• Title/Summary/Keyword: Mechanical diagnosis

Search Result 652, Processing Time 0.028 seconds

Fault Diagnosis Method based on Feature Residual Values for Industrial Rotor Machines

  • Kim, Donghwan;Kim, Younhwan;Jung, Joon-Ha;Sohn, Seokman
    • KEPCO Journal on Electric Power and Energy
    • /
    • 제4권2호
    • /
    • pp.89-99
    • /
    • 2018
  • Downtime and malfunction of industrial rotor machines represents a crucial cost burden and productivity loss. Fault diagnosis of this equipment has recently been carried out to detect their fault(s) and cause(s) by using fault classification methods. However, these methods are of limited use in detecting rotor faults because of their hypersensitivity to unexpected and different equipment conditions individually. These limitations tend to affect the accuracy of fault classification since fault-related features calculated from vibration signal are moved to other regions or changed. To improve the limited diagnosis accuracy of existing methods, we propose a new approach for fault diagnosis of rotor machines based on the model generated by supervised learning. Our work is based on feature residual values from vibration signals as fault indices. Our diagnostic model is a robust and flexible process that, once learned from historical data only one time, allows it to apply to different target systems without optimization of algorithms. The performance of the proposed method was evaluated by comparing its results with conventional methods for fault diagnosis of rotor machines. The experimental results show that the proposed method can be used to achieve better fault diagnosis, even when applied to systems with different normal-state signals, scales, and structures, without tuning or the use of a complementary algorithm. The effectiveness of the method was assessed by simulation using various rotor machine models.

Self-Diagnostic Signal Monitoring System of KWP2000 Vehicle ECU using Bluetooth

  • Choi, Kwang-Hun;Lee, Hyun-Ho;Lee, Young-Choon;Kwon, Tae-Kyu;Lee, Seong-Cheol
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2004년도 ICCAS
    • /
    • pp.132-137
    • /
    • 2004
  • On-Board Diagnostic(OBD) systems are in most cars and light trucks on the load today. During the 1970's and early 1980's manufacturers started using electronic means to control engine functions and diagnose engine problems. The CARB's diagnostic requirements to meet EPA emission standards have been designated as OBD with a goal of monitoring all of the emissions-related components, as well as the chassis, body, accessory devices and the diagnostic control network of the vehicle for proper operation. In this paper, we present a remote measurement system for the wireless monitoring of diagnosis signal and sensors output signals of ECU adopted KWP2000, united the OBD communication protocol, on OBD-compliant vehicle using the wirless communication technique of Bluetooth. In order to measure the ECU signals, the interface circuit is designed to communicate ECU and designed terminal wirelessly according to the ISO, SAE regulation of communication protocol standard. A microprocessor S3C3410X is used for communicating ECU signals. The embedded system's software is programmed to measure the ECU signals using the ARM compiler and ANCI C based on MicroC/OS kernel to communicate between bluetooth modules using bluetooth stack. The diagnostic system is developed using Visual C++ MFC and protocol stack of bluetooth for Windows environment. The self-diagnosis and sensor output signals of ECU is able to monitor using PC with bluetooth board connected in serial port of PC. The algorithms for measuring the ECU sensor output and self-diagnostic signals are verified to monitor ECU state. At the same time, the information to fix the vehicle's problem can be shown on the developed monitoring software. The possibility for remote measurement of self-diagnosis and sensor signals of ECU adopted KWP2000 in embedded system verified through the developed systems and algorithms.

  • PDF

가스배관망 작동상태 실시간 진단용 인공신경망 기반 모니터링 시스템 (A Monitoring System Based on an Artificial Neural Network for Real-Time Diagnosis on Operating Status of Piping System)

  • 전민규;조경래;이강기;도덕희
    • 대한기계학회논문집B
    • /
    • 제39권2호
    • /
    • pp.199-206
    • /
    • 2015
  • 본 연구에서는 인공신경망을 이용하여 배관이나 배관요소의 작동상태를 예측할 수 있는 진단방법을 제안한다. 입자영상유속계 기술을 이용하여 얻어진 배관의 검사부위의 진동에 의한 이동량을 인공신경망의 학습용으로 사용한다. 측정시스템은 카메라, 조명, 인공신경망이 탑재된 호스트컴퓨터로 구성된다. 구축된 모니터링시스템이 제대로 작동하는지 이미 알고 있는 진동원(2개의 휴대폰)에 대하여 적용하였다. 진동가속도의 최소값, 최대값, 평균값을 인공신경망의 학습에 사용해 본 결과, 평균값이 진동상태의 실시간 모니터링에 적합함을 확인하였다. 구축된 진단시스템은 실제 가스배관의 작동상태에 대하여 모니터링 가능함이 확인되었다.

LNG 펌프 고장 진단 시스템 개발 (Development of Diagnosis System for LNG Pump)

  • 홍성호;이용원;황원걸;기창두;김영배
    • 한국가스학회지
    • /
    • 제2권3호
    • /
    • pp.88-95
    • /
    • 1998
  • 회전기계의 진동해석은 기계의 이상을 미리 판정하여 적절한 유지 보수를 수행하기 위한 지표로 팔용이 가능하다 현재 평택기지에 설치된 고장진단시스템은 LNG펌프의 진동수치가 위험수준에 도달시 기계적 결함부위 진단을 할 수 있다. 본 연구는 Windows NT환경에서 DSP보드를 사용한 자동진단시스템 개발에 대한 것이다. 펌프의 상태진단을 위해 2개의 가속도센서로부터의 속도신호를 해석하고 펌프의 상태에 대한 다양한 그래프를 보여주며 특정 진동값을 일정시간 간격마다 저장하여 펌프의 결함 발생시 운전자가 컴퓨터 모니터에서 전문가 시스템을 활용하여 자동으로 진단하고 경향을 감시함으로써 펌프의 상태를 점검할 수 있다.

  • PDF

가속도 신호의 주파수 분석에 기반한 종이용기 성형기 구동축 고장진단 요소기술 개발 (Development of Fault Diagnosis Technology Based on Spectrum Analysis of Acceleration Signal for Paper Cup Forming Machine)

  • 장재호;하창근;주백석;박준영
    • 한국기계가공학회지
    • /
    • 제15권6호
    • /
    • pp.1-8
    • /
    • 2016
  • As demand for paper cups markedly increases, this has brought about a requirement to develop fast paper cup forming machines. However, the fast manufacturing speed of these machines causes faults to occur more frequently in the final product. To reduce the possibility of producing faulty products, it is necessary to develop technologies to monitor the manufacturing process and diagnose the machine status. In this research, we selected the main driving axis of the forming machine for fault diagnosis. We searched the states of rotational elements related to the driving axis and suggested a fault diagnostic system based on spectrum analysis consisting of a real-time data acquisition device, accelerometers, and a diagnosis algorithm. To evaluate the developed fault diagnostic system, we performed experiments using a test station which resembles the actual paper cup forming machine. As a result, we were able to confirm that the proposed system was sufficiently feasible to diagnose any abnormalities in the operation of the paper cup forming machine.

비선형회귀모델을 이용한 히트펌프시스템의 열교환기 고장에 대한 고장감지 및 진단에 대한 연구 (Fault Detection and Diagnosis (FDD) Using Nonlinear Regression Models for Heat Exchanger Faults in Heat Pump System)

  • 김학수;김민수
    • 대한기계학회논문집B
    • /
    • 제35권11호
    • /
    • pp.1111-1117
    • /
    • 2011
  • 본 연구에서는 비선형회귀모델을 이용한 히트펌프시스템에서의 고장감지 및 진단 알고리즘을 개발하였다. 히트펌프시스템에 발생할 수 있는 다양한 고장요소 중, 열교환기 고장에 대한 연구를 수행하였다. 해석 식을 바탕으로 제작한 모델을 이용하여 총 4가지 작동 모드(무고장, 증발기 고장, 응축기 고장, 응축기와 증발기 고장)에 대한 시뮬레이션을 수행하였다. 고장감지 및 진단 알고리즘을 개발하기 위해 무고장모드에서의 데이터를 바탕으로 각 열교환기의 과열도 또는 과냉도를 예측할 수 있는 비선형회귀모델을 제시하였다. 고장감지 및 진단 알고리즘은 이 비선형회귀모델을 바탕으로 예측한 열교환기에서의 과열도 또는 과냉도 값과 시뮬레이션 값을 비교하여 그 차이의 정도에 따라 각 열교환기의 고장을 감지 및 진단하도록 하였다.