scholarly journals Identification of tool wear using acoustic emission signal and machine learning methods

2021 ◽  
Author(s):  
Paweł Twardowski ◽  
Maciej Tabaszewski ◽  
Martyna Wiciak – Pikuła ◽  
Agata Felusiak-Czyryca
Keyword(s):  
Machine Learning ◽  
Acoustic Emission ◽  
Tool Wear ◽  
Acoustic Emission Signal ◽  
Learning Methods ◽  
Emission Signal ◽  
Machine Learning Methods

Identification Method of Tool Wear Based on Locally Linear Embedding and Support Vector Machine

2012 ◽  
Vol 246-247 ◽  
pp. 1289-1293
Author(s):  
Zheng Qiang Li ◽  
Peng Nie ◽  
Shu Guo Zhao
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Acoustic Emission Signal ◽  
Support Vector ◽  
Emission Signal ◽  
Identification Method ◽  
Local Linear Embedding ◽  
Local Linear ◽  
Data Points ◽  
Linear Embedding

Aiming at the nonlinear characteristics of the tool wear Acoustic Emission signal, tool wear state identification method is proposed based on local linear embedding and vector machine supported. The local linear embedding algorithm makes high dimensional information down to low dimension feature space through commutation, and thus to compress the data for highlighting signal features. This algorithm well compensates for the weakness of linear dimension reduction failing to find datasets nonlinear structure. In this paper, acoustic emission signal is firstly made by phase space reconstruction. Using local linear embedding method, the high dimension space mapping data points are reflected into low-dimensional space corresponding data points, then extracting tool wear state characteristics, and using vector machine supported classifier to identify classification of the tool wear conditions. Experimental results show that this method is used for the exact recognition of the tool wear state, and has widespread tendency.

Wavelet Packet analyses of Acoustic Emission Signal for Tool Wear in High Speed Milling

2013 ◽  
Vol 589-590 ◽  
pp. 600-605
Author(s):  
Shun Xing Wu ◽  
Peng Nan Li ◽  
Zhi Hui Yan ◽  
Li Na Zhang ◽  
Xin Yi Qiu ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Acoustic Emission Signal ◽  
High Speed ◽  
Feature Vector ◽  
Wavelet Packet ◽  
High Speed Milling ◽  
Band Energy ◽  
Emission Signal ◽  
Frequency Band Energy

Tool wear condition monitoring technology is one of the main parts of advanced manufacturing technology and is a hot research direction in recent years. A method based on the characteristics of acoustic emission signal and the advantages of wavelet packets decomposition theory in the non-stationary signal feature extraction is proposed for tool wear state monitoring with monitor the change of acoustic emission signal feature vector. In this paper, through the method, firstly, acoustic emission signal were decomposed into 4 layers with wavelet packet analysis, secondly, the frequency band energy of the have been decomposed signal were extracted, thirdly, the frequency band energy that are sensitive to tool wear were selected as feature vector, and then the corresponding relation between feature vector and tool wear was established , finally, the state of the tool wear can be distinguished according to the change of feature vector. The results show that this method can be feasibility used to monitor tool wear state in high speed milling.

Investigation of Stamping Tool Wear Initiation at Microscopic Level Using Acoustic Emission Sensors

2019 ◽  
Vol 794 ◽  
pp. 285-294 ◽  
Author(s):  
Vignesh V. Shanbhag ◽  
Bernard F. Rolfe ◽  
Narayanan Arunachalam ◽  
Michael P. Pereira
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Acoustic Emission Signal ◽  
Adhesive Wear ◽  
Microscopic Level ◽  
Mean Frequency ◽  
Severe Wear ◽  
Emission Signal ◽  
Early Stages ◽  
Acoustic Emission Sensors

Stamping tools are prone to an adhesive wear mode called galling. Adhesive wear on stamping tools can degrade the product quality and can affect the mass production. Even a small improvement in the maintenance process is beneficial for the stamping industry. Therefore, this study will focus on understanding and detecting the initiation of tool wear at the microscopic level in sheet metal stamping using acoustic emission sensors. Stamping tests were performed using a semi-industrial stamping process, which can perform clamping, piercing, stamping and trimming in a single cycle. The stamping test was performed using a high strength low alloy sheet steel and D2 tool steel for dry and lubricated conditions. The acoustic emission signal was recorded for each stamped part until severe wear on the dies was observed. These acoustic emission signals were later analyzed using time and frequency domain features. The time domain features such as peak, RMS, kurtosis and skewness could identify significant changes in the acoustic emission signal only when the severe wear was observed on the stamped parts for both dry and lubricated conditions. However, this study has identified that a frequency feature – known as mean-frequency estimate – could identify early stages of wear initiation at the microscopic level. Evidence of this early stage of wear on the part surfaces was not clearly visible to the naked eye, and could only be clearly observed via surface measurement instruments such as an optical profilometer. The sidewalls of the stamped parts corresponding to the initial change in AE mean-frequency trend were qualitatively correlated with 3D profilometer scans of the stamped parts, to show that AE mean-frequency can indicate the initial minor scratches on the sidewalls of the stamped parts due to the galling wear on the die radii surfaces. The results from this study can be used to develop a methodology to determine the very early stages of stamping tool wear, providing a strong basis for condition monitoring in the stamping industry.

Acoustic Emission Signal Acquisition and Analysis on Tool Wear

2014 ◽  
Vol 621 ◽  
pp. 171-178
Author(s):  
Hui Yu Huang ◽  
Yang Hong
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Acoustic Emission Signal ◽  
Cutting Tool ◽  
Signal Acquisition ◽  
Monitoring Methods ◽  
Damage State ◽  
Emission Signal

In the field of machinery manufacture, broken state at the time of the cutting tool in cutting metal, recognition has always been a study is of great significance. Currently, for the state of tool wear and collapse edge damage identification method already has a mature experience. However the existing condition monitoring methods are often used in accuracy and convenience has limitations, this paper USES the acoustic emission technology, as a kind of integrated online test sys tem design lay the foundation. This paper aimed at the sensor in the wireless transmission module, the performance characteristics of tool condition monitoring system of the main structure was designed, and then by acoustic emission signal from the cutting tool in cutting process as the research object, studies the cutting tool characteristics of acoustic emission signal under different damage state, for the on-line monitoring system design and calibration to provide theoretical support.

Study on accurate tool wear monitoring based on acoustic emission signal

2010 ◽  
Author(s):  
Yinhu Cui ◽  
Guofeng Wang ◽  
Dongbiao Peng ◽  
Xiaoliang Feng ◽  
Lu Zhang ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Acoustic Emission Signal ◽  
Tool Wear Monitoring ◽  
Emission Signal ◽  
Wear Monitoring
Sign in / Sign up

Export Citation Format

Share Document