• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.280-285
• /
• 2004

In this study, we made a comparative study of backpropagation neural network and probabilistic neural network and bayesian classifier and perceptron as shape recognition algorithm of welding flaws. For this purpose, variables are applied the same to four algorithms. Here, feature variable is composed of time domain signal itself and frequency domain signal itself. Through this process, we comfirmed advantages/disadvantages of four algorithms and identified application methods of four algorithms.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.6
• /
• pp.604-608
• /
• 2008

The TFT-LCD image allows non-uniform illumination variation and that is one of main difficulties of finding defect region. The SQI (self quotient image) has the HPF (high pass filter) shape and is used to reduce low frequency-lightness component. In this paper, we proposed the TFT-LCD defect-enhancement algorithm using characteristics of the SQI, that is the SQI has low-frequency flattening effect and maintains local variation. The proposed method has superior flattening effect and defect-enhancement effect compared with previous the TFT-LCD image preprocessing.

• Journal of the Korean Society for Railway
• /
• v.10 no.6
• /
• pp.730-734
• /
• 2007

In this paper, we suggest the criticality of Hidden Failure with regard to the design of watch dog timer, used to detect HALT on railway signaling embedded controller, via FMEA and FTA. Hidden Failure means reliability and safety degradation of the system due to any failure occurred on elements added for fault tolerance. In this paper, therefore, we design vital watch dog timer to prevent the system from operating in low SIL conditions and assess the safety of circuit on failure occurrence to demonstrate that safety degradation problems owing to existing design are supplemented.

• Proceedings of the KIEE Conference
• /
• 2004.07c
• /
• pp.1894-1896
• /
• 2004

전력을 공급하는 변전소 등의 주요 위치에 시설되는 GIS는 사고를 미연에 방지하기 위해 여러 가지 진단방법을 이용하여 이상여부를 판별한다. 이러한 진단 방법 중 현재 국내외적으로 각광을 받고 있는 방법이 UHF센서를 이용한 부분방전 검출방법이다. 따라서, 본 논문에서는 부분방전을 발생시키기 위한 인공결함을 제작하여 GIS 내부에 삽입하고 부분 방전을 발생시켰으며, 이때 발생된 부분방전 신호를 UHF센서를 이용하여 검출하였다. 검출된 부분방전 신호는 phi-f-q 방법으로 분석 하였으며, 그 결과 발생된 파라메터를 인공신경망에 적용하여 각각의 결함에 따른 인식률에 대하여 알아보았다.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.103-111
• /
• 2002

In this study, the natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.304-309
• /
• 2003

In this study, natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.3
• /
• pp.39-44
• /
• 2006

In this study, we nodestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of welding flasw. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from welding flaws in time domain. Through this process, we confirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.

• Proceedings of the KIEE Conference
• /
• 2003.07c
• /
• pp.1812-1814
• /
• 2003

$SF_6$ 가스로 절연된 GIS(Gas Insulation Switchgears)는 매우 신뢰성이 높은 것으로 평가되어왔다. 그러나 GIS 내부에서 발생하는 결함에 대하여 완전하게 배제시키지 못하고 있으며, 이러한 부분방전 활동에 의한 대부분의 결함들이 GIS의 사고를 이끈다고 알려져 있다[1]. 따라서, GIS 내부에서 발생하는 부분방전 현상의 위치와 측정은 1940년대 초반부터 관심을 가져왔으며, 현재에는 부분방전 형태의 패턴이 사용된 부분방전 검출회로 및 신호의 전파와는 무관하다는 것을 알아낸 시점에 이르렀다. 이에 따라, 본 논문에서는 $SF_6$ 가스가 봉입된 GIS 내부에서 발생하는 부분방전 형태의 패턴인식을 위한 방법으로 NN(Neural Network)의 알고리즘 중 BP(Back-Propagation) 알고리즘을 이용하였다.

• The magazine of the Korean Society for Advanced Composite Structures
• /
• v.6 no.3
• /
• pp.17-23
• /
• 2015

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.3
• /
• pp.247-252
• /
• 2013

In this paper, a microwave tag system of a frequency-scanning type is proposed with multi-resonators using defected ground structures. While a conventional chip-based RFID stores time-sequential codes, the proposed type achieves pure passive tags by using multi-resonant bits over a frequency range. Moreover, the resonators of the spiral defected ground structures implemented on the back side of transmission lines have advantages of the excellent bandstop characteristics as well as the bit-error avoidance by the re-radiation on normal resonators. The proposed microwave tag is designed with UWB antennas at 3~7 GHz. From the experimental results in an anechoic chamber, it has been verified of the excellent recognitions for various 5-bits identification codes.