http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
배용환 ( Yong Hwan Bae ) 대한설비관리학회 2014 대한설비관리학회지 Vol.19 No.2
Roll wear is a complex process where mechanical and thermal fatigue combines with impact, abrasion, adhesion and corrosion, which all depend on rolling system interactions rather than material characteristics only. The principal aim of this study is focused to the relationship between the rolling campaign, the pass schedule and work roll stress amplification by wear model and work roll fatigue damage. The roll wear and stress amplication prediction model are developed on real process working condition in computer. Wear pattern is calculated with various hot rolling pass schedule. The stress amplification effect in worn roll is proved through FEA by using ANSYS Workbenchⓡ. The stress amplification factor is calculated by comparision normal contact in dressing roll with abnormal contact at worn roll edge.
배용환 ( Yong Hwan Bae ),김호찬 ( Ho Chan Kim ) 대한설비관리학회 2014 대한설비관리학회지 Vol.19 No.4
In this paper was described implementation of a wireless remote equipment monitoring system, for realtime machine tool health condition monitoring in a limited area using wireless CDMA modem. The proposed system consists of two CDMA modem for wireless transmission and wireless reception. A hole sensor was used for measuring lathe motor current. A thermal sensor was used for measuring cutting temperature. In addition, the control unit and GPS sensor and the central monitoring PC was used for remote monitoring. The control unit is able to detect motor current value and temperature by embedded A/D converter module and transmits these values to the central monitoring PC. The system can be used for long-time continuous monitoring of machine tool with the cutting state to change. Also this system can be used for remote condition monitoring of automatic production equipment. A user-friendly graphical display was developed to display current and temperature coming from the monitored lathe.
배용환 ( Yong Hwan Bae ) 대한설비관리학회 2009 대한설비관리학회지 Vol.14 No.2
This research focuses on the development and evaluation of green wood chipper cutting assembly(herical drum cutter and feeding system). The waste wood dominates a lot of weights among industrial waste. Recycling of wood waste is very important in environmental problem solving and energy saving. Green wood chipper is needed for this purpose. The traditional chipper drum has an orthogonal cutting(2D) condition considering of saw cutter and wood cutting pattern. Additional disadvantage of this type include big cutting resistance, high cost of cutting power and extreme occurrence of vibrations. To improve this shortcoming, a helical type drum with an oblique cutting(3D) condition and feeding system are developed, this new parts decreased the vibration and cutting resistance of chipper and also improved productivity and chip porosity.
밴딩크랙방지를 위한 자동차 도어체크 마운트 브라켓 고속생산시스템 개발
배용환 ( Yong Hwan Bae ) 대한설비관리학회 2010 대한설비관리학회지 Vol.15 No.2
The anisotropy of sheet metal is important in bendability. The anisotropy in cold rolling sheets appears by the alignment of impurities, inclusions, and voids. The material ductility is reduced by this anisotropy. This anisotropy leads to cracks. Therefore, it is important to consider this anisotropy when designing progressive die. A automatic production system was developed for high productivity and safety. The conventional semi-progressive die is unfavorable for safety, material saving and high-speed production. By introducing two array type new progressive die for automobile door checker mount bracket, four times productivity more than conventional production methods is achieved. The press die parts solid modeling system is built by using Pro-Engineerⓡ through this research and verified allowable tolerance and possibility of assembly and disassembly of parts. Therefore, die manufacturing time and cost was reduced. The conventional die can produce 1000 products per hour, but new progressive die is able to produce 2000 an hour. The manufacturing cost curtailment effect is accomplished more than 40% in comparison with traditional method.
배용환(Yong Hwan Bae),김호찬(Ho-Chan Kim) 한국기계가공학회 2024 한국기계가공학회지 Vol.23 No.6
Recently, deep learning techniques have been widely used in the fields of image classification and speech recognition. In this study, we separate the image and cutting sound signal from the video obtained through the screw shaft machining process. From the separated sound signals, 13 pure cutting operation signals were extracted using signal processing software and converted into two-dimensional image spectrograms to generate training data and test data. The training data was trained using Python-based deep learning programs Deep Neural Network (DNN) and Convolutional Neural Network (CNN), and the classification accuracy was checked by test data. The results show that the job classification of turning operations using the spectrogram technique was highly accurate. In the future, it will be easier to classify stable and problematic work processes in unmanned turning systems by utilizing deep learning techniques.
선삭공정에서 딥러닝 영상처리 기법을 이용한 작업자 위험 감소 방안 연구
배용환(Yong Hwan Bae),이영태(Young Tae Lee),김호찬(Ho-Chan Kim) 한국기계가공학회 2021 한국기계가공학회지 Vol.20 No.12
The deep learning image processing technique was used to prevent accidents in lathe work caused by worker negligence. During lathe operation, when the chuck is rotated, it is very dangerous if the operator"s hand is near the chuck. However, if the chuck is stopped during operation, it is not dangerous for the operator’s hand to be in close proximity to the chuck for workpiece measurement, chip removal or tool change. We used YOLO (You Only Look Once), a deep learning image processing program for object detection and classification. Lathe work images such as hand, chuck rotation and chuck stop are used for learning, object detection and classification. As a result of the experiment, object detection and class classification were performed with a success probability of over 80% at a confidence score 0.5. Thus, we conclude that the artificial intelligence deep learning image processing technique can be effective in preventing incidents resulting from worker negligence in future manufacturing systems.