• Journal of the Korea Institute of Military Science and Technology
• /
• v.2 no.2
• /
• pp.83-91
• /
• 1999

Dynamic characteristic of manufacturing stage is understood and the utilization of each machine is maximized by developing on-line dynamic CAPP system to consider the overloads in the aircraft part manufacturing line. In this paper, a scheme of production planning and scheduling system was proposed through inspection about some predeveloped CAPP system. Developed production planning and scheduling system included process planning module. After precise inspection of some FMS line schema at domestic heavy industry, optimized FMS line was applied to aircraft part manufacturing and repairing factory. By virtue of considering overloads of factory and machine through on-line dynamic CAPP system, the utilization of resources is maximized and manufacturing lead time is minimized.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.118-121
• /
• 2002

In this study, we describe the development of viscous inspection equipment for flatron panel glass by Moire phenomenon and propose a new idea to develop an automatic inspection system for viscous or cord defects. It is possible to detect string viscous more easily and the equipment is practically being applied in production line. After using this equipment, the ratio of defective from customer is dropped significantly.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.6
• /
• pp.459-467
• /
• 2016

Using a line scan camera and a Galvano mirror, we constructed a high-speed line-scanning microscope that can generate 2D images ($8000{\times}8000pixels$) without any moving parts. The line scanner consists of a Galvano mirror and a cylindrical lens, which creates a line focus that sweeps over the sample. The measured resolutions in the x (perpendicular to line focus) and y (parallel to line focus) directions are both $2{\mu}m$, with a 2X scan lens and a 3X relay lens. This optical system is useful for measuring defects, such as spalling, chipping, delamination, etc., on the surface of carbon fiber reinforced plastic (CFRP) holes after machining in conjunction with adjustments in the angle of LED lighting. Defects on the inner wall of holes are measured by line confocal laser scanning. This confocal method will be useful for analyzing defects after CFRP machining and for fast 3D image reconstruction.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.303-309
• /
• 2018

Computer vision technology is a component inspection to obtain a video image from the camera to the machine to perform the capabilities of the human eye with a field of artificial intelligence, and then analyzed by the algorithm to determine to determine the good and bad of production parts It is widely applied. Shape inspection method was used as how to identify the location of the start point and the end point of the search range, measure the height to the line scan method, in such a manner as to determine the presence or absence of the bolt tabs average brightness of the inspection area in a circular scan type value And the degree of similarity was calculated. The total time it takes to test in the test performance tests of two types of bolts tab enables test 300 min, and demonstrated the accuracy and efficiency of the inspection on the production line represented a complete inspection accuracy.

• IE interfaces
• /
• v.4 no.2
• /
• pp.43-51
• /
• 1991

A line search method is developed to locate all the conerpoints of 2-dimensional polygon images for inspection purposes. This optimization-based method is used to approximate a 2-D curved object by a polygon. This scheme is also developed for inspection of objects in industrial environment. The inspection includes dimensional verification and pattern matching which compares a 2-D image of an object to a pattern image. The method proves to be computationally efficient and accurate for real time application.

• Journal of the Korean Institute of Gas
• /
• v.15 no.1
• /
• pp.15-21
• /
• 2011

Cost-benefit analysis (CBA) has been performed in order to decide whether the ILI (in-line inspection) suggested as risk mitigation measure (RMM) from quantitative risk assessment is reasonably practicable. As a result of CBA, we could find out the reasonable intervals of implementation of ILI. In order to assess the benefit, value of preventing a fatality (VPF), which measures value of human life, has been used. The adequate VPF figure of high pressure urban gas pipelines for CBA used in this paper is two billion won. As a result of 2 case studies, we found that the most reasonable intervals of ILI suggested as RMM were 13 years or 15 years.

• Journal of the Korea Safety Management & Science
• /
• v.10 no.3
• /
• pp.253-265
• /
• 2008

In this paper, we developed a heuristic algorithm to assign job to workers in parallel line inspection process without sequence. Objective of assigning job in inspection process is only to assign job to workers evenly. But this objective needs much time and effort since there are many cases in assigning job and cases increase geometrically if the number of job and worker increases. In order to solve this problem, we proposed heuristic algorithm to assign job to workers evenly. Experiments of assigning job are performed to evaluate performance of this heuristic algorithm. The result shows that heuristic algorithm can find the optimal solution to assign job to workers evenly in many type of cases. Especially, in case there are more than two optimal solutions, this heuristic algorithm can find the optimal solution with 98% accuracy.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.769-772
• /
• 1998

This paper present an efficient techniques for visual inspection of taped electronic parts, suitable for real time implementation. The main environments of developed system are IBM-compatible personal computer, frame grabber, digital input-output board. It is connected to the programmable logic controller unit of the taping machine in real time. Using a queuing structure, operator or extractor machine can remove easily the defect one from production line. Also, we design a new illumination system for sacquring shape and subface features of object. Therefore, it redue pre-processing step and processing time.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.1
• /
• pp.167-177
• /
• 2012

In this paper, we raised the performance of heuristic algorithm to assign job to workers in parallel line inspection process without sequence. In previous research, we developed the heuristic algorithm. But the heuristic algorithm can't find optimal solution perfectly. In order to solve this problem, we proposed new method to make initial solution called FN(First Next) method and combined the new FN method and old FE method using previous heuristic algorithm. Experiments of assigning job are performed to evaluate performance of this FE+FN heuristic algorithm. The result shows that the FE+FN heuristic algorithm can find the optimal solution to assign job to workers evenly in many type of cases. Especially, in case there are optimal solutions, this heuristic algorithm can find the optimal solution perfectly.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.