• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4117-4135
• /
• 2020

Due to the angle of view, illumination and scene diversity, real-time dynamic face detection and recognition is no small difficulty in those unrestricted environments. In this study, we used the intrinsic correlation between detection and calibration, using a multi-task cascaded convolutional neural network(MTCNN) to improve the efficiency of face recognition, and the output of each core network is mapped in parallel to a compact Euclidean space, where distance represents the similarity of facial features, so that the target face can be identified as quickly as possible, without waiting for all network iteration calculations to complete the recognition results. And after the angle of the target face and the illumination change, the correlation between the recognition results can be well obtained. In the actual application scenario, we use a multi-camera real-time monitoring system to perform face matching and recognition using successive frames acquired from different angles. The effectiveness of the method was verified by several real-time monitoring experiments, and good results were obtained.

• Biomedical Science Letters
• /
• v.26 no.4
• /
• pp.302-309
• /
• 2020

Human Coxsackievirus B5 (HuCoxV-B5) infection has been associated with various diseases such as myocarditis, aseptic meningitis, hand-foot-and mouth-disease, and insulin-dependent diabetes. HuCoxV-B5 is a virus transmitted through the fecal-oral route and is detected in clinics, aquatic environments, food, shellfish, etc. and is one of the more important viruses in public health because of its incidence rate reported worldwide. In this study, a combination of SYBR Green-based real-time PCR primers for molecular diagnosis including monitoring of HuCoxV-B5 was selected and the optimal reaction conditions were established. Compared with the previously reported TaqMan probe-based real-time PCR method, assessments including a sample applicability test were performed. Results showed that the real-time PCR method developed in this study was suitable for a molecular diagnostic technique for detecting HuCoxV-B5. This study is expected to contribute to efforts in responding to safety accidents in public health because the proposed method facilitates rapid diagnosis of clinical patients. It can also be used as a specific monitoring tool of HuCoxV-B5 in non-clinical areas such as aquatic environments among others.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.87-92
• /
• 2012

Wireless sensor network is a technology that collects the information about object in real-time. Sensor data has a characteristic that is generated an unprecedented volume data in short time. Analysis is essential to define the relationship between the data, including more of the data from a large volume data stream which is acquired from the sensor. In order to effectively handle the sensor data stream, in this paper, using ECA rules to organize data in a meaningful and more practical real-time monitoring systems is proposed.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.6
• /
• pp.1-7
• /
• 2016

An uninterruptible power supply (UPS) allows small companies and domestic users to cope with power outages; but existing designs lack flexibility of control and require expensive battery maintenance, with a cost proportional to the outage compensation time. We combine a compact synchronous generator with a battery, with 10% of the capacity that would otherwise be required, to obtain a UPS with reduced maintenance costs for the same performance. Any UPS must respond immediately to a power loss, and our uninterruptible generator supply (UGS) is therefore built around real-time scheduling of its internal operations; this also makes it suitable for integration into the industrial gateway. The UGS is based on a real-time operating system, with an integrated wireless module providing connectivity to a web server, for monitoring and management, which can be performed remotely on a mobile device.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.6
• /
• pp.556-562
• /
• 2007

This paper presents the use of a novel fiber optic accelerometer system to monitor ambient vibration (both wind-induced one and vehicle-induced) of a real bridge structure. This sensor system integrates the $Moir\'{e}$ fringe phenomenon with fiber optics to achieve accurate and reliable measurements. A low-cost signal processing unit implements unique algorithms to further enhance the resolution and increase the dynamic bandwidth of the sensors. The fiber optic accelerometer has two major benefits in using this fiber optic accelerometer system for monitoring civil engineering structures. One is its immunity to electromagnetic (EM) interference making it suitable for difficult applications in such environments involving strong EM fields, electrical spark-induced explosion risks, and cabling problems, prohibiting the use of conventional electromagnetic accelerometers. The other is its ability to measure both low- and high-amplitude vibrations with a constantly high resolution without pre-setting a gain level, as usually required in a conventional accelerometer. The second benefit makes the sensor system particularly useful for real-time measurement of both ambient vibration (that is often used for structural health monitoring) and strong motion such as earthquake. Especially, the semi-strong motion and the small ambient one are successfully simulated and measured by using the new fiber optic accelerometer in the experiment of the structural health monitoring of a real bridge.

• Journal of the Korean Society for Railway
• /
• v.19 no.4
• /
• pp.445-455
• /
• 2016

A goal of the Real-time railway safety supervision system is to improve the safety oversight efficiency and to prevent accidents by integrating existing distributed monitoring systems, train, signal, power and facilities. So, the system require better performance regarding real-time processing based on big data. The disk-based database that is used in existing railway control systems has a problem with real-time processing; memory-based databases haves a limitation in terms of big-data processing; and time series databases haves a limitation in terms of real-time processing. So, we need a new database architecture for simultaneous real-time processing based on big data. In this study, we review the existing railway monitoring systems and propose a new database architecture for a real-time railway safety supervision system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.124-133
• /
• 2021

Smart factory is a future factory that collects, analyzes, and monitors various data in real time by attaching sensors to equipment in the factory. In a smart factory, it is very important to inquire and generate the status and history of equipment in real time, and the emergence of various smart devices enables this to be performed more efficiently. This paper proposes a multi device-based system that can create, search, and delete equipment status and history in real time. The proposed system uses the Android system and the smart glass system at the same time in consideration of the special environment of the factory. The smart glass system uses a QR code for equipment recognition and provides a more efficient work environment by using a voice recognition function. We designed a system structure for real time equipment monitoring based on multi devices, and we show practicality by implementing and Android system, a smart glass system, and a web application server.

• International Journal of High-Rise Buildings
• /
• v.1 no.1
• /
• pp.37-51
• /
• 2012

New generation of tall and complex buildings systems are now introduced that are reflective of the latest development in materials, design, sustainability, construction, and IT technologies. While the complexity in design is being overcome by the availability and advances in structural analysis tools and readily advanced software, the design of these buildings are still reliant on minimum code requirements that yet to be validated in full scale. The involvement of the author in the design and construction planning of Burj Khalifa since its inception until its completion prompted the author to conceptually develop an extensive survey and real-time structural health monitoring program to validate all the fundamental assumptions mad for the design and construction planning of the tower. The Burj Khalifa Project is the tallest structure ever built by man; the tower is 828 meters tall and comprises of 162 floors above grade and 3 basement levels. Early integration of aerodynamic shaping and wind engineering played a major role in the architectural massing and design of this multi-use tower, where mitigating and taming the dynamic wind effects was one of the most important design criteria established at the onset of the project design. Understanding the structural and foundation system behaviors of the tower are the key fundamental drivers for the development and execution of a state-of-the-art survey and structural health monitoring (SHM) programs. Therefore, the focus of this paper is to discuss the execution of the survey and real-time structural health monitoring programs to confirm the structural behavioral response of the tower during construction stage and during its service life; the monitoring programs included 1) monitoring the tower's foundation system, 2) monitoring the foundation settlement, 3) measuring the strains of the tower vertical elements, 4) measuring the wall and column vertical shortening due to elastic, shrinkage and creep effects, 5) measuring the lateral displacement of the tower under its own gravity loads (including asymmetrical effects) resulting from immediate elastic and long term creep effects, 6) measuring the building lateral movements and dynamic characteristic in real time during construction, 7) measuring the building displacements, accelerations, dynamic characteristics, and structural behavior in real time under building permanent conditions, 8) and monitoring the Pinnacle dynamic behavior and fatigue characteristics. This extensive SHM program has resulted in extensive insight into the structural response of the tower, allowed control the construction process, allowed for the evaluation of the structural response in effective and immediate manner and it allowed for immediate correlation between the measured and the predicted behavior. The survey and SHM programs developed for Burj Khalifa will with no doubt pioneer the use of new survey techniques and the execution of new SHM program concepts as part of the fundamental design of building structures. Moreover, this survey and SHM programs will be benchmarked as a model for the development of future generation of SHM programs for all critical and essential facilities, however, but with much improved devices and technologies, which are now being considered by the author for another tall and complex building development, that is presently under construction.

• Journal of Satellite, Information and Communications
• /
• v.7 no.1
• /
• pp.134-138
• /
• 2012

In this paper, we implement the real-time status monitoring system to surveil the object in the automation manufacturing facilities and we propose the CCTV video tracking system using the video tracking filter to improve efficiency. To surveil the object in automation manufacturing facilities, we implement monitoring SW on the based of the video tracking filter instead of the general method for the video monitoring so the reliable monitoring based on the PC is possible efficiently. In addition, accessibility and convenience for administrator are improved as the real-time status confirmation function. Also, we conform the performance improvement effect through the performance analysis of the proposed monitoring system using the video tracking filter.