• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.181-189
• /
• 2023

In this paper, we present a case study of developing MVIS (Machine Vision Inspection System) designed for exterior quality inspection of stamping dies used in the production of automotive exterior components in a small to medium-sized factory. While the primary processes within the factory, including machining, transportation, and loading, have been automated using PLCs, CNC machines, and robots, the final quality inspection process still relies on manual labor. We implement the MVIS with general-purpose industrial cameras and Python-based open-source libraries and frameworks for rapid and low-cost development. The MVIS can play a major role on improving throughput and lead time of stamping dies. Furthermore, the processed inspection images can be leveraged for future process monitoring and improvement by applying deep learning techniques.

• Journal of Korea Multimedia Society
• /
• v.21 no.6
• /
• pp.649-658
• /
• 2018

In this paper, we propose a mechanical contact inner tap inspection system that can inspect the defect of the inner tap immediately after inner tap is processed within the machining center. The inspection module has the collet chuck structure, so it can mounted on the main spindle of the machining center during inspection. It was developed with a focus on inspection for tap having 20 mm depth which is primarily fabricated in automotive parts and has a double sided PCB-type control system including sensing function based on Zigbee module, micom and IR sensor for wireless transmission of measured data with low power operation, and also a battery for supplying electric power. The current consumption is 46.8mA in the inspection operation mode and 0.0268mA in the power saving mode for 3.7V of the applied power source, so that 30,000 times or more inspection can be performed with assumed 5 seconds inspection time for one tap. Experiments in test jig system and actual machining center confirm that the proposed inner tap inspection system can be applied to the batch process of simultaneous inspection after tapping in the machining center.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.8
• /
• pp.83-88
• /
• 2004

The Classification of defected oil-seals using a vision system with the artificial neural network is presented. The artificial neural network fur classification consists of 27 input nodes, 10 hidden nodes, and one output node. The selection of the number of the input nodes is based on an observation that the difference among the defected, non-defected, and smeared oil-seals is greatly pronounced in the 26 step gray-scale level thresholding. The number of the hidden nodes is chosen as a result of a trade-off between accuracy and computing time. The back-propagation algorithm is used for teaching the network. The proposed network is capable of successfully classifying the defected from the smeared oil-seals which tend to be classified as the defected ones using the binary thresholding. It is envisaged that the proposed method improves the reliability and productivity of the automotive vision inspection system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.3
• /
• pp.71-78
• /
• 1999

This paper presents an integrated and automated inspection system using image processing technology for the automotive engine assembly process. The system make it possible for the inspected data to be entered directly from the machine vision into the statistical process control system. Such direct entry enables the prompt preparation of corrective actions against process problems. An IVP-150 machine vision board is installed within the PC for image processing, and a template matching technology is implemented to precisely verify quality factors. The developed system showed robustness to the problems of noise, distortion, and orientation.

• International Journal of Automotive Technology
• /
• v.7 no.7
• /
• pp.777-784
• /
• 2006

The lateral dynamic behaviours of a track inspection vehicle with laterally guided system are studied for the safety and comfort. A 10-DOF dynamic model is proposed counting for lateral and yaw motions. The equations for motions of the vehicle running on curved tracks at a constant speed are presented. It is shown by simulation that lateral guiding forces applied to the guiding wheels on the inner side of the track increase in a larger scale in comparison with those on the outer side when the vehicle passes through curved tracks with cant, and the front guiding spring forces is larger than the rears. Lateral vibrations due to yaw motions of the vehicle take place when the vehicle runs through curved tracks. Finally, effect of the lateral guidance on the vehicle dynamics is also examined and advantages of such a guiding system are discussed in some details. An optimal guided control is applied to restrain the lateral and yaw motions. The comparisons between the active and passive guidance explain the effect of the active control approaches.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4145-4150
• /
• 2010

This research aims to design on an automatic machine vision system to replace eye inspection of alternator spool which is one of the key automotive parts. The alternator spool, plastic extrusion part would have various defects like unfinished, crack and burr. Through the design failure examples the optimized fast machine vision system will be designed to inspect all spools also focuses on the low cost machine for the middle sized company as 2'nd automotive supplier. 3-dimensional design softwares of Pro-Engineer & CATIA were used and the system were built based on the design. The system will contribute to satisfy the cycle time and can inspect each part in an absolutely accurate method, which is sufficient for industrial applications.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.8
• /
• pp.74-81
• /
• 2019

Cars are inspected in the transport sector for their ability to achieve the greenhouse gas reduction targets. A vehicle (automobile) inspection broadly consists of regular and total checks, and both the safety level and the amount of exhaust gas are checked simultaneously during a vehicle inspection. This study deals with the efficiency of a soot probe to measure soot emissions from diesel vehicles. When the vehicle exhaust gas measurement is performed, there may be a difference between the exhaust gas temperature and the soot suction amount because of the different shape and angle of the exhaust port for each vehicle type. This may result in some incidents where the correct inspection nonconforming vehicle is not selected. Therefore, in this study, the shape of the probe was improved to increase the soot measurement efficiency under the condition of the exhaust pipe angle change.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.179-184
• /
• 2024

In the car industry, welding is a fundamental linking technique used for joining components, such as steel, molds, and automobile parts. However, accurate inspection is required to test the reliability of the welding components. In this study, we investigate the detection of weld beads using 2D image processing in an automatic recognition system. The sample image is obtained using a 2D vision camera embedded in a lighting system, from where a portion of the bead is successfully extracted after image processing. In this process, the soot removal algorithm plays an important role in accurate weld bead detection, and adopts adaptive local gamma correction and gray color coordinates. Using this automatic recognition system, geometric parameters of the weld bead, such as its length, width, angle, and defect size can also be defined. Finally, on comparing the obtained data with the industrial standards, we can determine whether the weld bead is at an acceptable level or not.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.5
• /
• pp.146-152
• /
• 2007

Recently, The air pollution problems become hot issues as the production of the diesel automotive increases. The ministry of environment has enforced a precise inspection law to decrease the vehicle emission. In this circumstances, the smoke measurement is somewhat complicated by the use of the different type smoke meters. Although the paper filtration type opacimeter has been used for measuring smoke widely but currently the light extinction type is being used for precise inspection law. These two type opacimeters are different in their measuring principles on each other. So, for the time being the regulation standards can be confused by these two type opacimeters. In this article, The correlation factor between these two type opacimeters is studied by using engine dynamometer and vehicle test. The result of the dynamometer test shows the light extinction type is more sensitive than the filtration type by 1.47 times. But the relation factor by the vehicle test achieved 1.37 value, which is lower than that of the dynamometer test. In the future study the more precise research is needed to estimate the relation factor on vehicle test.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.10
• /
• pp.5906-5911
• /
• 2014

Currently, there are many processes of package assembly and inspections of real fields that examine whether a manufactured semiconductor can be operated regularly and can endure low humidity or high temperatures. As the inspection equipment of a semiconductor test handler picker has been used at the inspection process, these inspection equipment frames were modelled in 3D and these models were analyzed using 3 kinds of fatigue loadings. As the analysis result, maximum deformation occurred at the midparts of the frames at cases 1 and 2. Among the cases of nonuniform fatigue loads, the 'SAE bracket history' with the severest change in load became the most unstable but the 'Sample history' became the most stable. Fatigue analysis result can be used effectively with the design of an inspecting equipment frame of a semiconductor test handler picker to examine the prevention and durability against damage.