• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.5
• /
• pp.383-392
• /
• 2007

In this paper, we study the prediction of depth and width of a defect in steam generator tube in nuclear power plant using neural network. To this end, we first generate eddy current testing (ECT) signals for 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. In particular, we generate 400 ECT signals for various widths and depths for each defect type by the numerical analysis program based on finite element modeling. From those generated ECT signals, we extract new feature vectors for the prediction of defect size, which include the angle between the two points where the maximum impedance and half the maximum impedance are achieved. Using the extracted feature vector, multi-layer perceptron with one hidden layer is used to predict the size of defects. Through the computer simulation study, it is shown that the proposed method achieves decent prediction performance in terms of maximum error and mean absolute percentage error (MAPE).

• Composites Research
• /
• v.16 no.5
• /
• pp.15-20
• /
• 2003

In this paper, the fracture strength of the surface damaged laminates was predicted by applying the fracture strengths of the unflawed and flawed laminates. For prediction, the theoretical equation about the fracture strength of laminates was simplified applying classical laminate theory and was applied to the surface damaged laminates. Lagace's and Tsai's experimental data were used for verifying the theoretical equation. Moreover, to verify the theoretical prediction, an experiment was performed. Surface unflawed laminate and flawed laminates were fabricated and the experiments were made and these results were compared with theoretical predictions. The specimens' fiber direction was same to the tensile direction and the theoretical predictions and the experimental results were showed good agreement. Therefore, by this equation, the fracture strength of structures made of composites will be able to be predicted when the surface of the structures was damaged.

• Plant Journal
• /
• v.14 no.2
• /
• pp.45-50
• /
• 2018

Nuclear safety law's amendment caused many problems to use radiography testing(RT). Phased array ultrasonic testing(PAUT) was adapted instead of RT for NDE of welding points in boiler tubes these days. Unfortunately, PAUT doesn't give us the discrimination characteristics about flaws distinction and flaws size clearly. In this thesis, the distinction characteristics of flaw types and the detection characteristics of flaw size using PAUT of welding points in boiler tubes were analyzed. It was concluded that PAUT can distinguish between planar flaws and rounded flaws, but it is hard to tell apart the types of flaw respectively. We paid attention to the discrimination of flaws size because PAUT tends to underestimate the flaw size of porosity and underestimate or overestimate the flaw size of porosity.

• Plant Journal
• /
• v.11 no.2
• /
• pp.39-44
• /
• 2015

According to a research that is based on a previous study, But in a different way, This study shows fault diagnosis of Induction motor bearing which runs in coal-fired power plant industries on Desulfurization absorber agitator using Spectrum analysis of Stator Current and visual inspection. As a result of harmonic content analysis of stator current spectrum, It was possible to detect ball and outer race fault frequency. The comparison in the context of this experiment proves that the amplitude of faulty frequency is increased in three times at a fault in ball and in outer race. Spectrum analysis of stator current can be used to detect the presence of a fault condition as well as experiment in faulty bearings, besides early fault detection in bearings can prevent unexpected power generation loss and emergency maintenance cost.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.3
• /
• pp.238-247
• /
• 2007

Genetic Algorithms(GA) which searches optimum solution using natural selection and the law of heredity has been applied to learning algorithms in order to estimate performance deterioration of the aircraft gas turbine engine. The compressor, gas generator turbine and power turbine are considered for engine performance deterioration and estimation for performance deterioration of a single component at design point was conducted. As a result of that, defect diagnostics has been conducted. The input criteria for the genetic algorithm to guarantee the high stability and reliability was discussed as increasing learning data sets. As a result, the accuracy of defect estimation and diagnostics were verified with its RMS error within 3%.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1
• /
• pp.5-9
• /
• 1997

If small cracks in stud bolts are not detected early enough, they grow rapidly and cause total fracture. It is difficult to detect, prior to failure, flaws such as stress-corrosion cracking in thread roots and corrosion wastages using conventional ultrasonic testing methods during inservice inspection. This study show a method of detecting a small crack by digital signal processing. When ultrasonic beams travels into threads in parallel way, the echoes from each successive threads has almost the same intervals between any two signals. We can estimate the next thread signal based on previous thread signal by the predictive distance. The optimized operator is used to remove the predicted successive thread signals so that a small crack signal can be detected.

• Annual Conference of KIPS
• /
• 2001.10a
• /
• pp.397-400
• /
• 2001

본 논문에서는 운전 단계중의 상용소프트웨어 성장활용을 설명한 수 있고 또 현장 고장 데이타로부터 활용성장을 예측하는데 관계되는 인자를 결합할 수 있는 새로운 모델을 개발한다. 이 모델은 상용 소프트웨어의 실제 황용이 시간의 멱수 함수로 나타난다는 가정으로부터 생기는 웨이블 분포에 근거한다. 선형신뢰도모델은 잔여결함의 평균크기와 작업량이 일정하고 겉보기 결함밀도가 실제 결함밀도와 동일하다는 가정 하에 유도된다. 기하학적모델은 결함을 수정함에 따라 평균결합크기가 기하학적으로 감소한다는 가정에 있어서 파이가 있다. 한편, Rayleigh모델은 잔여 결함의 평균크기가 시간에 따라 선형적으로 감소한다는 가정에 있어서 차이가 있다. 본 논문에서는 소프트웨어의 신뢰도 요인의 거동을 가정하여 이러한 다양성을 수용하기 위한 모델링을 하였다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.1
• /
• pp.63-70
• /
• 2010

In this paper, we study the structure of neural network for predicting defect size of steam generator tube. After extracting the features from the eddy current testing (ECT) signals, multi-layer neural networks are used to predict the defect size. In order to maximize the prediction performance for the defect size, we should carefully choose the structure of neural networks, especially the number of neurons in the hidden layer. In this paper, it is shown that, for the prediction of defect size, the number of neurons in the hidden layer can be efficiently determined by using cross-validation.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.351-354
• /
• 2008

소프트웨어 프로젝트를 진행할 때, 소프트웨어 개발에 투입할 노력의 정확한 추정과 더불어 소프트웨어 생명주기 단계별 적정한 개발노력을 투입하는 것은 프로젝트 성공을 위해 필요한 요소 중 하나이다. 조직의 과거 데이터를 활용한 기존의 개발노력 분배 방식은 단계별로 발생되는 결함의 양에 따라 개발노력의 투입량 변동이 발생될 수 있다. 본 연구에서는 CMMI 조직 프로세스성과(Organization Process Performance) 프로세스 기반의 결함 예측을 이용한 개발노력 분배 성과모델을 제시하고, 제시한 성과모델의 예측값과 프로젝트 수행 결과 값의 비교를 통해서 제시한 성과모델의 유효성 및 결함과 개발노력 분배의 연관성에 대해서 검증 하고자 한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.1-6
• /
• 2013

For predicting defect-prone module in software, SVM classifier showed good performance in a previous research. But there are disadvantages that SVM parameter should be chosen differently for every kernel, and algorithm should be performed iteratively for predict results of changed parameter. Therefore, we find these parameters using Genetic Algorithm and compare with result of classification by Backpropagation Algorithm. As a result, the performance of GA-SVM model is better.