• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.12
• /
• pp.56-63
• /
• 2008

In this study, a side inspection system for circular o-ring, bolt, plastic and gasket using 8 side mirrors has been developed. The system is comprised of a CCD camera, an illumination, the first 8 mirrors and the second 8 mirrors, and moreover the image processing algorithm for detecting three different type samples is developed. The effectiveness of this algorithm was experimentally verified with three different type samples, and the inspection process is completed within max 0.2 second by help of smart camera. It is envisaged that this inspection method for side inspection system of a circular will have a wide application in the future industry.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.145-146
• /
• 2008

The appearance inspection of various electronic products and parts has been executed by the eyesight of human. But inspection by eyesight cannot bring about uniform inspection result. Because the appearance inspection result by eyesight of human is changed by condition of physical and spirit of the checker. So machine vision inspection system is currently used to many appearance inspection fields instead of the checker. However the inspection result of machine vision is changed by the illumination of workplace. Therefore we proposed histogram specification in this paper for machine vision inspection accuracy. As a result of histogram specification algorithm, we could increase the exactness of visual inspection and prevent system error from physical and spirit condition of human. More specifically, average inspection error rate was 7.5[%] in existing inspection method but we could see 0.6[%] error rate after applying the algorithm which is presented in this paper.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1642-1649
• /
• 2010

At present, KORAIL is in the middle of renovating. All steps exert great effort at cost reduction and a profit improvement. Especially to improve maintenance method and inspection period at the rolling-stock division lots of research is under progress. Daily inspection of rolling stocks is to operate the rolling stock normally. Daily inspection items are driving control device, coupling device, brake system, water system and air conditioning system, electrical system etc. Half of the maintenance manpower are inputted at daily inspection. Strengthens the quality and optimize the proportion of daily inspection are urgent problem. Daily inspection period extension aim is as follows. KTX from 3,500km to 5,000km, passenger car from 1st to 3,500km, new style electric locomotive from 2nd to 5,000km, the diesel locomotive is 2,800km from 1,200km. In this paper, the optimal daily inspection period and methods are considered including expected problem and counter measures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.6
• /
• pp.1239-1244
• /
• 2011

In our previous paper, we developed an insulator inspection robot system for a suspension insulator string in the 345kV power transmission line. However, this robot cannot be applied to a tension insulator string, because its constituent insulators are different in diameter and height from those of a suspension insulator string. To solve this problem, we developed a new live-line insulator inspection robot system that is applicable to both suspension and tension insulator strings. We confirmed its effectiveness through live-line performance tests.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.865-870
• /
• 2018

A machine vision based industrial inspection includes defects detection and classification. Fast inspection is a fundamental problem for many applications of real-time vision systems. It requires little computation time and localizing defects robustly with high accuracy. Deep learning technique have been known not to be suitable for real-time applications. Recently a couple of fast region-based CNN algorithms for object detection are introduced, such as Faster R-CNN, and YOLOv2. We apply these methods for an industrial inspection problem. Three CNN based detection algorithms, VOV based CNN, Faster R-CNN, and YOLOv2, are experimented for defect detection on metal surface. The results for inspection time and various performance indices are compared and analysed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.960-969
• /
• 2015

Over time, the import of seafood has been increased causing a corresponding increase in recall and recall costs of the fishery on the threshold level. In order to reduce recall costs and to ensure the safety of imported seafood, a moveable lab and its supporting software specialized in seafood inspection were designed. A new fishery quarantine support system software, ‘M-LIMS’ is proposed to strengthen an inspection and quarantine process for the imported seafood at the local level. This new software reads data from an external inspection equipment when it is connected to a USB or RS232 cable inspection equipment on a regular basis to save a report sent to the server after its use. Reading was possible by reading records on a central server. Each time users can check own data through a mobile device.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.8
• /
• pp.1177-1183
• /
• 2013

In this paper, the analysis of inspection period bases on reliability is suggested in the field of traction power system. Even though there are several maintenance models, the most commonly used maintenance assessment has been focused on time based maintenance in real traction power systems. The maintenance intervals are selected on the basis of long-time experience. It ensures high availability and exact planning of staff. Reliability centered maintenance, which evaluates criticality and severity of each failure mode, achieves the operation, maintenance, and cost-effective improvement that will manage the risks of equipment. This paper deals with electrification in railway inspection frequency and applied reliability based inspection frequency instead of constant intervals. The distribution function of failure rate in traction power system belongs to Weibull function. Also, the fault data and the number of installed equipments for electrifications are collected. The failure history is investigated and classified in detail. Though these complicated procedures, it contribute to extend equipment lifetime and to reduce maintenance costs.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.62 no.3
• /
• pp.127-132
• /
• 2013

In order to check traction of the elevator, the load-test is positively necessary on the inspection of elevator in Korea. So actual loads are used in the elevator car for the load-test. However, some of advanced countries in Europe, for example Germany, are using the alternative method with no load test instead of traditional load-test. Commonly hydraulic elevator, compared to passenger elevator is mainly used for loading heavy weights. It requires a great deal of labor to carry out load-test. The reason is why we developed a new inspection skill for the load-test of hydraulic elevator without actual loads. The results of studies show that the new method of the load-test can be replace the traditional load-test.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.1
• /
• pp.96-104
• /
• 2006

We propose a path planning method to improve the productivity of AOI (automated optical inspection) machines in PCB (printed circuit board) assembly lines. The path-planning problem is the optimization problem of finding inspection clusters and the visiting sequence of cameras to minimize the overall working time. A unified method is newly proposed to determine the inspection clusters and visiting sequence simultaneously. We apply a hybrid genetic algorithm to solve the highly complicated optimization problem. Comparative simulation results are presented to verify the usefulness of the proposed method.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.445-446
• /
• 2007

The goal of this paper is accuracy improvement of appearance inspection by using image separation average value matching method. The appearance inspection of various electronic products and parts has been executed by the eyesight of human. But inspection by eyesight can't bring about uniform inspection result. Because the appearance inspection result by eyesight of human is changed by condition of physical and spirit of the checker. So machine vision inspection system is currently used to many appearance inspection fields instead of the checker. However the inspection result of machine vision is changed by the illumination of workplace. Therefore we have used a average value matching in this paper for improvement of vision inspection accuracy and could increase inspection accuracy of vision system. In other words, we made an effort for elevation of vision inspection accuracy by making the identical image separation average value of reference image and input image. Also this system has been developed only using PC, CCD Camera and Visual C++ for universal workplace.