• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.113-118
• /
• 2023

Maintenance of semiconductor equipment processes is crucial for the continuous growth of the semiconductor market. The process must always be upheld in optimal condition to ensure a smooth supply of numerous parts. Additionally, it is imperative to monitor the status of the robots that play a central role in the process. Just as many senses of organs judge a person's body condition, robots also have numerous sensors that play a role, and like human joints, they can detect the condition first in the joints, which are the driving parts of the robot. Therefore, a normal state test bed and an abnormal state test bed using an aging reducer were constructed by simulating the joint, which is the driving part of the robot. Various sensors such as vibration, torque, encoder, and temperature were attached to accurately diagnose the robot's failure, and the test bed was built with an integrated system to collect and control data simultaneously in real-time. After configuring the user screen and building a database based on the collected data, the characteristic values of normal and abnormal data were analyzed, and machine learning was performed using the KNN (K-Nearest Neighbors) machine learning algorithm. This approach yielded an impressive 94% accuracy in failure diagnosis, underscoring the reliability of both the test bed and the data it produced.

• 한국IT서비스학회지
• /
• 제20권3호
• /
• pp.1-12
• /
• 2021

Reactor Coolant Pump (RCP) is core part of nuclear power plant to provide the forced circulation of reactor coolant for the removal of core heat. Properly monitoring vibration of RCP is a key activity of a successful predictive maintenance and can lead to a decrease in failure, optimization of machine performance, and a reduction of repair and maintenance costs. Here, we developed real-time RCP Vibration Analysis System (VAS) that web based platform using NoSQL DB (Mongo DB) to handle vibration data of RCP. In this paper, we explain how to implement digital signal process of vibration data from time domain to frequency domain using Fast Fourier transform and how to design NoSQL DB structure, how to implement web service using Java spring framework, JavaScript, High-Chart. We have implement various plot according to standard of the American Society of Mechanical Engineers (ASME) and it can show on web browser based on HTML 5. This data analysis platform shows a upgraded method to real-time analyze vibration data and easily uses without specialist. Furthermore to get better precision we have plan apply to additional machine learning technology.

• 한국인터넷방송통신학회논문지
• /
• 제20권1호
• /
• pp.163-169
• /
• 2020

최근 4차 산업혁명의 핵심기술인 인공지능, 빅데이터, 사물인터넷의 발전으로 산업 현장에서 가동되는 기계의 자동화 및 무인화에 대한 연구가 활발히 진행되고 있다. 이러한 공정 기계들은 부착된 다양한 센서들로부터 수집된 데이터를 기반으로 제어되고 이를 통해 공정이 관리된다. 만약 센서에 고장이 발생한다면 센서 데이터 이상으로 인해 자동화 기계들이 오작동함으로써 공정 손실 발생뿐만 아니라 인명피해로도 이어질 수 있다. 전문가가 센서의 이상 여부를 주기적으로 확인하여 관리하고 있으나 산업 현장의 여러 가지 환경요인 및 상황으로 인하여 고장점검 시기를 놓치거나 고장을 발견하지 못하여 센서 고장으로 인한 피해를 막지 못하는 경우가 발생하고 있다. 또한 고장이 발생하여도 즉각 감지하지 못함으로써 공정 손실을 더욱 악화시키고 있는 실정이다. 따라서 이러한 돌발적인 센서 고장으로 인한 피해를 막기 위해 자체적으로 임베디드 시스템에서 센서의 고장 유무를 실시간으로 파악하고 빠른 대응을 위해 고장 진단 및 유형을 판별하는 것이 필요하다. 본 논문에서는 대표적인 센서 고장 유형인 erratic fault, hard-over fault, spike fault, stuck fault를 분류하기 위해 딥 뉴럴 네트워크 기반의 고장 진단 시스템을 설계하고 라즈베리 파이를 활용하여 구현하였다. 센서 고장 진단을 위해 구글이 제안한 MobilieNetV2의 Inverted residual block 구조를 사용하여 네트워크를 구성하였다. 본 논문에서 제안하는 방식은 기존 CNN 기법을 사용한 경우보다 메모리 사용량이 줄고 성능이 향상되며, 입력 신호에 대해 구간별로 센서 고장을 분류하여 산업 현장에서 효과적으로 사용될 것으로 기대된다.

• 한국산학기술학회논문지
• /
• 제18권10호
• /
• pp.63-68
• /
• 2017

무인 운전 도시 철도시스템은 기관사 없이 열차를 운행 할 수 있는 장점을 갖지만, 이례상황 발생 시 유인운전의 기관사처럼 즉각적인 고장상태 파악, 관제보고, 수동조치가 어렵다. 따라서, 본선 운행 동안 차량 고장 / 상태 정보를 실시간으로 검지하여 차량기지 입고 시에 효율적으로 정비할 수 있는 유지보수 정보시스템의 구축이 필요하다. 본 논문에서는 무선통신망을 활용한 열차제어시스템, 관제 - 열차제어 정보시스템 콘솔 및 차량기지 유지보수 정보시스템간의 인터페이스를 실시간으로 구현하는 개념설계 방안을 제안하였다. 우선적으로 운행 중 발생되는 800,000 건/일의 많은 열차 상태 정보를 전송하기 위하여 본 연구에서 제안한 데이터 처리 알고리즘을 이용하여 56byte의 데이터 테이블로 수집한다. 이러한 상태 정보를 4자리의 헥사 코드화하여 분류하고, 본선 운행 동안 실시간으로 전동차 상태와 고장정보를 맵핑함으로서, 차량기지 내에 차량 유지보수 정보시스템에 전송한다. 또한 열차제어 정보시스템과 차량기지 유지보수 정보시스템 간에 실시간으로 송 / 수신 데이터의 전송을 각각 확인하고, 이로부터 현장에서 사용하도록 고장정보 화면구현을 구현하였다.

• Computers and Concrete
• /
• 제25권1호
• /
• pp.15-27
• /
• 2020

During the past decades, the application of acoustic emission techniques (AET) through the diagnosis and monitoring of the fracture process in materials has been attracting considerable attention. AET proved to be operative among the other non-destructive testing methods for various reasons including their practicality and cost-effectiveness. Concrete and rock structures often demand thorough and real-time assessment to predict and prevent their damage nucleation and evolution. This paper presents an overview of the work carried out on the use of AE as a monitoring technique to form a comprehensive insight into its potential application in brittle materials. Reported properties in this study are crack growth behavior, localization, damage evolution, dynamic character and structures monitoring. This literature review provides practicing engineers and researchers with the main AE procedures to follow when examining the possibility of failure in civil/resource structures that rely on brittle materials.

• Journal of Power Electronics
• /
• 제16권3호
• /
• pp.1012-1024
• /
• 2016

This study deals with an on-line software fault detection, localization, and system reconfiguration method for electrical system drives composed of three-phase AC/DC/AC converters and three-phase permanent magnet synchronous machine (PMSM) drives. Current sensor failure (outage), speed/position sensor loss (disconnection), and damaged DC-link voltage sensor are considered faults. The occurrence of these faults in PMSM drive systems degrades system performance and affects the safety, maintenance, and service continuity of the electrical system drives. The proposed method is based on the monitoring signals of "abc" currents, DC-link voltage, and rotor speed/position using a measurement chain. The listed signals are analyzed and evaluated with the generated residuals and threshold values obtained from a Sliding Mode Current-Speed-DC-link Voltage Observer (SMCSVO) to acquire an on-line fault decision. The novelty of the method is the faults diagnosis algorithm that combines the use of SMCSVO and adaptive thresholds; thus, the number of false alarms is reduced, and the reliability and robustness of the fault detection system are guaranteed. Furthermore, the proposed algorithm's performance is experimentally analyzed and tested in real time using a dSPACE DS 1104 digital signal processor board.

• 한국컴퓨터정보학회논문지
• /
• 제3권2호
• /
• pp.147-154
• /
• 1998

건물에서 사용되는 시스템 기술이 발전됨에 따라 프로세서와 시스템을 운영자가 이해 하기가 어려워지고 있다. 복잡한 시스템 설비를 운영할 때, 시스템 고장 처리를 위한 결정을 도울 수 있는 도구가 운영자에게 제공되면 설비를 관리하는데 유리하다. 따라서 본논문의 주요 목적은 IBS 건물을 최적으로 운전하기 위한 실시간 자동 에러 검출 및 진단시스템을 개발하는 데 있다.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2001년도 유체기계 연구개발 발표회 논문집
• /
• pp.315-321
• /
• 2001

The shaft system of turbine is composed of rotating shaft, blades, bearings which support the shaft, packing seal which prevent the leakage of steam, and couplings which connect the shaft. Shaft system component failure, incorrect assemblage or deflection by unexpected forces causes vibration problem. And every turbine has its own characteristics in dynamic response. In this paper we propose the three-bearing supported type rotor which is real equipment and being operated this time as commercial operation. From 1996 it has a high vibration problem and there are many kinds of trial to solve this problem. In resent outage we performed a special diagnosis and carried out appropriate work. We would like to introduce and explain about this case history.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1198-1205
• /
• 2003

Most domestic fossil power plant have exceeded 100,000 hours of operation with the severe operating condition. Among the critical components of fossil power plant, high temperature steam pipe system have had a many problems and damage from unstable displacement behavior because of frequent start up and shut down. In order to prevent the serious damage and failure of the critical pipe system in fossil power plant, 3-dimensional displacement measurement system were developed for the on-line monitoring system. 3-D Measurement system was developed with using the LVDT type sensor and rotary encoder type sensor, this system was installed and operated on the real power plant successfully. In the future time, network system of on-line diagnosis for critical pipe will be designed.

• Journal of Periodontal and Implant Science
• /
• 제42권6호
• /
• pp.217-223
• /
• 2012

Purpose: Several parameters have been described for determining the success or failure of dental implants. The surface properties of transgingival implant components have had a great impact on the long-term success of dental implants. The purpose of this study was to compare the tendency of two periodontal pathogens to adhere to and colonize zirconia abutments and titanium alloys both in hard surfaces and soft tissues. Methods: Twelve patients participated in this study. Three months after implant placement, the abutments were connected. Five weeks following the abutment connections, the abutments were removed, probing depth measurements were recorded, and gingival biopsies were performed. The abutments and gingival biopsies taken from the buccal gingiva were analyzed using real-time polymerase chain reaction to compare the DNA copy numbers of Aggregatibacter actinomycetemcomitans, Porphyromonas gingivalis, and total bacteria. The surface free energy of the abutments was calculated using the sessile water drop method before replacement. Data analyses used the Mann Whitney U-test, and P-values below 0.05 find statistical significance. Results: The present study showed no statistically significant differences between the DNA copy numbers of A. actinomycetemcomitans, P. gingivalis, and total bacteria for both the titanium and zirconia abutments and the biopsies taken from their buccal gingiva. The differences between the free surface energy of the abutments had no influence on the microbiological findings. Conclusions: Zirconia surfaces have comparable properties to titanium alloy surfaces and may be suitable and safe materials for the long-term success of dental implants.