• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1385-1398
• /
• 2016

A pressurizer is a major equipment system in a nuclear power plant (NPP) and controls the reactor cooling system pressure within the allowable range. Faults in the pressurizer can be critical to the NPP; therefore, early fault detection in the pressurizer is significant for NPP safety. This study applies Mahalanobis Taguchi system (MTS), which is one of the promising pattern classification methods, based on the Mahalanobis distance concept and Taguchi quality engineering theory to the early fault detection problem of the pressurizer pressure control system. We conducted experiments using data from full scope NPP simulator based on a pressurizer pressure transmitter faults scenario to validate the faults detection performance of MTS. As a result, MTS can rapidly detect the faults compared to conventional faults detection based on single sensor monitoring.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.492-498
• /
• 2016

It is well known that since abrupt faults in induction motors tend to lead to subsequent faults and deterioration of the drive apparatus, motor faults may lead to several operating restrictions, such as security problems and economic loss. A lot of research has been done in the area of diagnosis to detect machine faults and to prevent catastrophic hazards in the motor drive system. This paper presents a new method of motor current signature analysis in which the DC-link current of the inverter-driven induction motor system, where a single current sensor is employed instead of three AC current sensors, is measured, and fast Fourier transform analysis is performed. This proposed method makes it possible to easily discern and clearly separate the motor fault current signature from the normal operation current flowing through the stator and rotor windings.

• Journal of KSNVE
• /
• v.14 no.1
• /
• pp.18-23
• /
• 2004

균열 현상은 모든 필터에서 발생하였다. 1997년 9월 원심 압축기 B에서 발생한 지나친 진동현상으로 여러 필터 중 한 필터가 부서져 임펠러 흡입부로 빨려 들어갔다. 1997년 10월 기동중에 선회실속 문제가 임펠러에서 발생하였고, 이 원인은 임펠러 eye가 부분적으로 막혔기 때문이었다. 압축기 입구와 출구의 전체 유량과 압력 상태는 정상이었기 때문에 어떠한 서지현상도 anti-surge 시스템에 의해서 감지되지 않았다. 고장상태를 진단함으로써 압축기의 재가동을 방지하여 필터들이 부서졌다는 것을 확인하게 되었다. 이번 기계 점검과정을 통하여 원격진단의 중요성을 확인하였으며, 이에 회사는 원격서비스(remote service) 계약을 체결하여 현재 원격 진단 서비스 점검이 계약 기간에 따라 정기적으로 이루어지고 있다. 이와 같이 기계에 대한 정기적인 점검을 실시하는 목적은 기계의 결함이나 고장문제를 조기에 발견함으로써 중대한 고장으로의 진행을 사전에 예방하거나 또는 최소화하는데 있다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.9
• /
• pp.1281-1286
• /
• 2010

Power plants have many components and equipment. It is difficult for operators to know the time of failure or the equipment that fails. Plants incur heavy economic losses due to unexpected failure. The equipment in power plants is constantly monitored by various sensors and instruments. However, prevention of failure is very difficult. Therefore, engineers are developing many types of failure-alarm systems that can detect the abnormal functioning of equipment. Such failure-alarm systems inform only about the abnormal functioning of equipment and do not indicate the cause of failure or the parts that have failed. In this study, we have developed a failure-prediction system that can provide details on the cause of trouble and the maintenance method.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.36-44
• /
• 2024

This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.

• Journal of the Korean Society of Industry Convergence
• /
• v.14 no.3
• /
• pp.95-100
• /
• 2011

The modern society longing for the convenience of up-to-date technology, there are attempts of miniaturization and high reliance of power equipments in the effectiveness aspect of urban area's usage of space while requiring more electrical energy than now. Consequently, paper used to the Neral Network for a forcasting conservation system. A neral network is powerful asta modeling tool that is able to capture and represent complex input/output relationships. The true power and advantage of neral networks lies in their ability to learn these relationships directly from the data being modeled. Traditional linear models are simply inadequate when it comes to modeling data that contains non-linear characteristics. Form results of this study, the Neral Network is will play an important role for insulation diagnosis system of real site GIS and power eqipment using $SF_6$ gas.

• Journal of Power System Engineering
• /
• v.20 no.2
• /
• pp.66-72
• /
• 2016

As a method to improve the equipment reliability, early warning researches that can be detected fault symptom of an equipment at an early stage are being performed out among developed countries. In this paper, when abnormal signal is input to actual normal signal of a pump, early detection studies on pump's fault symptom were carried out with auto-associative kernel regression as an advanced pattern recognition algorithm. From analysis, correlations among power of motor driving pump, discharge flow of pump, power output of pump, and discharge pressure of pump are exited. When the abnormal signal is input to one of those normal signals, the other expected values are changed due to the influence of the abnormal signal. Therefore, the fault symptom of pump through the early-warning index is able to detect at an early stage.

• Journal of the Korean Institute of Gas
• /
• v.1 no.1
• /
• pp.27-32
• /
• 1997

Continual monitoring of abnormal operating conditions i a key issue in maintaining high product quality and safe operation, since the undetected process abnormality may lead to the undesirable operations, finally producing low quality products, or breakdown of equipment. The statistical projection method recently highlighted has the advantage of easily building reference model with the historical measurement data in the statistically in-control state and not requiring any detailed mathematical model or knowledge-base of process. As the complexity of process increases, however, we have more measurement variables and recycle streams. This situation may not only result in the frequent occurrence of process Perturbation, but make it difficult to pinpoint trouble-making causes or at most assignable source unit due to the confusing candidates. Consequently, an ad hoc skill to monitor and diagnose in plat-wide scale is needed. In this paper, we propose a hierarchical plant-wide monitoring methodology based on hierarchical decomposition and principal component analysis for handling the complexity and interactions among process units. This have the effect of preventing special events in a specific sub-block from propagating to other sub-blocks or at least delaying the transfer of undesired state, and so make it possible to quickly detect and diagnose the process malfunctions. To prove the performance of the proposed methodology, we simulate the Tennessee Eastman benchmark process which is operated continuously with 41 measurement variables of five major units. Simulation results have shown that the proposed methodology offers a fast and reliable monitoring and diagnosis for a large scale chemical plant.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.14 no.2
• /
• pp.122-131
• /
• 1994

Journal bearings in the rotating machineries are vulnerable to the contamination or the insufficient supply of lubricating oil, which is likely to be the cause of unexpected shutdown or malfunction of these systems. Various destructive and nondestructive testing methods had been used for the reduction of maintenance cost and the operational safety problems due to the accidents related to bearing damages. In this experimental approach, acoustic emission monitoring is employed to the detection of incipient failure caused by intervention of foreign particles most probable in the journal bearing systems. Experimental schedules for the intervention of foreign particles was composed to be more quantitative and systematic than last study in consideration of minimum oil film thickness and particle size. The experiment was conducted under such designed conditions as inserting alumina particles to the lubrication layer in the simulated journal bearing system. Several parameters such as AE rms level, waveform, AE energy distribution and other AE event parameters are used for analysis and characterization of damage source. The results showed that the history of damage was well correlated with the changes of AE rms level and the type of damage source signal can be verified using other informations such as waveform, distributions of AE parameters etc.