• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.356-367
• /
• 2011

In this paper, we proposed a new car engine sealing inspection system based on image processing and understanding. The car engine sealing inspection plays very important role for protecting leakage caused by inappropriate sealing, which is a crucial point for productivity of car engines. The proposed inspection system has been aimed to enhance the previously proposed sealing inspection systems based on image processing, which have high computation complexity and low performance for correctly inspecting some contamination by oil with similar color with that of sealing. Moreover, the previously proposed system has a difficulty in installing the camera system on the sealing machine. The proposed system considers a difference of images before and after sealing obtained from one static camera. By utilizing a difference of images, the proposed system shows very robust performance using a proposed simple depth checking algorithm for some contamination cases by oil with similar color with that of sealing and the total inspection system is simple and cheap to implement. According to the experiments conducted in a real car product line, the proposed inspection system shows better inspection performance and needs smaller implementation cost than three other previously proposed system working in current car sealing inspection systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.4
• /
• pp.1559-1564
• /
• 2011

This study presents the development of a machine vision inspection system(MVIS) purposely for car seat frames as an alternative for human inspection. The proposed MVIS is designed to meet the demands, features and specifications of car seat frame manufacturing companies in striving for increased throughput of better quality. This computer-based MVIS is designed to perform quality measures by detecting holes, nuts and welding spots on every car seat frame in real time. In this study, the NI Vision Builder software for Automatic Inspection was used as a solution in configuring the aimed quality measurements. The techniques for visual inspection are optimized through qualitative analysis and simulation of human tolerance on inspecting car seat frames. Furthermore, this study exemplifies the incorporation of the optimized vision inspection environment to the pre-inspection and post-inspection subsystems. The system built on this proposed MVIS for car seat frames has successfully found the possible detections.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.11
• /
• pp.854-860
• /
• 2014

Workers engaged in car inspection works have been exposed to many occupational hazards including noise, particulate matter, and volatile organic substances. Noise-induced hearing loss(NIHL) is one of the leading health hazards among Korean workers. The aim of this study is to evaluate the noise levels in several car inspection shops by introducing the evaluation methods of KMOEL/OSHA and ACGIH. Six sites in central area of Korea were selected to monitor the noise levels of workers by personal and area sampling methods for two consecutive days in spring, summer, fall and winter seasons. Dosimeters have been used for this noise monitoring program. Obtained noise levels by the evaluation method according to KMOEL/OSHA are the range of 50.2~88.2 dB(A), these are lower than KOEL/OSHA standards level of 90 dB(A). But highest noise by ACGIH's evaluation methodology is recorded 92.3 dB(A) and is greater than NIHL standard level of 85 dB(A). So that many workers may be exposed to the dangerous noise environment. The higher the car inspection loads daily, the higher the noise levels in the sites. Seasonal fluctuation of noise levels at the process might give monitoring results with high variations. Area noise levels showed higher than those of personal sampling, which illustrate some high noise spots in the car inspection areas.

• Journal of Information Technology Services
• /
• v.17 no.3
• /
• pp.53-61
• /
• 2018

In this paper, we propose a car sealing monitoring system combined with ICT Technology. The automobile sealer is an adhesive used to bond inner and outer panels of doors, hoods and trunks of an automobile body. The proposed car sealer monitoring system is a system that can accurately and automatically inspect the condition of the automobile sealer coating process in the general often factory production line where the lighting change is very severe. The sealer inspection module checks the state of the applied sealer using an area scan camera. The vision inspection algorithm is adaptive to various lighting environments to determine whether the sealer is defective or not. The captured images and test results are configured to send the task results to the task manager in real-time as a smartphone app. Vision inspection algorithms in the plant outdoors are very vulnerable to time-varying external light sources and by configuring a monitoring system based on smart mobile equipment, it is possible to perform production monitoring regardless of time and place. The applicability of this method was verified by applying it to an actual automotive sealer application process.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1553-1558
• /
• 2007

This paper presents a vision based autonomous inspection system for welding quality control of car sinking seat. In order to overcome the precision error that arises from a visible inspection by operator in the manufacturing process of a car sinking seat, this paper proposes the MVWQC (machine vision based welding quality control) system. This system consists of the CMOS camera and NI machine vision system. The image processing software for the system has been developed using the NI vision builder system. The geometry of welding bead, which is the welding quality criteria, is measured by using the captured image with median filter applied on it. Experiments have been performed to verify the proposed MVWQC of car sinking seat.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1378-1387
• /
• 2011

Seoul Metropolitan Rapid Transit Corporation - which is operating the subway lines No. 5, 6, 7 and 8 of Seoul's subway - has been operating a variety of motor cars and rail inspection vehicles to transport workers and materials into the tunnel at night after the daily revenue service for the maintenance of tunnel structure and track. However, the air quality in tunnels has been contaminated due to the operation of diesel engine cars, and rail inspection vehicles are now having higher chances of risks since the lightweight vehicles made with aluminum bogie became too obsolete. In this study, MRT type eco-friendly electric multi-inspection car has been elaborated for the purpose of improvement of tunnel environment and replacement of motor cars and rail inspection vehicles.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.5
• /
• pp.812-816
• /
• 2015

Recently, various monitoring systems have been proposed to detect interaction performance between trains and infrastructure, as well as, various techniques to improve the accuracy and performance of such inspection equipment in high speeds. Especially, it is important to predict electric noise of high speed trains due to its effect on detection system accuracy. In this paper, we analyze various types of electrical noise in electric vehicles to improve the accuracy of the detection module of the inspection car. In detail, analysis of electric noise of high speed railway is performed as a function of speed based on field tests that were carried out by HEMU-430X (Highspeed Eletric Multiple Unit - 430 km/h eXperiment).

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.253-255
• /
• 2007

The increasing requirement for consistency and quality in the automotive industry started the development of a Machine Vision Inspection System (MVIS) for a car seat bottom cushion frame with the goal of providing a higher precision Inspection System with minimal components and less human intervention. The modifications made to an existing PC-based MVIS were shown to improve the accuracy and precision of the system. By using four monochrome cameras, the working distance was lowered and the image distortions were lessened without resorting to extensive image processing. The inspection scripts were evaluated if it could recognize good and bad products and were shown to be robust and able to reach an acceptable level of precision. It was also shown that the amount of human interaction was lessened.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.10a
• /
• pp.309-310
• /
• 2006

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.521-523
• /
• 1997

In this paper, We carried out investigation of monitoring algorithm development for electric car inspection and repair. For transmitting a data, reliable RS-422 is adopted. The LabWindows/CVI development tool of National Instruments Co. is used for the formation of monitoring screen. The experimental set-up is composed of a PC to PC system. It is applicable to electric car imspection and repair.