오토인코더를 활용한 선반 공구의 크레이터 마모 영상 특징 추출

최재욱,허효범,박승환 대한기계학회 2023 大韓機械學會論文集A Vol.47 No.3

To monitor tool wear during cutting processing, tool wear is mainly measured indirectly through sensor signals that are most correlated with wear. The direct measurement method of tool wear using image and optical sensors is more accurate than indirect measurement, but it is mainly used to measure the amount of wear because it is difficult to apply in real time. Existing studies have been conducted mainly on flank wear caused by friction with workpiece. On the other hand, crater wear is an important monitoring factor because it is caused by friction with chips generated during processing and causes sudden tool breakage. However, for crater wear, it is difficult to measure the amount of wear because the indicator of the amount of wear is depth. Therefore, although image processing-based studies have been conducted to measure the amount of crater wear, there is a clear limit to accurately measure the depth only with the image on the top of the tool. In this work, we propose a method to extract unique features of crater wear images through autoencoder, a deep learning technique, and use them as a new measure of wear. 절삭 가공 시 공구 마모 모니터링을 위해 주로 마모와 가장 상관관계가 높은 센서 신호를 통해 공구 마모를 간접측정한다. 영상 및 광학 센서를 이용한 공구 마모의 직접측정 방식은 간접측정에 비해 정확하지만, 실시간 적용이 어렵기 때문에 주로 마모량 계측을 위해 사용한다. 기존의 연구들은 주로 가공물과의 마찰에 의해 발생하는 플랭크 마모를 대상으로 이루어졌다. 반면에, 크레이터 마모는 가공 중 생성되는 칩과의 마찰에 의해 발생하며 갑작스러운 공구 파손의 원인이 되기 때문에 중요한 모니터링 인자이다. 하지만, 크레이터 마모는 마모량의 지표가 깊이이기 때문에 마모량 계측이 어렵다. 따라서 크레이터 마모량 계측을 위한 영상처리 기반의 연구들이 진행되었지만, 공구 윗면의 영상만으로는 깊이를 정확히 측정하기에 한계가 명확하다. 본 연구에서는 딥러닝 기법인 오토인코더를 통해 크레이터 마모 영상의 고유한 특징을 추출하여 마모량의 새로운 척도로 사용하는 방법을 제안한다.

공구 교체 시점 기반 라벨링을 활용한 공구 수명 예측 모델

황주효(Ju-Hyo Hwang),진교홍(Kyo-Hong Jin) 한국정보통신학회 2024 한국정보통신학회논문지 Vol.28 No.5

제조업 분야에서 공구 마모는 생산성과 제품 품질 저하에 영향을 미치는 주요 요소로 인식되고 있다. 이를 해결하기 위해 공구 사용 횟수와 마모 기록을 라벨 데이터로 활용하여 공구 수명 예측 모델을 개발하고 있지만, 산업 현장에서는 다양한 가공 조건과 제품 생산 중단 등으로 공구 마모 데이터를 수집하기 어렵다. 또한 공구 사용 횟수는 공구품질 변동, 작업 환경 온습도 등의 요인으로 인해 사용 횟수가 동일하더라도 공구 마모도가 다르게 나타날 수 있다. 본 논문에서는 공구의 실제 교체 시기를 그 수명 종료로 간주하고 이를 기반으로 공구 교체 시점 기반 라벨링 방식을 제안하였다. 그리고 트랜스포머 기반 딥러닝 모델을 이용한 공구수명 예측 모델을 개발하고 성능 분석을 수행하였다. In the manufacturing industry, tool wear is recognized as a major factor affecting productivity and product quality degradation. To solve this problem, tool life prediction models are being developed using the number of tool uses and wear records as labeling data, but it is difficult to collect tool wear data in industrial sites due to various machining conditions and product production interruptions. In addition, the number of tool uses can cause different tool wear degrees even if the number of uses is the same due to factors such as tool quality fluctuations and working environment temperature and humidity. In this paper, the actual replacement time of a tool is considered as the end of its life, and based on this, a tool replacement time-based labeling method is proposed, and a tool life prediction model using a transformer-based deep learning model is developed and performance analysis is performed.

신경회로망을 이용한 원격모니터링을 위한 가공공정의 공구마모와 표면조도에 관한 연구

권정희(Jung-Hee Kwon),장우일(U-Il Jang),정성현(Seong Hyun Jeong),김도언(Do-Un Kim),홍대선(Dae Sun Hong) 한국생산제조학회 2012 한국생산제조학회지 Vol.21 No.1

The tool wear and failure in automatic production system directly influences the quality and productivity of a product, thus it is essential to monitor the tool state in real time. For such purpose, an ART2-based remote monitoring system has been developed to predict the appropriate tool change time in accordance with the tool wear, and this study aims to experimently find the relationship between the tool wear and the monitoring signals in cutting processes. Also, the roughness of workpiece according to the wool wear is examined. Here, the tool wear is indirectly monitored by signals from a vibration senor attached to a machining center. and the wear dimension is measured by a microscope at the start, midways and the end of a cutting process. A series of experiments are carried out with various feedrates and spindle speeds, and the results show that the sensor signal properly represents the degree of wear of a tool being used, and the roughnesses measured has direct relation with the tool wear dimension. Thus, it is concluded that the monitoring signals from the vibration sensor can be used as a useful measure for the tool wear monitoring.

Vision Based On-Machine Measurement of Flank Wear in Drill Tool for Smart Machine Tool

김태곤(Tae-Gon Kim),신강우(Kangwoo Shin),이석우(Seok-Woo Lee) Korean Society for Precision Engineering 2018 한국정밀공학회지 Vol.35 No.2

Tool wear is an essential parameter in determining tool life, machining quality and productivity. Current or power signals from motor drivers in machine have been used to estimate tool wear. However, accuracy of tool wear estimation was not enough to measure the amount of tool wear. In this study, flank wear of a drill tool was measured using vision sensor module which has zoom lens, CCD camera and image processing technique. The vision module was set up in the machine tool. Therefore, the image was acquired without ejecting the tool from the machine. Image processing techniques were used to define the cutting edge shape, tool diameter, and the wear edge on cutting rips with the proposed measuring algorithm. The automatically calculated wear value was compared with a manually measured value. As a result, the difference between the manual and the automatic methods was below 4.7%. The proposed method has an advantage to decrease the measuring time and improve measuring repeatability because the tool is measured holding chuck in a spindle.

가공 조건에 따른 CNC 공작기계의 스핀들 모터 전류 부하 예측 모델 개발

조민준,정양언,김유경,강호정,김태진 대한기계학회 2023 大韓機械學會論文集A Vol.47 No.7

A CNC machine is a production equipment used for precise processing and plays a key role in automation and flexible production. CNC machines have advantages of complex and sophisticated machining, but disadvantages of quality and productivity degradation owing to tool wear and frequent tool replacement. Tool wear is significantly affected by the tool load according to cutting conditions. Tool wear can be alleviated by relaxing the machining conditions, but this results in a decrease in productivity. Therefore, determining a balance between tool wear and machining time by setting appropriate machining conditions is important. Hence, in this study, a machine learning technique is used to develop a spindle motor current load model according to machining conditions. The current load of the CNC spindle motor is a factor correlated with the tool load and wear. Therefore, the developed model can be used to improve future machining conditions. CNC 공작기계는 소재의 정밀 가공을 위해 사용되는 생산 장비로 생산자동화 및 유연생산에 있어 핵심적 역할을 수행한다. CNC 공작기계는 복잡하고 정교한 가공에 장점이 있으나 공구의 마모로 인한 품질저하 및 잦은 공구 교체로 인한 생산성 저하가 문제가 된다. 공구의 마모는 절삭조건에 따른 공구 부하에 크게 영향을 받는다. 절삭조건을 완화하여 공구부하를 감소시키면 마모를 줄일 수 있으나 이는 생산속도의 저하를 초래한다. 따라서 적절한 가공 조건을 설정하여 공구 마모와 가공시간 간의 균형을 찾는 것이 중요하다. 이를 위해 본 연구에서는 머신러닝 기법을 이용하여 가공 조건에 따른 스핀들 모터의 전류 부하 예측 모델을 개발한다. CNC 스핀들 모터의 전류 부하는 공구 부하 및 마모와 상관성을 가지는 인자로 개발된 모델은 추후 가공조건을 결정하는 데 활용될 수 있다.

선삭가공시 지르코늄 코팅공구의 공구마모 특성

설한욱(Seol Han-Wook),송춘삼(Song Chun-Sam),문창성(Mun Chang-Seong),김주현(Kim Joo-Hyun) 한국생산제조학회 2005 한국공작기계학회 추계학술대회논문집 Vol.2005 No.-

In the metal cutting field many kinds of coating tools are used for improving the accuracy, reducing the cutting time and economized the material cost. Because the use of these coating tools leads desirable results, the researches recently have been considered in various ways. The research is specially investigated on measurement of tool wear. Coating material used on this research is called "zirconium" which is widely applied in daily life and in industrial area. For comparison, ZrN/TiN deposited on tools and SUS304/ Al2024 were used as the workpiece materials. Experimental results were compared with wear, surface roughness and cutting force. This new stuff "zirconium coating tool" is defined that it wears 33% less and improves surface roughness 23% more when both materials are involved in cutting condition on tool. Cutting force is discovered in vary by various workpiece however the research strongly confirms that "zirconium" remains better condition than "Titanium". As a result "Zirconium" used tool can be performed far better than "Titanium" used tool on metal cutting.

음향방출을 이용한 코팅공구의 마멸검출

맹민재,정준기 한국공작기계학회 2001 한국생산제조학회지 Vol.10 No.5

Turning experiments are conducted to investigate characteristics of acoustic emission due to wear of the coated tool. The AE signals are obtained with a sensor attached to tool holder side. Tool states are identified with scanning electron microscopy and optical microscopy. It is demonstrated that the AE signals provide reliable informations about the cutting processes and tool states. Moreover, tool wear can be detected successfully using the AE-RMS.

코어 다중가공에서 공구마모 예측을 위한 기계학습 데이터 분석

최수진(Sujin Choi),이동주(Dongju Lee),황승국(Seungkuk Hwang) 한국기계가공학회 2021 한국기계가공학회지 Vol.20 No.9

As real-time data of factories can be collected using various sensors, the adaptation of intelligent unmanned processing systems is spreading via the establishment of smart factories. In intelligent unmanned processing systems, data are collected in real time using sensors. The equipment is controlled by predicting future situations using the collected data. Particularly, a technology for the prediction of tool wear and for determining the exact timing of tool replacement is needed to prevent defected or unprocessed products due to tool breakage or tool wear. Directly measuring the tool wear in real time is difficult during the cutting process in milling. Therefore, tool wear should be predicted indirectly by analyzing the cutting load of the main spindle, current, vibration, noise, etc. In this study, data from the current and acceleration sensors; displacement data along the X, Y, and Z axes; tool wear value, and shape change data observed using Newroview were collected from the high-speed, two-edge, flat-end mill machining process of SKD11 steel. The support vector machine technique (machine learning technique) was applied to predict the amount of tool wear using the aforementioned data. Additionally, the prediction accuracies of all kernels were compared.

진동 신호의 스펙트로그램을 통한 CNC 공구 마모도 예측

강재민,임현진,구본유,권선영 한국정보과학회 2023 정보과학회 컴퓨팅의 실제 논문지 Vol.29 No.8

The use of appropriate tools in the CNC process greatly affects the overall cost of the plant and the quality of the product. Various methods are proposed for precise timing of CNC tool replacement. As a part of it, this research processed vibration time series data as an image through audio feature extraction and searched for ways to use vibration data. For predicting CNC tool wear, the accuracy was only 84.68% when using the 1D-CNN model for time-series data, whereas the accuracy was 93.75% when using the 2D-CNN model for extracted vibration images. Furthermore, the performance was improved up to 94.61% when signals from different axes were used simultaneously, and an accuracy of 98.33% was obtained when images and time series data were used simultaneously. Vibration data can be used as a useful feature for determining tool wear, and it is expected that learning methods using this feature will contribute more to tool wear management in the future.

지르코늄 코팅공구의 절삭특성

설한욱(Han-Wook Seol),김주현(Joo-Hyun Kim) 한국생산제조학회 2006 한국생산제조학회지 Vol.15 No.1

Zirconium is widely applied in industrial area. In this study, the exeperiments are performed to investigate the differences in cutting characteristics of zirconium coated material which deposited on cutting tool using physical vapor deposition(PVD). For comparison, TiN coated tool is used to compare with zirconium coated tool. Experimental results were compared for tool wear, surface roughness and cutting force. The tool wear of PVD coated bites is affected by the various cutting conditions. This new stuff “zirconium coated tool” wears 33% less and improves surface roughness 23% more in various cutting conditions. Cutting force is analyzed by using various workpiece, and the research strongly confirms that “zirconium” remains better condition than “titanium”. As a result “zirconium” coated tool can be performed far better than “titanium” coated tool on metal cutting.