• Nuclear Engineering and Technology
• /
• v.42 no.2
• /
• pp.219-230
• /
• 2010

In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor's operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal component-based auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.16 no.2
• /
• pp.97-104
• /
• 2011

This paper deals with the quick and precise disaster prevention automation system (DPAS) based on information communication technology (IT) that detects fire and disasters in the building automatically and quickly and then activates the facilities to extinguish fire and disasters, monitoring such situation in a real time through wire-wireless communication network. The proposed DPAS is applied a programmable logic controller (PLC) of one-chip type which is smallsize and lightweight and also has highly sensitive-precise reliabilities. The one-chip type PLC analyzes detected signals from sensors in a case of fire and disasters, then activates fire extinguishing facilities for rapid suppression. The detected data is also transferred to a remote situation room through wire-wireless network of RS232c and bluetooth communication. The transferred data sounds an emergency alarm signal, and operates a monitoring program. The proposed DPAS based on IT will minimize the life and wealth loss from rapid measures while prevents fire and disasters.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.5
• /
• pp.303-310
• /
• 2020

In this study, a method for selection of the location and number of monitoring sensors in a building structure using artificial neural networks is proposed. The acceleration-history values obtained from the installed accelerometers are defined as the input values, and the mass and stiffness values of each story in a building structure are defined as the output values. To select the installation location and number of accelerometers, several installation scenarios are assumed, artificial neural networks are obtained, and the prediction performance is compared. The installation location and number of sensors are selected based on the prediction accuracy obtained in this study. The proposed method is verified by applying it to 6- and 10-story structure examples.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• KSCI Review
• /
• v.14 no.2
• /
• pp.159-164
• /
• 2006

MES(Manufacturing Execution System) is a control system which supports basic activities(scheduling, working process and qualify management, etc) to execute working on the shop floor. As especially MES is a system to decrease the gap between production planning and operating, it executes functions that make decision between management and labor using real-time data. MES for real-time information processing requires certain conditions such as data modeling of RFID, which has recently attracted attentions, and monitoring of each product unit from manufacture to sales. However, in the middle of processing the unit with a RFID tag, transponders(readers) can't often read the tag due to reader's malfunctions, intentional damages, loss and the circumstantial effects; for that reason, users are unable to confirm the location of the product unit. In this case, users cannot avoid tracing the path of units with uncertain clues. In this paper, we suggest that the unique MES based on RFID and Bayesian Network can immediately track the product unit, and show how to evaluate it.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.1
• /
• pp.107-114
• /
• 2011

The building infrastructures such as high-rise buildings, shopping malls, exhibition centers, etc. are becoming larger in magnitude and more complex in complexity. Considering a large number of tenants and visitors are staying in these facilities, it is upper most important to keep those in safe from fire outbreak. In this paper, a u-Disaster Prevention System has been presented to provide effective fire evacuation when fire breaks out in building infrastructures. The ubiquitous sensor network (USN) technology was applied to detect heat and smoke from fire outbreak. The information then is transmitted wirelessly to a host computer. The tenants and visitors residing in the facility can evacuate following the instruction that is displayed in LED sign boards of the u-Disaster Prevention System. A case study shows that the ubiquitous environment can help people evacuate faster in time, shorter in distance with the assistance of the u-Disaster Prevention System.

• Convergence Security Journal
• /
• v.4 no.3
• /
• pp.27-35
• /
• 2004

A current trend in telecommunication is the convergence of wireless communication and computer network technologies, and the emergence of wireless application protocol(WAP) devices is an example. Computer system managers are often requested to solve urgent system problems. Many times, they cannot access a computer to perform remote system management tasks. Aiming at solving this problem, this paper presents a novel tool for system management that uses a WAP interface, and focuses on the description of the architecture and the associated application modules.

• Journal of Ecology and Environment
• /
• v.47 no.4
• /
• pp.264-271
• /
• 2023

Environmental crises caused by climate change and human-induced disturbances have become urgent challenges to the sustainability of human beings. These issues can be addressed based on a data-driven understanding and forecasting of ecosystem responses to environmental changes. In this study, we introduce a long-term ecological monitoring system in Korean Long-Term Ecological Research (KLTER), and a plan for the Korean Ecological Observatory Network (KEON). KLTER has been conducted since 2004 and has yielded valuable scientific results. However, the KLTER approach has limitations in data integration and coordinated observations. To overcome these limitations, we developed a KEON plan focused on multidisciplinary monitoring of the physiochemical, meteorological, and biological components of ecosystems to deepen process-based understanding of ecosystem functions and detect changes. KEON aims to answer nationwide and long-term ecological questions by using a standardized monitoring approach. We are preparing three types of observatories: two supersites depending on the climate-vegetation zones, three local sites depending on the ecosystem types, and two mobile deployment platforms to act on urgent ecological issues. The main observation topics were species diversity, population dynamics, biogeochemistry (carbon, methane, and water cycles), phenology, and remote sensing. We believe that KEON can address environmental challenges and play an important role in ecological observations through partnerships with international observatories.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.117-127
• /
• 2024

Purpose: The purpose is to conduct basic research to save energy and improve the safety of manufacturing plant infrastructure by comprehensively monitoring energy management, temperature, humidity, dust and gas, air quality, and machine operation status in small and medium-sized manufacturing plants. Method: To this end, energy-related data and environmental information were collected in real time through digital power meters and IoT sensors, and research was conducted to disseminate and respond to situations for energy saving through monitoring and analysis based on the collected information. Result: We presented an application plan that takes into account energy management, cost reduction, and safety improvement, which are key indicators of ESG management activities. Conclusion: This study utilized various sensor devices and related devices in a smart factory as a practical case study in a company. Based on the information collected through research, a basic system for energy saving and safety improvement was presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.11
• /
• pp.2107-2112
• /
• 2006

As growing up of elderly population, the interesting on healthcare system in normal life using W is increasing. An integrated u-healthcare service architecture with IEEE 802.11 and IEEE 802.15.4 based sensor network and code divisi(m multiple access(CDMA) public mobile telecommunication networks was designed and developed. Sensor nodes with electrocardiogram(ECG), body core temperature sensors are attached on the patients' body. The healthcare parameters are transferred to web server via CDMA mobile network or through existed LAN network. The existed LAN network is suggested to be used for continuous monitoring of patient's health status in hospital while mobile networks can be used for general purpose at home or outdoor where infra networks unavailable. This system enable healthcare personal to be able to continuously access, review, monitor and transmit the patients information whereever they are, whenever they want. And immediately check their status by using cellular phone and obtain detail information by communication with medical information server through CDMA. By using this developed integrated u-healthcare service architecture, we can monitor patients' health status for 24 hours.