scholarly journals New Approach based on Autoencoders to Monitor the Tool Wear Condition in HSM

2019 ◽  
Vol 52 (11) ◽  
pp. 206-211 ◽  
Author(s):  
Luis Enrique Escajeda Ochoa ◽  
Israel Benjamin Ruiz Quinde ◽  
Jorge Patricio Chuya Sumba ◽  
Antonio Vallejo Guevara ◽  
Ruben Morales-Menendez
Author(s):  
Eckart Uhlmann ◽  
Linus Lichtschlag

AbstractIn grinding, the design of the dressing process is an essential part of work preparation and restoration of the grinding wheel’s profile and cutting ability. In contrast to most grinding processes, the choice of dressing parameters in double face grinding with planetary kinematics has so far only been experience-based. As a consequence, the dressing process causes a higher degree of tool wear than the machining of the workpieces. A focused design of the dressing process based on a scientific data could help to improve the ecological and the economic efficiency by reducing tool wear and the amount of dressing tools used. In this paper, methods for determining the wear condition and the result of the dressing process, including macro- and microscopic characteristic are presented. This includes a correlation analysis between parameters of wear characteristics and workpiece surface quality. Furthermore, technological investigations are carried out in order to systematically limit the main influencing factors on the dressing process. As a result, the parameters dresser grain size dgd, rotational speed ratio nld and the machined dresser height ∆hd are identified as significant for dressing. The knowledge about their principal influence on the dressing result could provide the basis for further research.


2011 ◽  
Vol 66-68 ◽  
pp. 1163-1166
Author(s):  
Mao Jun Chen ◽  
Zhong Jin Ni ◽  
Liang Fang

In automated manufacturing systems, one of the most important issues is the detection of tool wear during the machining process. The Hausdorff-Besicovitch (HB) dimension is used to analyze the feature of the surface texture of work-piece in this paper. The value of the fractal dimension of the work-piece surface texture tends to decrease with the machining process, due to the texture becoming more complex and irregular, and the tool wear is also becoming more and more serious. That can describe the inherent relationship between work-piece surface texture and tool wear. The experimental results demonstrate the probability of using the fractal dimension of work-piece surface texture to monitor the tool wear condition.


2012 ◽  
Vol 184-185 ◽  
pp. 663-667 ◽  
Author(s):  
Lin Hui Zhao ◽  
Jian Cheng Zhang ◽  
Wei Su

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.


2014 ◽  
Vol 541-542 ◽  
pp. 1419-1423 ◽  
Author(s):  
Min Zhang ◽  
Hong Qi Liu ◽  
Bin Li

Tool condition monitoring is an important issue in the advanced machining process. Existing methods of tool wear monitoring is hardly suitable for mass production of cutting parameters fluctuation. In this paper, a new method for milling tool wear condition monitoring base on tunable Q-factor wavelet transform and Shannon entropy is presented. Spindle motor current signals were recorded during the face milling process. The wavelet energy entropy of the current signals carries information about the change of energy distribution associated with different tool wear conditions. Experiment results showed that the new method could successfully extract significant signature from the spindle-motor current signals to effectively estimate tool wear condition during face milling.


Sign in / Sign up

Export Citation Format

Share Document