tool. The result indicates that this method of tool wear recognition based on time series analysis and fuzzy cluster is effective.

Development of the innovative differential tool wear modeling for high-feed milling and its experimental verification

2020 ◽  
Vol 235 (1-2) ◽  
pp. 85-97
Author(s):  
PeiYi Zhao ◽  
Kai Cheng ◽  
Bin Jiang ◽  
LinHan Zuo
Keyword(s):  
Tool Wear ◽  
Milling Process ◽  
Key Factors ◽  
Wear Model ◽  
Factors Affecting ◽  
Boundary Recognition ◽  
Milling Tool ◽  
Tool Posture ◽  
High Feed ◽  
Differential Wear

During the high-feed milling process, the vibrations generated by interrupted cutting cause changes in the instantaneous tool posture, as well as in the working angle and the distribution of the thermal stress coupling fields of each tool blade. These changes result in significant differences in the wear distribution of each tool blade. In this research, well-designed experiments for the high-feed milling of titanium alloys were carried out to identify the key factors affecting the differential wear on the milling tool insert blades. A differential tool wear model for the tool blades was developed in order to comprehensively describe the effects of the location error of the blades, the vibrations in the tool posture, and the working angle of each tool blade. The wear status of the milling tool was simulated based on the dynamic tool trajectories and postures derived by the model, and the entire simulated wear distribution was investigated with an innovative wear boundary recognition method. The differential tool wear model was evaluated and validated by the milling experiments and further supported by simulations.

Sign in / Sign up

Export Citation Format

Share Document