이미지 피라미드와 중첩을 활용한 영상처리 기반의 인덱서블 엔드밀 공구마모영역 및 마모최대폭 측정기법

다국어 초록 (Multilingual Abstract)

Because the condition of machining tools has a significant influence on the machine downtime and the quality of machining products, maintaining it is the most important aspect in machining. This paper presents the detection process of the tool wear area and its maximal length based on image processing techniques. After collecting tool images from microscopes on the machine, we extracted region of interest (RoI) from them. Subsequently, we applied median filter, Sobel and Otsu method to RoI images to detect the flank wear area of them. To verify our proposed method, we compared it with the human measurement and image processing techniques proposed by prior literatures. Our experimental results were at least 6.7% more accurate because we used overlaid unworn tool images taken previously . With these techniques, we were able to detect tool wear area and its maximal length even for the worn tool wear area of curved surfaces.

참고문헌 (Reference)

1 E.O. Ezugwu, "Tool-wear prediction using artificial neural networks" Elsevier BV 49 (49): 255-264, 1995

2 Pauline Ong, "Tool condition monitoring in CNC end milling using wavelet neural network based on machine vision" Springer Science and Business Media LLC 104 (104): 1369-1379, 2019

3 Ulaş Çaydaş, "Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel" Springer Science and Business Media LLC 23 (23): 639-650, 2012

4 Tuğrul Özel, "Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks" Elsevier BV 45 (45): 467-479, 2005

5 Satish Chinchanikar, "Predictive modeling for flank wear progression of coated carbide tool in turning hardened steel under practical machining conditions" Springer Science and Business Media LLC 76 (76): 1185-1201, 2015

6 T. Mikołajczyk, "Predicting tool life in turning operations using neural networks and image processing" Elsevier BV 104 : 503-513, 2018

7 Chen Zhang, "On-line tool wear measurement for ball-end milling cutter based on machine vision" Elsevier BV 64 (64): 708-719, 2013

8 Thakre, A. A., "Measurements of Tool Wear Parameters using Machine Vision System, Model" 1876489-, 2019

9 Xiaolong Yu, "Image edge detection based tool condition monitoring with morphological component analysis" Elsevier BV 69 : 315-322, 2017

10 Lee, J. Y., "Image Process for Tool Wear Measure" 294-295, 2015

11 Martinsen, K., "HumanMachine Interface for Artificial Neural Network based Machine Tool Process Monitoring" 41 : 933-938, 2016

12 Kim, D. U., "Design of a Remote Monitoring System for Application to Monitoring of Multiple-Tool Wear" 136-136, 2012

13 Ramón Quiza, "Comparing statistical models and artificial neural networks on predicting the tool wear in hard machining D2 AISI steel" Springer Science and Business Media LLC 37 (37): 641-648, 2008

14 Lihong Li, "An in-depth study of tool wear monitoring technique based on image segmentation and texture analysis" Elsevier BV 79 : 44-52, 2016

15 D.R. Salgado, "An approach based on current and sound signals for in-process tool wear monitoring" Elsevier BV 47 (47): 2140-2152, 2007

16 Kim, Y. I., "A Study on the Image Processing Technique Development by Flank Wear Measurement of Cutting Tools" 302-305, 1992