• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.11
• /
• pp.94-101
• /
• 2020

In the age of industry 4.0, artificial intelligence is being widely used to realize machinery condition monitoring. Due to their excellent performance and the ability to handle large volumes of data, machine learning techniques have been applied to realize the fault diagnosis of different equipment. In this study, we performed the failure mode effect analysis (FMEA) of an aluminum electrolytic capacitor by using deep learning and big data. Several tests were performed to identify the main failure mode of the aluminum electrolytic capacitor, and it was noted that the capacitance reduced significantly over time due to overheating. To reflect the capacitance degradation behavior over time, we employed the Vanilla long short-term memory (LSTM) neural network architecture. The LSTM neural network has been demonstrated to achieve excellent long-term predictions. The prediction results and metrics of the LSTM and Vanilla LSTM models were examined and compared. The Vanilla LSTM outperformed the conventional LSTM in terms of the computational resources and time required to predict the capacitance degradation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.1
• /
• pp.51-58
• /
• 2016

As semiconductor technology has developed, device performance has been improved. However, since device structures became smaller, circuit aging due to operational and environmental conditions can be accelerated. Circuit aging causes a performance degradation and eventually a system error. In reliable systems, a failure due to aging might cause a great disaster. Therefore, these systems need a performance degradation prediction function so that they can take action in advance before a failure occurs. This paper presents an on-line circuit performance degradation monitoring scheme for predicting a failure by detecting performance degradation during circuit normal operation. In our proposed scheme, IEEE 1149.1 output boundary scan cells and TAP controller are reused. The experimental result shows that the proposed architecture can monitor the performance degradation during normal operation without stopping the circuit.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.191-195
• /
• 2007

Recently, landslides frequently happen at a natural slope during period of intensive rainfall. With rapidly increasing population of steep terrain in Korea, landslides have become one of the most significant natural hazards. Thus, it is necessary to protect people from landslides and to minimize the damage of houses, roads and other facilities. To accomplish this goal, many landslide prediction methods have been developed in the world. In this study, a simple landslide prediction system that enables people to escape the endangered area is developed. The system is focused to debris flows which happen frequently during periods of intensive rainfall at steep slopes in Kangwondo. This system is based on the wireless sensor network that is composed of sensor nodes, gateway, and server system. Sensor nodes that are composed of sensing part and communication part are newly developed to detect sensitive ground movement. Sensing part is designed to measure tilt angle and acceleration accurately, and communication part is deployed with Bluetooth (IEEE 802.15. I) module to transmit the data to the gateway. To verify the feasibility of this landslide prediction system, a series of laboratory tests is performed at a small-scale earth slope supplying rainfall by artificial rainfall dropping device. It is found that sensing nodes installed at slope can detect the ground motion when the slope failure starts. It is expected that the landslide prediction system by wireless senor network can provide early warnings when landslides such as debris flow occurs, and can be applied to ubiquitous computing city (U-City) that is characterized by disaster free.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.4
• /
• pp.87-91
• /
• 2019

The diagnosis of the failure for the existing electrical facilities was based on regular preventive maintenance, but this preventive maintenance was limited in preventing a lot of cost loss and sudden system failure. To overcome these shortcomings, fault prediction and diagnostic techniques are critical to increasing system reliability by monitoring electrical installations in real time and detecting abnormal conditions in the facility early. As the performance and quality deterioration problem occurs frequently due to the increase in the number of users of the motor pump, the purpose is to build an intelligent control system that can control the motor pump to maximize the performance and to improve the quality and reliability. To this end, a vibration sensor, temperature sensor, pressure sensor, and low water level sensor are used to detect vibrations, temperatures, pressures, and low water levels that can occur in the motor pump, and to build a system that can identify and diagnose information to users in real time.

• Journal of the Korean Geosynthetics Society
• /
• v.16 no.3
• /
• pp.1-10
• /
• 2017

Recently, one of the natural disasters, landslide is causing huge damage to people and properties. In order to minimize the damage caused by continuous landslide, a scientific management system is needed for technologies related to measurement and monitoring system. This study aims to establish a management system for landslide damage by prediction of slope failure. Ground behavior was predicted by surface ground deformation in case of slope failure, and the change in ground displacement was observed as slope surface. As a result, during the slope failure, the ground deformation has the collapse section, the after collapse precursor section, the acceleration section and the burst acceleration section. In all cases, increase in displacement with time was observed as a slope failure, and it is very important event of measurement and maintenance of risky slope. In the future, it can be used as basic data of slope management standard through continuous research. And it can contribute to reduction of landslide damage and activation of measurement industry.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.1
• /
• pp.145-151
• /
• 2017

In this paper, we propose the design and implementation of the system that is predicting the failure of ballast water treatment system by analysing its sensor datum and is reserving the most effective service center for sellecting the repair location on the way to the destination port. These data are collected in real time during draining or filling up the sea water from/to the ship, and it is essential to preliminarily repair the equipment showing unstable characteristics by analyzing the normal and abnormal data characteristics. We proposed a software platform for predicting and repairing faults by selecting the most efficient repair center based on this e-Navigation while the vessel is navigating to the next destination port. This system, as announced by the IMO Convention for the Prevention of Marine Pollution in 2017, provides a stable economic impact from stable cargo operation and stable out/in from/to port and marine ecosystem.

• Journal of the Korean Institute of Gas
• /
• v.27 no.2
• /
• pp.71-78
• /
• 2023

In general, electric submersible pumps (ESPs), which have an average life of 1.0 to 1.5 years, experience a decrease in performance and a reduction in life of the pump depending on oil and gas reservoir characteristics and operating conditions in wells. As the result, the failure of ESP causes high well workover costs due to retrieval and installation, and additional costs due to shut down. In this study, a flow loop system was designed and established to predict the life of ESP in long­term operation of oil and gas wells, and the life cycle data of ESP from the time of installation to the time of failure was acquired and analyzed. Among the data acquired from the system, flow rate, inlet and outlet temperature and pressure, and the data of the vibrator installed on the outside of ESP were analyzed, and then the performance status according to long-term operation was classified into five stages: normal, advice I, advice II, maintenance, and failed. Through the experiments, it was found that there was a difference in the data trend by stage during the long­term operation of the ESP, and then the condition of the ESP was diagnosed and the failure of the pump was predicted according to the operating time. The results derived from this study can be used to develop a failure prediction program and data analysis algorithm for monitoring the condition of ESPs operated in oil and gas wells.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.10a
• /
• pp.223-226
• /
• 2009

Various database and analysis system has been used for the cost effective maintenance of distribution facility but it is not effective because of the lack of interconnection among these systems. In order to overcome this problem this paper proposes reliability centered maintenance system based on the on-line monitoring of distribution system through intelligent distribution equipment. This system is made by the interconnection of distribution automation system, asset management system, failure analysis system and failure mode effect analysis system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.9
• /
• pp.1302-1307
• /
• 2013

MOV(Metal Oxide Varistor) is the most important part of SPD(Surge Protective Device) which can protect electric facilities from an impulse current such as a lightning. So far, the fault of MOVs have decided only by surge count without considering magnitude of surge current and an amount of input energy. This paper proposed the fault prediction algorithm for the MOV using look up table made by surge count and input current data which have non-linear characteristics for input current and are estimated by high voltage experimental results. Proposed algorithm was proved by experiment on verification at a high voltage laboratory.

• Journal of Advanced Marine Engineering and Technology
• /
• v.10 no.3
• /
• pp.1-10
• /
• 1986

This paper describes a new, effective method developed at the National Research Council Canada for rolling element bearing incipient failure detection. This method can detect not only outer race damage, previously published, but also inner race damage with a 100% detection rate based on a sample size of 32. The prediction of the exact angular location of the damage spot along the raceway is illustrated and experimental confirmation is presented. For the first time, a statically measurable parameter for inner and outer race damage is introduced as a means of verifying other techniques which do not offer absolute proof, but resort only to "overwhelming evidence". A brief comparison with other methods such as Shock Pulse Method, Kurtosis Analysis and High Frequency Resonance Technique is presented. A computerized automatic monitoring system utilizing the new method is described and experimental results are presented.presented.