• 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.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.2
• /
• pp.27-32
• /
• 2005

This paper presents the optimization of expanding velocity for tube expanding process in the manufacturing of a heat exchanger. In specific, the expanding velocity has a great influence on the performance of a heat exchanger because it is a key variable determining the quantity of tube expending at assembly stage as well as a key Parameter determining overall production rate. The simulation showed that the genetic algorithm used in this paper resulted in the optimal tube expanding velocity by performing the following series of iteration; the generation of arbitrary population for tube expanding parameters, consequently the generation of tube expanding velocities, the evaluation of tube expanding quantity using the pre-trained data of plastic deformation by means of a neural network and finally the generation of next population using a penalty faction and a Roulette wheel method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.10
• /
• pp.1445-1453
• /
• 2017

In this paper, we propose a fault detection model based on multi-layer neural network using data mining technique for faults due to boiler tube leakage in a thermal power plant. Major measurement data related to faults are analyzed using statistical methods. Based on the analysis results, the number of input data of the proposed fault detection model is simplified. Then, each input data is clustering with normal data and fault data by applying K-Means algorithm, which is one of the data mining techniques. fault data were trained by the neural network and tested fault detection for boiler tube leakage fault.

• Proceedings of the Korean Society of Embryo Transfer Conference
• /
• 2004.10a
• /
• pp.88-88
• /
• 2004

• Journal of Veterinary Clinics
• /
• v.26 no.5
• /
• pp.467-471
• /
• 2009

This report describes Neural Tube Defects (NTDs) with Abdominal Wall Defects (AWDs) on the sibling of Yorkshire terriers. The NTDs and AWDs are rare serious congenital defects. The NTDs are neurulation abnormality that results from to failed transformation of the neurual tube by the incomplete closure of the embryonic neural plate. These dysraphic states range form mild to severe according to developmental malformation that include fusion defects of skull (crania bifida; CB) and fusion defects of vertebrae (spina bifida; SB). The AWDs are genetic defects that results from to failed formation of abdominal wall and cavity. These dysraphic states are omphalocele and gastroschisis. The 12-month dam was delivered by caesarian section and 4 littermate had obvious malformations. One male dead stillbirth fetus (L1) was revealed the extruded abdominal viscera, omphalocele. One female fetus (L2) was died within 1 hour after birth with defects of abdominal muscle upper umbilicus, gastroschisis. 3rd fetus (L3) was died within 36 hours after parturition and revealed a copious dermal and vertebral defects on the midline thorax, upper SB asperta. 4th fetus (L4) is still growing well now at 6 months but at the 2 week age, appears hairy nevus on the frontal cranium and dorsal thoracic portion. The radiograph of L1 and L2 are shown decrease bony density of calvarium and L3 was shown defect of spinose processes of the T9-T13. On our knowledge, this is first report of the SB and CB in Yorkshire terrier. And also sibling of NTDs with AWDs that has not previously been reported in the dog.

• Steel and Composite Structures
• /
• v.35 no.3
• /
• pp.415-437
• /
• 2020

Circular concrete filled steel tube (CFST) columns have an advantage over all other sections when they are used in compression members. This paper proposes a new approach for deriving a new empirical equation to predict the axial compressive capacity of circular CFST columns using the Artificial Neural Network (ANN). The developed ANN model uses 5 input parameters that include the diameter of circular steel tube, the length of the column, the thickness of steel tube, the steel yield strength and the compressive strength of concrete. The only output parameter is the axial compressive capacity. Training and testing the developed ANN model was carried out using 219 available sets of data collected from the experimental results in the literature. An empirical equation is then proposed as an important result of this study, which is practically used to predict the axial compressive capacity of a circular CFST column. To evaluate the performance of the developed ANN model and the proposed equation, the predicted results are compared with those of the empirical equations stated in the current design codes and other models. It is shown that the proposed equation can predict the axial compressive capacity of circular CFST columns more accurately than other methods. This is confirmed by the high accuracy of a large number of existing test results. Finally, the parametric study result is analyzed for the proposed ANN equation to consider the effect of the input parameters on axial compressive strength.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.9
• /
• pp.73-79
• /
• 2012

In this paper, we study on how to determine the number of hidden layer neurons in neural network for predicting defect size of steam generator tube. It was reported in the literature that the number of hidden layer neurons can be efficiently determined with the help of cross-validation. Although the cross-validation provides decent estimation performance in most cases, the performance depends on the selection of validation set and rather poor performance may be led to in some cases. In order to avoid such a problem, we propose to use multifold cross-validation. Through the simulation study, it is shown that the estimation performance of defect width (defect depth, respectively) attains 94% (99.4%, respectively) of the best performance achievable among the considered neuron numbers.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.7
• /
• pp.1224-1230
• /
• 2007

In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing (ECT). We consider 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.

• Steel and Composite Structures
• /
• v.33 no.2
• /
• pp.181-194
• /
• 2019

This paper presents an efficient approach to generate a new empirical formula to predict the axial compression capacity (ACC) of circular concrete-filled tube (CCFT) columns using the artificial neural network (ANN). A total of 258 test results extracted from the literature were used to develop the ANN models. The ANN model having the highest correlation coefficient (R) and the lowest mean square error (MSE) was determined as the best model. Stability analysis, sensitivity analysis, and a parametric study were carried out to estimate the stability of the ANN model and to investigate the main contributing factors on the ACC of CCFT columns. Stability analysis revealed that the ANN model was more stable than several existing formulae. Whereas, the sensitivity analysis and parametric study showed that the outer diameter of the steel tube was the most sensitive parameter. Additionally, using the validated ANN model, a new empirical formula was derived for predicting the ACC of CCFT columns. Obviously, a higher accuracy of the proposed empirical formula was achieved compared to the existing formulae.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.