• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.9
• /
• pp.906-908
• /
• 2009

AVI (Automatic Vision Inspection) systems automatically detect defect features and measure their sizes via camera vision. It is important to predict the performance of an AVI to meet customer's specification in advance. Also the prediction can indicate the level of current performance of an AVI system. In this paper, we propose a statistical method for prediction of false alarm rate regarding inconsistency of defect size measurement process. For this purpose, only simple experiments are needed to measure the defect sizes for certain number of times. The statistical features from the experiment are utilized in the prediction process. Therefore, the proposed method is swift and easy to implement and use. The experiment shows a close prediction compared to manual inspection results.

• Korean Security Journal
• /
• no.32
• /
• pp.205-225
• /
• 2012

This study is to present an improvement of facility security through the evaluation of facility security operation level. To fulfill the purpose of the study, a survey of some facilities was conducted and the result was analyzed as follows; First, although security personnels were deployed in the facilities, the level of security personnel operation was relatively low. Second, job education training level was relatively proper, that is relevant to the result that show the level of service mind and the working mind of security personnel were proper, also relevant to the relatively good work shift system. Third, although situation room was operated well, the level of restricted area set-up and access control of visitor were low, and the level of article inspection and vehicle access control were very low. Forth, the level of security manual application that include detailed security method and procedure was proper. But accident prevention and response manual application was lower than security manual application, that show preparation for fire and negligent-accident is passive. For the improvement of facility security, the high level part and low level part in the survey result could be merged. For example, we could specify factors that show low level in the survey such as security personnel operation, access control of visitor and vehicle, article inspection, accident prevention and response in the security manual and promote education circumstance that show high level.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.33 no.4
• /
• pp.368-375
• /
• 2013

Failure of small bore piping welds is a recurring problem at nuclear power plants. And the socket weld cracking in small bore piping has caused unplanned plant shutdowns for repair and high economic impact on the plants. Consequently, early crack detection, including the detection of manufacturing defects, is of the utmost importance. Until now, the surface inspection methods has been applied according to ASME Section XI requirements. But the ultrasonic inspection as a volumetric method is also applying to enforce the inspection requirement. However, the conventional manual ultrasonic inspection techniques are used to detect service induced fatigue cracks. And there was uncertainty on manual ultrasonic inspection because of limited access to the welds and difficulties with contact between the ultrasonic probe and the OD(outer diameter) surface of small bore piping. In this study, phased array ultrasonic inspection technique is applied to increase inspection speed and reliability. To achieve this object, the 3.5 MHz phased array ultrasonic transducer are designed and fabricated. The manually encoded scanner was also developed to enhance contact conditions and maintain constant signal quality. Additionally inspection system is configured and inspection procedure is developed.

• International Journal of Precision Engineering and Manufacturing
• /
• v.6 no.3
• /
• pp.45-50
• /
• 2005

This paper proposed an efficient manufacturing system using the OMM (on-machine measurement) system. The OMM system is software-based 3D modeler for inspection on machine, and it is interfaced with machine tools via RS232C. The software is composed of two inspection modules; one is touch probe operating module, and the other is laser displacement sensor operating module. The module for touch probe needs the inspection feature extracted from CAD data. The touch probe moves to workpiece by three operating modes as follows: manual, general and automatic mode. The operating module of the laser displacement sensor is used to inspect profiles and very small holes. An advantage of this inspection method is the ability to execute on-line inspection during machining or afterward. The efficiency of proposed system which can predict and define the machining errors of each process was verified, so the developed system was applied to inspect a mold-base (cavity, core).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.5
• /
• pp.374-383
• /
• 1990

For a visual inspectio system to be viable, it must in general achieve the same or lower costs as those incurred by manual methods, it must have a reasonable inspection rate, and it must be reliable and maintainable : for the visual inspection system, inspection at high speed, flexibility for variety of products, and low cost are needed. In order to solve these problems, we propose the visual inspection algorithm by divide-and-conquer technique using the pyramid data structure and the development of simplified pattern matching method. By this method we can reduce the number of data required to compare with patterns and make the inspection time short.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.3
• /
• pp.134-141
• /
• 2014

A testing inspection is one of the important in the industry, owing to determine the reliability and directivity of testing inspection results. Therefore, the quality assurance and quality control (QA/QC) work which performed by personnel not directly in the inventory compilation development, in testing inspection must be thoroughly considered. Some agencies for environmental test inspection, they sometimes misunderstood that the QA/QC was ended with proficiency testing performance and on-site assessment by a director. Thus, results were often calculated without QA/QC work by self manual when conducting test. The objective of this study was to improve reliability of testing and inspection agency through the QA/QC case study which basically performed to raising reliability of testing and inspection agency. In this study, it increased reliability of result by verifying calibration curve (IC, ICV, CCV), blank, accuracy (LCS, MS) and precision as QA/QC performance, while performing investigation of soil contamination in mining areas. This study suggests that reliability establishing method of test result and management method of analysis process, through the QA/QC instance of testing agency.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.432-435
• /
• 2005

The Mega-pixel camera phones become main trends in mobile phone market. The lens modules used in mesa-pixel camera phones need high resolution. One of the main factors of resolution drop is the defects of bare lens. Though there are many advantages in auto-inspection of defects of bare lens, high technical problems take the defect inspections to be done with manual process. In this paper, the type and the source of defects were described and bare lens defect auto-inspection system design was explained. The designed auto-inspection system is composed of illumination optics part, focusing optics part and auto-moving system. With the proposed auto-inspection system, fast and uniform inspection of bare lens can be achieved.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.147-153
• /
• 2024

X-rays are extensively employed for non-destructive inspection, applied to packaged food, human anatomy, and industrial products. Recently, this technology has extended to inspecting batteries in electric vehicles. Given the challenge of manual inspection for a substantial volume of batteries, deep learning is leveraged to detect battery defects. However, the effectiveness of deep learning heavily depends upon data size, and acquiring authentic defective images is a difficult and time-consuming task. In this study, we use data augmentation and investigate the impact of data size on battery inspection performance. The results provide valuable insights for enhancing the capabilities of the inspection process.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.3
• /
• pp.95-107
• /
• 2024

In South Korea, over 400,000 Non-building Structures are inadequately managed and exposed to potential risks due to insufficient inspection systems, leading to an increase in accidents and significant losses of life and property. Therefore, it is crucial for users to conduct proactive self-inspections to identify and mitigate potential hazards. This study reclassified Non-building Structures into four main categories by analyzing their structural characteristics and associated risks through statistical analysis. Among these, retaining walls, which account for the largest proportion, were systematically analyzed to identify common damage patterns. Based on this analysis, self-inspection checklists were developed for both non-experts and experts. The proposed process involves an initial visual inspection using a simple non-expert checklist, followed by a more detailed expert-level inspection if any anomalies are detected. The reliability of this process was validated through approximately 120 validation processes.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.401_402
• /
• 2009