• 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.

• Spatial Information Research
• /
• v.8 no.1
• /
• pp.31-50
• /
• 2000

In establishing the NGIS (The National Geographic Information System) , the Korean Government has been computerizing maps such as topographical maps as well as thematic maps. If the digital maps are mapped according to their use purpose, they can be efficiently used. The goals of this study is to describes the reasonable inspection process of digital maps. For these goals, quality controls and test processes of digital maps are investigated and then the error types of digital maps are analyzed. Nine standards which are data lineage, data format, positional accuracy, attribute accuracy, topology, logical consistency, edge-matching , completeness, outline range are established and nine steps, multi steps, which are making a work plan, analysing error types of digital maps, inspection with the naked eyes, a computerized inspection , a automatic inspection, the judge of results, the analysis of results are proposed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.8
• /
• pp.625-632
• /
• 2002

We propose an outsole measurement/inspection system to improve the quality of the shoe product. It uses the Divide-and-Conquer technique to measure the length of shoes'outsole. First, it detects edge positions of outsole's toe and heel from each image frame using an unique scale block we defined and calculates the outsole's length as the distance of two edge positions. Then it compensates the total length of outsole using the side image of outsole. Next, it classifies the outsole as inferior goods if the measurement error is bigger than 5.8mm. As a result of testing with the various kinds of outsoles, it was shown that the 95% accuracy was acquired within 1mm allowable error range. In conclusion, the proposed inspection system is effective and useful in the measurement/inspection process of shoe product and any material object as well.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.4
• /
• pp.206-213
• /
• 2011

Line sleeves, which used to connect ACSR cables when transmission lines were constructing, sometimes cause power transmission failure due to deterioration and corrosion. Therefore, power transmission line should be inspected regularly to prevent national disaster. Current inspection tool detects insertion length of transmission line on line sleeves, the inspection tool includes enormous error by operator. Moreover, the system is not controlled remotely, negligent accident would be caused while inspecting. To deal with those problems, KEPCO reviewed several ways to inspect line sleeves and proposes new method to inspect line sleeve by measuring magnetic flex which penetrate junction of steel and aluminum sleeve. The developed inspection tool is reliable enough to detect eccentric sleeves. Also, the developed inspection device was applied on actual transmission line and verified its effectiveness.

• Journal of Korean Society for Quality Management
• /
• v.24 no.1
• /
• pp.20-31
• /
• 1996

A pure zero-one integer program is formulated for determining where to assign the inspection stations in a multi-stage production system. The objective fuction is formulated to minimize the overall inspection costs. One of the major characteristics of this system is that an assigned inspection station is to inspect only the items produced in previous manufacturing stages. Each inspection station can be assigned to any possible inspection stage between two manufacturing stages. Error-free and screening inspection policy is assumed in this system and the defective items found in any inspection station will be reworked at once. The integer programming model presented in this paper has the advantages in the ease of modeling and modifiing as compared with the existing dymanamic programming methods. The solutions of the model can be easily obtained by the commercially available softwares like LINDO and GAMS.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.167-174
• /
• 1995

The Dynamic programming method are developed for determining where to assign the inspection efforts in serial multi-stage production systems. The objective function is formulated to minimize the inspection and repairing costs. One of the major assumptions in this systems is that every assigned inspection stations should inspect the only items produced in manufacturing stages after the previous inspction station. The inspection stations can be assigned at every possible inspection stage after the manufacturing stages. Two type error is considered and screening inspection policy is assumed in this system and the defective items detected in tile inspection stations will be repaired or scraped by the defective types.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1155-1160
• /
• 2017

This paper describes a system implementation for the automatic inspection on the ventilating electronic device based on the reliability improvement. To be enhancement, the inspection error is minimized by the automatic inspection system on the ventilating apparatuses against the manual inspecting system. The system consists of the control system, software structure and monitoring system to be scanning the inspection processing. The inspection system for reliability improvement is evaluated in Gage Repeatability and Reproducibility. The experimental results are improved about 2 times inspecting speed, measured error ${\pm}0.02V$, effectiveness of discriminating performance 15%, missing probability 17% and false alarm probability 12% respectively in comparing with the manual inspection based on the wind pressure sensor. The system will be also improved more by making database and product bar codes for the total quality control system to the effective reliability enhancement in the future.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.1141-1149
• /
• 2009

In Bone Mineral Density(BMD) measurements, accuracy and precision must be superior in order to know the small changes in bone mineral density and actual biological changes. Therefore the purpose of this study is to increase the reliability of bone mineral density inspection through appropriate management of image quality from machines and inspectors. For the machine management method, the recommended phantom from each bone mineral density machine manufacturer was used to take 10~25 measurements to determine the standard amount and permitted limit. On each inspection day, measurements were taken everyday or at least three times per week to verify the whether or not change existed in the amount of actual bone mineral density. Also evaluations following Shewhart control chart and CUSUM control chart rules were made for the bone mineral density figures from the phantoms used for measurements. Various forms of management became necessary for machine installation and movement. For the management methods of inspectors, evaluation of the measurement precision was conducted by testing the reproducibility of the exact same figures without any real biological changes occurring during reinspection. There were two measurement methods followed: patients were either measured twice with 30 measurements or three times with 15 measurements. An important point to make regarding measurements is that after the first inspection and any other inspection following, the patient was required to come off the inspection table completely and then get back on for any further measurements. With a 95% confidence level, the precision error produced from the measurement bone mineral figures produced a precision error of 2.77 times the minimum of the biological bone mineral density change (Least significant change: LSC). In order to assure reliability in inspection, there needs to be good oversight of machine management and measurer for machine operation and inspection error. Accuracy error in machines needs to be reduced to under 1% for scientific development in bone mineral density machines.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.3
• /
• pp.273-286
• /
• 2017

We develop an inspection method for bearing faults with a rapid change in the rotation speed and present indexes for the pass/fail inspection. At the end of line, impulse noises generated by the operation of machines and conveyors may distort the inspection results. In this paper, we present robust inspection indexes for bearing faults under impulse noises, by taking into account fault signals having pulse train. Using logistic regression, we optimize the pass/fail criterion for each index and evaluate the performance of the inspection indexes based on the total error rate.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.3
• /
• pp.297-304
• /
• 2001

Procurement decisions for inspection equipment are often made heavily based on the initial purchase price instead of the effects of inspection cost, equipment calibration and utilization over the lifetime. Cost of ownership(COO) models that take into account all of these cost factors together have been developed focusing on a single quality characteristic. In modern manufacturing environment, inspection equipment often can deal with more than one quality characteristic simultaneously. In this paper, we propose the revised COO model for the economic evaluation of the inspection equipment that can accommodate multiple quality characteristics. We also employ an engineering economy model to compare equipments with different life span. Software is developed for handy comparison of the COO of alternative equipments along with sensitivity analysis far the optimal procurement decision.