• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.1
• /
• pp.39-48
• /
• 2022

In earthquake situations, broadcasting and communication services are directly linked to rapid on-site rescue and effective restoration works. Recently, a variety of base isolation devices are widely introduced on building floors to avoid critical seismic damages of telecommunication facilities. However, in buildings with long fundamental periods, those devices may have undesirable amplification of seismic responses due to resonance effect between the building floors and base isolation devices. This study performs the seismic safety evaluation of two types of base isolation devices deployed for telecommunication facilities in mid- and high-rise buildings through numerical and experimental approaches. It is found that mid- and high-rise buildings can have low-frequency dynamic responses at the top floor when being subjected to design basis earthquake loading. Furthermore, bi-directional shake table testing demonstrated that the selected base isolation devices can exhibit unstable dynamic behaviors under such low-frequency excitations of the floor.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.126-131
• /
• 2004

The popularity of flat-panel display(FPD), including plasma display panel(PDP) and liquid-crystal display(LCD), has given rise to the need to streamline their production. In these days, PDP is one of the most popular display devices because of its expansion of manufacturing process and simplicity. Bus electrodes, sustain electrodes, barrier ribs and RGB phosphors are patterned on PDP panel to display an image. Since a minute damage on the pattern can cause a serious defect to display, it is important to inspect the pattern precisely. In this paper, an automatic inspection system of repeated pattern in PDP panel has been introduced to find the defect, such as open, short, dirt, island, and so on. And the inspection system has been operated in the mass production line of PDP.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.109-112
• /
• 1996

The more integrated and smaller SMD are needed, new solder joints packaging technologies are developed in these days such as BGA(Ball Grid Array), Flip Chip, J-lead etc. But, it's unable to inspect solder joints in those devices by visual inspection methods, because they are hided by it's packages. To inspect those new SMD packages, an X-ray system for acquiring a cross-sectional image of a arbitrary plane is necessary. In this paper, an analysis for designing X-ray cross sectional imaging system is presented including the way for correcting the distortion of image intensifier. And we show computer simulation of that system with a simple PCB model to show it's usefulness in applying PCB solder joint inspection.

• Proceedings of the KSME Conference
• /
• 2003.11a
• /
• pp.1442-1447
• /
• 2003

Computer is a very powerful machine which is widely using for data processing, DB construction, peripheral device control, image processing etc. Consequently, many researches and developments have progressed for high performance processing unit, and other devices. Especially, the core units such as semiconductor parts are rapidly growing so that high-integration, high-performance, microminiat turization is possible. The packaging in the semiconductor industry is very important technique to de determine the performance of the system that the semiconductor is used. In this paper, the inspection of the inner defects such as delamination, void, crack, etc. in the semiconductor packages is studied. ESPI which is a non-contact, non-destructive, and full-field inspection method is used for the inner defect inspection and its results are compared with that of C-Scan method.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.21 no.1
• /
• pp.72-79
• /
• 2016

Uninterruptible power supplies are extensively used as backup power in various applications such as telecommunication systems, Internet data centers, hospitals, and military technologies. Some of these applications require a considerable number of batteries, and the maintenance of such batteries is critical for the reliability of a system. However, batteries are chemical energy storage devices that deteriorate over time and frequently inspecting their performance and suitability is difficult. A real-time remote battery inspection system that applies electrochemical impedance spectroscopy is proposed and implemented in this study. The proposed system consists of a small inspection circuit and software for control. The former is developed to monitor the impedance variation of the battery and to diagnose its state. The validity and feasibility of the proposed system is proven by experimental results.

• Journal of Auto-vehicle Safety Association
• /
• v.10 no.4
• /
• pp.13-24
• /
• 2018

According to DEKRA (a Germany Certification and Inspection Agency)'s accident rate analysis by vehicle defect factor, as a result of analysis of the causes of accidents by flaws, it was found that braking devices accounted for 41%. Defects in the braking system are closely related to the accident, so it is very important to find faulty brking systems to ensure safety. The EU and USA uses ISO brake tester and the Korea is brake teater is first introduse in Japan for vehicle inspection and maintanance. KOTSA introduce the ISO brake tester in order to promote the advanced standardization of the inspection equipment and inspection tecnology, and examined the detection characteristics and applied it to the improvement direction of the brake tester to secure the driving safety.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Journal of the Korean Society of Systems Engineering
• /
• v.12 no.1
• /
• pp.89-103
• /
• 2016

Due to safety of the plant, it became very clear the importance of study occurrence reactor coolant system (RCS) issues specially the primary water stress corrosion cracking (PWSCC). The Systems Engineering (SE) approach is characterized by the application of a structured engineering methodology for the design of a complex system or component. Robotic devices have been used for internal inspection, maintenance and performing remote welding and inspection in high-radiation areas. In this paper, PWSCC overview and inlay and over lay welding methodology introduced, concept of robotic device that can be inserted into the piping via Steam Generator (SG) main way to access to primary piping of pressurized water reactor (PWR) is developed based on SE methodology. A 3D model of the inspection system was developed along with the APR1400 (Advanced Power Reactor)reactor coolant systems (RCS) and internals with virtual 3D simulation of the operation for visualization to prove the validity of the concept.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.11
• /
• pp.126-134
• /
• 1997

In this study, We made visual inspection system using Vision Board. It is consist of an illuminator (a fluorescent lamp), image input device (CCD (Charge-Coupled Device) camera), image processing system(Vision Board(FARAMVB-02)), image output device (video monitor, printer), and a measuring instrument(TELMN1000). Length measurement by visual inspection system make use of 100mm guage block(instead of calculating distance between a camera and a object). It measured horizontal and vertical length factor from 400mm to 650mm by increasing 50mm. In this place, measured horizontal and vertical length factor made use of length measure- ment of a injection. A measuring instrument used to ompare a measured length of a injection visual inspection system with it. In conclusion, length measurement of a injection compared a measuring instrument with visual inspecion system using length factor of 100mm gauge block. We find that maximum error of length is 0.55mm when it compar with the measuring value of two devices(FARAMVB-02, TELMN1000). Program of visual inspection system is made up Borland C++3.1.