• The Korean Journal of Applied Statistics
• /
• v.24 no.3
• /
• pp.515-521
• /
• 2011

In this paper we consider failure detection equipment that which find failures in repairable systems and enable repair operations. In practical situations, failure detection equipment may come across troubles that can cause the omissions in detecting system failures and have a serious effect on system reliability. We analyze this effect through the appropriate modeling of Markov processes.

• The Korean Journal of Applied Statistics
• /
• v.26 no.1
• /
• pp.111-118
• /
• 2013

In this paper we study the effect of failure detection equipment(FDE)s on system availability. A new repair scheme is considered for the step of repairing FDE which becomes out of order in the course of repairing the main system(MS). We compute and compare the availability of MS.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.3
• /
• pp.15-23
• /
• 2019

This paper contains analyses and development processes of the requirements to detect the possible intermittent failure in an old avionics backplane. Interconnections for signal transmission between electronic components, such as Pin-to-PCB, FPCB-to-FPCB, pin-to-FPCB, and pint-to-wire, were selected as the main cause of intermittent failure by analyzing target equipment and documents. The possibility of detecting intermittent failures occurring in the target equipment is verified by physics-of-failure analyses. In order to verify the occurrence of intermittent failures and their detectability, latching continuity circuit testers were manufactured and accelerated life tests were performed by applying temperature and vibration cycle in consideration of flight conditions. Through the above process, the detection requirements for the major intermittent failure in the target avionics backplane was developed.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.151-160
• /
• 2022

The total system is composed of the main system (MS) and the failure detection equipment (FDE) which detects failures of MS. The analysis of system reliability is performed when the failure of FDE is possible. Several repair policies are considered to determine the order of repair of failed systems, which are sequential repair (SQ), priority repair (PR), independent repair (ID), and simultaneous repair (SM). The states of MS-FDE systems are represented by Markov models according to repair policies and the main purpose of this paper is to derive the system availabilities of the Markov models. Analytical solutions of the stationary equations are derived for the Markov models and the system availabilities are immediately determined using the stationary solutions. A simple illustrative example is discussed for the comparison of availability values of the repair policies considered in this paper.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.581-594
• /
• 2021

Purpose: The purpose of this study is to compare machine learning models for anomaly detection of mechanical facility equipment and suggest an anomaly detection system for mechanical facility equipment in subway stations. It helps to predict failures and plan the maintenance of facility. Ultimately it aims to improve the quality of facility equipment. Methods: The data collected from Daejeon Metropolitan Rapid Transit Corporation was used in this experiment. The experiment was performed using Python, Scikit-learn, tensorflow 2.0 for preprocessing and machine learning. Also it was conducted in two failure states of the equipment. We compared and analyzed five unsupervised machine learning models focused on model Long Short-Term Memory Variational Autoencoder(LSTM-VAE). Results: In both experiments, change in vibration and current data was observed when there is a defect. When the rotating body failure was happened, the magnitude of vibration has increased but current has decreased. In situation of axis alignment failure, both of vibration and current have increased. In addition, model LSTM-VAE showed superior accuracy than the other four base-line models. Conclusion: According to the results, model LSTM-VAE showed outstanding performance with more than 97% of accuracy in the experiments. Thus, the quality of mechanical facility equipment will be improved if the proposed anomaly detection system is established with this model used.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.5
• /
• pp.45-50
• /
• 2013

Recently, as the market for SMART TV expands, the camera is embedded for providing various user experience. However, this leads to occurrence of camera failure due to TV power up sequence problem, which are usually not detectable in conventional test equipments. Although the failure-detection can be possible by re-generating control signals for audio interface with new equipment, it is expensive and also requires much time to test. In this paper, for SMART TV, FPGA(Field Programmable Gate Array)-based failure-detection system is proposed which can lead to reduction of both cost and time for test.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.822-829
• /
• 2022

According to existing study into the remote fault diagnosis procedure, the current diagnostic approach has an imperfect decision model, which only supports communication in a close distance. An Internet of Things (IoT)-based remote fault diagnostic approach for wind power equipment is created to address this issue and expand the communication distance of fault diagnosis. Specifically, a decision model for active power coordination is built with the mechanical energy storage of power generation equipment with a remote diagnosis mode set by decision tree algorithms. These models help calculate the failure frequency of bearings in power generation equipment, summarize the characteristics of failure types and detect the operation status of wind power equipment through IoT. In addition, they can also generate the point inspection data and evaluate the equipment status. The findings demonstrate that the average communication distances of the designed remote diagnosis method and the other two remote diagnosis methods are 587.46 m, 435.61 m, and 454.32 m, respectively, indicating its application value.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.173-174
• /
• 2023

In this paper, we introduce a model for detecting Personal Protective Equipment (PPE) using YOLO (You Only Look Once), an object detection neural network. PPE is used to maintain a safe working environment, and proper use of PPE protects workers' safety and health. However, failure to wear PPE or wearing it improperly can cause serious safety issues. Therefore, a PPE detection system is crucial in industrial settings.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.36-41
• /
• 2008

Fault detection and diagnosis(FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. An experimental study has been performed on fault detection and diagnosis method for a water chiller. Bayes classifier, which is one of classical pattern classifiers, is adopted in deciding whether fault occurred or not. FDD algorithm can detect refrigerant leak failure, when 20% amount of charged refrigerant for normal operation leaks from the water chiller. The refrigerant leak failure caused COP reduction by 6.7% compared with normal operation performance. When two kinds of faults, such as a decrease in the mass flow rate of cooling water and temperature sensor fault of cooling water inlet, are detected, COP is a little decreased by these faults.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.581-583
• /
• 2021

Due to the pendemic of Corona 19, the use of mobile services is increasing. However, since anomalies in most mobile devices are recognized by the device's alarm, it is difficult to intuitively determine the problem of the device when a complex failure occurs. To compensate for this, in this study, the Anomaly Score was created by RRCF algorithm to intuitively recognize the problem by combining the alarm and performance information of the equipment, and the effect of detecting 97% of the past failure history was verified.