• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.4
• /
• pp.331-338
• /
• 1992

The application of Connectionist expert system using neural network to fault diagnosis of power system is presented and compared with rule-based expert system. Also, the merits of Connectionist model using neural network is presented. In this paper, the neural network for fault diagnosis is hierarchically composed by 3 neural network classes. The whole power system is divided into subsystems, the neural networks (Class II) which take charge of each subsystem and the neural network (Class III) which connects subsystems are composed. Every section of power system is classified into one of the typical sections which can be applied with same diagnosis rules, as line-section, bus-section, transformer-section. For each typical section, only one neural network (Class I) is composed. As the proposed model has hierarchical structure, the great reduction of learning structure is achieved. With parallel distributed processing, we show the possibility of on-line fault diagnosis.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.228-232
• /
• 1993

This paper describes a on-line monitoring and fault diagnosis system designed for the automation of a medium-size concrete plant. The system is based on the structure of a hardware system of data acquisition and a personal computer. Simulation results are presented to illustrate the system operation. It applies the preconstructed rules to the plant data for the diagnosis of weighing processes.

• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.506-508
• /
• 2007

In this paper, the induction motor bearing fault diagnosis system using current signals which are measured by over-sampling method is presented. In the case of inverter fed motor drive unlike line-driven motor drive, that make a lot of noise which can cause a wrong fault signals because of PWM(pulse width modulation) voltage. So, the current signals for fault diagnosis need very precise and high resolution information, which means this system demand additional hardware such as low pass filter, high resolution ADC system and so on to use fault diagnosis system. Therefore, the proposed over-sampling method is expected to contribute to low cost fault diagnosis system even though previous inverter fed motor drive without any additional hardware. In order to confirm the presented algorithms, various experiments for bearing faults are tested and the line current spectrum of each faulty situation using park transformation is compared with a FFT results.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.963-968
• /
• 2003

The continuous process systems usually consists of various components: driven rollers. idle rolls, load-cell and so on. Even a simple fault in a single component in the line may cause a catastrophic damage on the final products. Therefore it is absolutely necessary to diagnosis the components of the continuous systems. In this paper, an adaptive eccentricity compensation method is presented. And a new diagnosis method for transverse roll shape defects on rolling process is developed. The new method was induced from analyzing the rolling mechanism by using rolling force model, tension model, Hitchcock's equation, and measured delivery thickness of materials etc. Computer simulation results also show that the proposed diagnosis methods is very effective in the diagnosis of 3-D roll shape

• Journal of the Korea Safety Management & Science
• /
• v.12 no.2
• /
• pp.65-73
• /
• 2010

In an automated industry PLC plays a central role to control the manufacturing system. Therefore, fault free operation of PLC controlled manufacturing system is essential in order to maximize a firm's productivity. On the contrary, distributed nature of manufacturing system and growing complexity of the PLC programs presented a challenging task of designing a rapid fault finding system for an uninterrupted process operation. Hence, designing an intelligent monitoring, and diagnosis system is needed for smooth functioning of the operation process. In this paper, we propose a method to continuously acquire a stream of PLC signal data from the normal operational PLC-based manufacturing system and to generate diagnosis model from the observed PLC signal data. Consequently, the generated diagnosis model is used for distinguish the possible abnormalities of manufacturing system. To verify the proposed method, we provided a suitable case study of an assembly line.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.8
• /
• pp.787-795
• /
• 2001

An experimentation on the on-line fault detection and diagnosis(FDD) system has been performed with HVAC system in he experimental building constructed inside the large scale environmental chamber. Personal computer with a home-made FDD program by pattern recognition method utilizing artificial neural network was connected on-line via Ether-net TCP/IP to the supervisory control server for HVAC system. The FDD program monitored the HVAC system by 1 minuted interval. The results showed that he FDD program detected the sudden or abrupt faults such s those in fans, sensors and heater, etc.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.616-619
• /
• 1995

This paper describes developement of on-line system for vibration signal analysis. In the power system, the main reason of transformer fault is due to a large amount of current by a short-circuit and a ground-fault. The electromagnetic force caused by fault-current deforms transformer windings and results in vibration pattern change. Therefore if the continuous on-line vibration monitoring on transformer is performed, an incipient failure can be detected. The developed system is composed of data acquisition devices, user interface program, signal processing program, diagnosis and trend analysis program, self diagnosis program and communication program.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.1
• /
• pp.138-145
• /
• 2000

This paper presents a robust fault diagnosis and fault tolerant control method for the control systems in closed-loop affected by unknown inputs or disturbances. The fault diagnostic scheme is based on the disturbance-decoupled state estimation using a 2-stage state observer for state, actuator bias and sensor bias. The estimated bias show the occurrence time, location and type of the faults directly. The estimated state is used for state feedback to achieve fault tolerant control against the faults. Simulation results show that the method has definite fault tolerant ability against actuator and sensor faults, moreover, the faults can be detected on-line, isolated and estimated simultaneously.

• Journal of the Korean Society of Safety
• /
• v.12 no.1
• /
• pp.37-43
• /
• 1997

There are two kinds of ground fault diagonosis system(GFD), which are for AC and DC power line. The ground fault current of a DC power line Is, first, analyzed for a description of a GFD system for DC power line and then the construction method of the GFD system, which could be processed and analyzed a ground fault current, are explained. Main functions of the system are that the detected ground fault current could be converted to the line insulation resistance by a program and saved in the system memory continuously. Finally a DC power line insulation safety could be decide by a change of the saved Insulation resistance for a given time. This system can detect the ground fault resistance to 100㏀.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.56 no.4
• /
• pp.168-172
• /
• 2007

The global environment deteriorating which originated from using of fossil fuel is an serious problem for human being to solve. The photovoltaic energy has been considered as a solution. In advanced countries, research and development for photovoltaic(PV) energy system is carrying on. Once installed, a PV array requires maintenance and fault diagnosis other than an occasional cleaning. In this research, the proposed system monitor and diagnosis the output of PV array by on-line for maintenance of PV power plant. The validity of proposed system is verified using sample system.