• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.11
• /
• pp.1009-1017
• /
• 2010

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying various techniques such as signal processing and pattern recognition. Recently, fault diagnosis systems using artificial neural network have been proposed. For effective fault diagnosis, this paper used MLP(multi-layer perceptron) network which is widely used in pattern classification. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes the decision method of the proper feature vectors about each fault signal for neural-network-based fault diagnosis system. We applied LPC coefficients, maximum magnitudes of each spectral section in FFT and RMS(root mean square) and variance of wavelet coefficients as feature vectors and selected appropriate feature vectors as comparing error ratios of fault diagnosis for sound, vibration and current fault signals. From experiment results, LPC coefficients and maximum magnitudes of each spectral section showed 100 % diagnosis ratios for each fault and the method using wavelet coefficients had noise-robust characteristic.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1668-1674
• /
• 2011

Door Inside Lamp of railway rolling stock is installed on interior of the side doors and illuminated at door opening and closing, isolation and fault. So drivers or passengers can notice the door status visually. In the past, a single color or Bi-color LED Lamps have been using and one ~ multiple lamp was used to implement the feature according to client's requirements. (Example: Total of between 2 and 4 lamps are required for the Warning / Emergency operation / Isolation / Fault.) However these design is not easy to apply if there is the mounting space restrictions and the problems such as rising costs can be caused. In addition, it has vulnerability from point of view aesthetic aspects. Therefore the lamp type has been required that has small size and number of colors in order to resolve these problems. Recently multi LED type door status indication lamp have been developed that can meet the requirements and this lamp has been applied in many railway projects. In this study, I'll introduce the general characteristics and mechanical & electrical characteristics of multi LED type door status indication lamp to help development of this kinds of lamp.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1466-1472
• /
• 2011

Door Inside Lamp of railway rolling stock is installed on interior of the side doors and illuminated at door opening and closing, isolation and fault. So drivers or passengers can notice the door status visually. In the past, a single color or Bi-color LED Lamps have been using and one ~ multiple lamp was used to implement the feature according to client's requirements. (Example: Total of between 2 and 4 lamps are required for the Warning / Emergency operation / Isolation / Fault.) However these design is not easy to apply if there is the mounting space restrictions and the problems such as rising costs can be caused. In addition, it has vulnerability from point of view aesthetic aspects. Therefore the lamp type has been required that has small size and number of colors in order to resolve these problems. Recently multi LED type door status indication lamp have been developed that can meet the requirements and this lamp has been applied in many railway projects. In this study, I'll introduce the general characteristics and mechanical & electrical characteristics of multi LED type door status indication lamp to help development of this kinds of lamp.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2203-2206
• /
• 2005

A load flow and short circuit fault simulation of AC electrified railway distribution systems is presented with DIgSILENT PowerFactory software. Load flow of electrified railways distribution system with concerning multi train lines and dynamic characteristics of train load is studied for different time laps. The dynamic characteristics of train load in starting and braking conditions with different starting and stopping times and its moving positions makes the load flow complicated so there is a great need in studying the effects of electrified railways on load flow. Short circuit fault transients is also studied and simulated for both power system or traction distribution system and their effects on the operation of the train sets is investigated.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.790-795
• /
• 1994

This paper describes multiple fault diagnosis method in complex system with hierarchical structure. Complex system is divided into subsystem, item, component. For diagnosing this hierarchical complex system, it is necessary to implement special neural network. We introducd to Hierarchical Artificial Neural Network(HANN) for this purpose. HANN consists of four level neural network, first level for symptom classification, second level for item fault diagnosis, third level for component symptom classification,forth level for component fault diagnosis. Each network is multi layer perceptron with 7 inputs, 30 hidden node and 7 outputs trainined by backpropagation. UNIX IPC(Inter Process Communication) is used for implementing HANN with multitasking and message transfer between processes in SUN workstation. We tested HANN in reactor system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10d
• /
• pp.690-694
• /
• 2006

동적인 이동 네트워크는 다중의 무선 Ad-hoc 네트워크들로 구성된 독립적인 WPAN(Wireless Personal Network)이 모인 이동 네트워크의 한 종류이다. 휴대폰과 같은 모바일 장치들이 동적인 이동 네트워크에서 모바일 라우터로 동작하기 때문에 트래픽 과부하, 네트워크 신뢰도, 에너지 소모율 등의 네크워크 fail과 관련된 문제점 들이 제시된다. 따라서 동적인 이동 네트워크에서 fault tolerant 메커니즘은 필수적인 이슈가 될 것이다. 본 논문에서는 빠른 경로 변경 메커니즘과 추가적인 모바일 라우터 선정 메커니즘을 이용하여 향상된 fault tolerant 메커니즘을 제시한다. 최종적으로 모의실험을 통해 에너지 소모율과 패킷 손실 측면에서의 효율성을 보여줄 것이다.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2228-2230
• /
• 2002

The research presented in this paper focuses on a method for the detection of High Impedance Fault(HIF). The method will use the Lifting and neural network system. HIF on the multi-grounded three-phase four-wires primary distribution power system cannot be detected effectively by existing over current sensing devices. These paper describes the application of lifting scheme to the various HIF data. These data were measured in actual 22.9kV distribution system. Wavelet transform analysis gives the frequency and time-scale information. The neural network system as a fault detector was trained to discriminate HIF from the normal status by a gradient descent method. The proposed method performed very well by proving the right state when it was applied staged fault data and normal load mimics HIF, such as arc-welder.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1015-1017
• /
• 1997

A high impedance fault on the multi-grounded three-phase four-wire distribution system can not be detected by conventional overcurrent sensing devices. In this paper, the neural network is used to detect high impedance faults. The proposed algorithm using back - propagation neural network is demonstrated by simulation with the staged fault test data. The harmonic components of current and the phase of voltage are used as the inputs of neural network. Results of the simulation can be used as a reference for the development of a high impedance fault detector.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.1
• /
• pp.10-19
• /
• 1990

A fault tolerant control system, in which a digital back-up controller system is added on the existing analog control system, is developed for enhancing reliability of boiler control system in power plant. The digital back-up controller system(DBCS) has a multi-processor structure with capabilities of fault diagnosis, back-up control, self test, and graphic monitoring. Specifically, switching mechanism composed of expandable modules is designed so that back-up controller takes over any faulty control loops and the number of back-up control loops is determined as that of simultaneous faults. A process simulator that simulates the boiler analog control system is developed for safety test and performance evaluation prior to real plant application. DBCS is installed at the Ulsan thermal power plant, and fault tolerant control performance is assured under the faults that some controller modules are pulled out.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.14 no.7
• /
• pp.560-566
• /
• 2002

The fault detection and diagnosis technology may be applied in order to decrease the energy consumption and the maintenance cost of the air-conditioning system. In this study, two different types of faults in the air-conditioning system, such as the condenser fouling and the evaporator fan slowdown, were considered. The neural network algorithm combined with data preprocessor was developed and applied to detect the faults of the real system. Test results show that this method is very effective to detect the faults in the air-conditioning system. Therefore, this developed method can be used for the development of the air-conditioner fault detection system.