• The Transactions of the Korean Institute of Power Electronics
• /
• v.16 no.5
• /
• pp.457-465
• /
• 2011

The fault analysis and detecting algorithm for a 3 phase diode rectifier is proposed. The 3 phase dioderectifier is used for the AC power rectifier of the PWM inverter. The input power or diode faults cause theripples of the DC voltage, degradation of the control performance and life shortening of the DC link capacitor.In this paper, the ripple of the DC voltage is mathematically analyzed for the earth fault of input power andopen circuit fault of the diode, respectively. The fault detection and type of fault can be obtained by comparingthe average DC voltage and the instant DC voltage which is sampled with 6 times of grid frequency. Theproposed method can be easily applicable and doesn't require additional circuit. The experimental and simulationresults are presented to verify the validity of the proposed method.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.451-452
• /
• 2011

최근 들어 전력공급의 신뢰성 강화를 위해 고장을 미리 진단할 수 있는 기술이 요구되고 있다. 전력IT 국책과제로 개발된 전력설비의 감시진단장치 중 송전선로 감시를 위한 센서 및 센서네트워크를 제주 구좌읍의 스마트그리드 실증단지내 기기설치 설치가 진행중이다. 실증사업 1단계로 SG실증단지의 송전선로를 활용하여 성과물의 성능검증하기 위해 송전선로 감시시스템을 현장에 적용하여 성능을 확인한 실증사례 및 문제점에 대한 개선사항을 소개하고 향후 2단계로 추가 실증 방향 및 송전선로용 센서를 활용한 시스템 운영 전망을 살펴보고자 한다.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.525-526
• /
• 2016

전기자동차 (EV)에서 구동용 모터의 토크 제어를 위한 인버터에는 제어 연산 및 고장 진단 기능을 수행하기 위한 MCU가 있으며, MCU는 상위 제어기 차량 제어 유닛 (VCU)에게 현재 모터 및 인버터의 상태를 주기적으로 전달하고, 현재 차량 주행에 적합한 토크 지령을 받아 토크 제어를 수행하게 된다. 이를 위해 MCU는 전류, 전압 및 위치 센서의 값을 읽어 제어를 수행하게 되며, 제어의 결과 값으로 pulse width modulation (PWM)을 생성하여 이를 통해 모터에 전압을 공급하게 된다. 즉 차량의 구동에 있어 PWM 신호는 가장 중요한 부분이다. 하지만 생산 불량 또는 진동에 의한 납땜 불량 또는 MCU 전원 고장 등으로 MCU에 고장이 발생하게 되면 이상 PWM을 생성하게 되고 정상적인 토크 제어가 불가능해진다. 이때 안전하게 EV를 정지 시키는 알고리즘이 필요하게 되며, 이를 수행 할 supervisor control unit (SCU)가 인버터 컨트롤 보드에 추가되어야 한다. 본 논문에서는 고속으로 주행하던 차량에서 메인 MCU가 고장 날 경우에 안전하게 EV를 정차시키는 방법에 대해 다루었다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.9
• /
• pp.835-842
• /
• 2016

In Korea, urban railway cars are typically maintained using the strategy of predictive maintenance. In an effort to overcome the limitations of the existing strategy, there is increased interest in adopting the condition-based maintenance strategy. In this study, a novel method is proposed to detect faults in the solenoid valves of the braking system in urban railway vehicles. We determined the key component (i.e., solenoid valve) that leads to braking system faults through the analysis of failure modes, effects, and criticality. Then, an equivalent circuit model was developed with the compensation of the temperature effect on solenoid coils. Finally, we presented how to detect faults with the equivalent circuit model and current signal measurements. To demonstrate the performance of the proposed method, we conducted a case study using real solenoid valves taken from urban railway vehicles. In summary, it was shown that the proposed method can be effective to detect faults in solenoid valves. We anticipate the outcome from this study can help secure the safety and reliability of urban railway vehicles.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.242-250
• /
• 2019

In this paper, we propose a method to predict the failure of industrial robot using Seq2Seq (Sequence to Sequence) model, which is a model for transforming time series data among Artificial Neural Network models. The proposed method uses the data of the joint current and angular value, which can be measured by the robot itself, without additional sensor for fault diagnosis. After preprocessing the measured data for the model to learn, the Seq2Seq model was trained to convert the current to angle. Abnormal degree for fault diagnosis uses RMSE (Root Mean Squared Error) during unit time between predicted angle and actual angle. The performance evaluation of the proposed method was performed using the test data measured under different conditions of normal and defective condition of the robot. When the Abnormal degree exceed the threshold, it was classified as a fault, and the accuracy of the fault diagnosis was 96.67% from the experiment. The proposed method has the merit that it can perform fault prediction without additional sensor, and it has been confirmed from the experiment that high diagnostic performance and efficiency are available without requiring deep expert knowledge of the robot.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.504-509
• /
• 1995

컴퓨터에 의한 생산시스템의 통합체계화와 온-라인화에 따라 자동화된 설비진단 방법이 요구되어지고 있다. 이에 따라 기계설비에 각종 센서를 부착하여 실시간으로 수집된 출력신호를 이용하여 기계설비를 온-라인으로 감시하는 여러가지 기법들이 제시되고 있다. 본 연구에서는 진동센서로부터의 신호를 radial 함수에 근거한 다단계 뉴럴 네트워크(Neural Network)로 모형화하여 기계설비 상태를 감시하는 방법을 제시한다. 또한 다단계 모델링 분석을 통하여 신호를 예측하고 설비고장 원인을 분류하며, 다른 모형과의 비교를 통하여 효율성 평가와 최적 단계수를 결정하였다. 온라인 학습 알고리즘은 recursive least squares와 clustering 방법을 이용한다.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.8
• /
• pp.351-356
• /
• 2014

Typical trouble patterns in solar thermal systems include working fluid leakage and freezing other than breakdown of pump. A fluid sensor for measuring electric resistance of fluid was developed and installed at the top of the collector piping in order to check the fault of solar system. Working fluid level in the pipe was determined by measuring electric resistance from a fluid sensor. On the base of this, it was confirmed that the fluid sensor diagnoses leakage of fluid. Electric resistance of propylene glycol aqueous solution was measured in the range of $0{\sim}70^{\circ}C$ and 0~40% of concentration. The response surface analysis was performed by using a central composite design, and the regression equation was derived from the relationship between electric resistance, temperature, and concentration. Through the experiment in a real solar system, we can estimate a concentration of working fluid when a pump is not operating and predict a possibility of freezing. Finally, an effective algorithm for trouble shooting was proposed to operate and maintain the solar system.

• Journal of Auto-vehicle Safety Association
• /
• v.9 no.4
• /
• pp.32-37
• /
• 2017

For automated vehicles, the integrity and fault tolerance of environment perception sensor have been an important issue. This paper presents radar, vision, lidar(laser radar) fusion-based fault detection algorithm for autonomous vehicles. In this paper, characteristics of each sensor are shown. And the error of states of moving targets estimated by each sensor is analyzed to present the method to detect fault of environment sensors by characteristic of this error. Each estimation of moving targets isperformed by EKF/IMM method. To guarantee the reliability of fault detection algorithm of environment sensor, various driving data in several types of road is analyzed.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.214-216
• /
• 2004

최근 들어 전력 공급의 신뢰성 강화를 위해 변전설비 고장을 미리 진단할 수 있는 예방진단기술이 절실히 요구되고 있으며, 한국전력공사 및 기타 수요자 층에서 예방진단기술 도입을 추진하고 있다. 또한 센서 기술과 디지털 기술, 통신 및 컴퓨터 기술의 발전과 더불어 실시 간으로 변전설비를 감시할 수 있는 온라인 예방진단이 가능하게 되었다. 이에 본 논문에서는 변전소용 온라인 예방진단 시스템을 현장에 적용한 사례를 소개 하고자 한다.