• Journal of the Korean Institute of Gas
• /
• v.27 no.3
• /
• pp.72-76
• /
• 2023

Among urban gas-using facilities, more and more cases are using gas meters for leakage inspection instead of inspection ports for concealment pipes. Leak alarm alarms were continuously generated according to the boiler's special usage pattern in an environment where there was no actual gas leakage among some households where this meter was installed. It does not perform its original function of detecting actual gas leakage. Based on these problems, this study analyzed the conditions under which the gas meter for leakage inspection generates leakage alarms according to the boiler's special gas use pattern, and sought a set value that can generate an alarm only in the case of actual gas leakage. Through this, it is intended to relieve citizens' anxiety about gas use due to malfunction of the alarm and at the same time perform the original function of the meter that can detect leaking gas.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.789-792
• /
• 2003

Pipe inspection has a great importance to ensure safety for the nuclear power plant. In this paper, we designed visual inspection module for the tube internal, which diameter is 15${\sim}$20mm. And we made inspection module which consisted of CCD camera and light. And the relation between image and real world coordinate is established. Image processing is performed to calculate mapping parameter and analyze the size of defect. For the calculation of mapping parameter, experiment is performed using grid type test pattern. Acquired image is processed to extract image coordinate. Edge detection, thresholding, median filtering and morphology filtering is applied to extract grid pattern. Extracted image coordinate is used to calculate image to real world mapping. Lens distortion was considered and corrected to get exact data. Coordinate transformation data is provided for the users to recognize easily. Experiment was performed using grid type test pattern, we extracted lens distortion parameter and real coordinate of defect point. Radial distortion of lens was corrected but tangential distortion was not considered. As continuum to this study, the tangential distortion of lens is considered and improvement of analy zing technique for the tube internal be explored continuously.

• Journal of the Korean Society of Industry Convergence
• /
• v.19 no.1
• /
• pp.42-49
• /
• 2016

This study proposes a non-contact inspective technology based robot vision system for Faulty Inspection of welding States and Parts Shape. The maine focus is real time implementation of the machining parts' automatic inspection by the robotic moving. For this purpose, the automatic test instrument inspects the precision components designator the vision system. pattern Recognition Technologies and Precision Components for vision inspection technology and precision machining of precision parts including the status and appearance distinguish between good and bad. To perform a realization of a real-time automation integration system for the precision parts of manufacturing process, it is designed a robot vision system for the integrated system controller and verified the reliability through experiments. The main contents of this paper, the robot vision technology for noncontact inspection of precision components and machinery parts is useful technology for FA.

• Korean Journal of Human Ecology
• /
• v.16 no.3
• /
• pp.577-585
• /
• 2007

This research aimed for 20 latter man whose body shape of torso alters remarkably to develop nipper pattern of running type considered characteristic of body shape of 20 latter man to keep rather balanced body shape against middle age when body shape changes extremely. 1. running type nipper pattern design. Pattern of running, lining and nipper were designed by flattening surface shell. A basis line of running pattern is completed by applying reduction ratio after 3 times of modification & complement based on surface shell. Nipper pattern is designed with design line set by a plaster cast based on running pattern line. Lining pattern is designed with lining design line set by a plaster cast based on running type outside material and nipper pattern. 2. Functional evaluation of research and commercial nipper. Functional inspection through dress test was applied 5point evaluation method and the result of functional inspection on the sight of a wearer is that research nipper(running reduction ratio 15%, nipper reduction ratio 18%) averaged more 4.8point but commercial nipper averaged less 1.8point in the aspect of 20 items such as wear sensibility, motional function and external appearance aesthetic. Research running type nipper scored high in order of motional function, looks of side, back, front and whole and wear sensibility. Functional inspection in the point of view of an observer is that research nipper(running reduction ratio 15%, nipper reduction ratio 18%) averaged over 4.8point and commercial nipper averaged under 1.9point in 17 items of external appearance beauty. Research running type nipper marked high in order of looks of back, whole, front and side.

• Corrosion Science and Technology
• /
• v.18 no.6
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.9
• /
• pp.913-917
• /
• 2010

To inspect the defects of printed markings on the surface of IC package, the OCV (Optical Character Verification) method based on NCC (Normalized Correlation Coefficient) pattern matching is widely used. In order to detect the micro pattern defects appearing on the small portion of the markings, a Partitioned NCC pattern matching method was proposed to overcome the limitation of the NCC pattern matching. In this method, the reference pattern is first partitioned into several blocks and the NCC values are computed and are combined in these small partitioned blocks, rather than just using the NCC value for the whole reference pattern. In this paper, we proposed a method to decide the proper number of partition blocks and a method to inspect and combine the NCC values of each partitioned block to identify the defective markings.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.2
• /
• pp.45-51
• /
• 2012

Multilayer co-extrusion blown film construction is a popular technique for producing plastic films for various packaging industries. Automated detection of defective films can improve the quality of film production process. In this paper, we propose a film inspection system that can detect and classify film defects robustly. In our system, first, film images are acquired through a high speed line-scan camera under an appropriate lighting system. In order to detect and classify film defects, an inspection algorithm is developed. The algorithm divides the typical film defects into two groups: intensity-based and texture-based. Intensity-based defects are classified based on geometric features. Whereas, to classify texture-based defects, a texture analysis technique based on local binary pattern (LBP) is adopted. Experimental results revealed that our film inspection system is effective in detecting and classifying defects for the multilayer co-extrusion blown film construction line.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.893-898
• /
• 2007

At present, one of the big characteristics in electric power market in korea is unique seller but in the near future competitions are expected in the market. so additional service for the electric power are expected. Also with development of IT technology, remote inspection for power usage are possible so as consumption pattern analysis. KORAIL is one of the biggest consumer in electric power market so it is necessary to investigate power consumption pattern. This paper presents electric load consumption pattern for representative substation like urban subway, high-speed train, industrial line and simulation program for electric power rate definition program based on billing system database. Base on the substation annual power usage DB data, the characteristic of the substation power consumption are investigated and effective electrical billing system are compared each other. Through this program it is verified that we can save more then several hundred million won for a year.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.2
• /
• pp.307-313
• /
• 2008

In this paper, we propose a novel defects inspection algorithm for TFT-LCD panels. We first compensate the distorted image caused by the camera distortion and the uneven illumination environment using the least squares method and the bezier surface. We find a starting point of each pattern for restricting each pattern. A clean image is compared to each pattern to find defects using modified PCSR-G algorithm. The simulation example shows that our algorithm not only inspects the defects well, but also is robust to the 1-pixel error.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.6
• /
• pp.45-54
• /
• 2004

Usually, according as accumulation degree of semi-conductor element increases, dynamic mistake test time increases sharply, and use of pattern generator is essential at manufacturing process to solve these problem. In this paper, we designed the PLD(Programmable Logic Device) circuit of pattern generator to examine dynamic mistake of semi-conductor element. Such all item got result that is worth verified action of return trip and function through simulation, and satisfy.