• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.792-795
• /
• 1996

In TIG welding of pipe, back bead size monitoring is important for weld quality assurance. Many researches have been performed on estimation of the back bead size by heat conduction analysis. However numerical conduction model based on many uncertain thermal parameters causes remarkable errors and thermomechanical phenomena in molten pool can not be considered. In this paper, filler wire feeding force in addition to weld current, wire feedrate, torch travel speed and orbital position angle is monitored to estimate back bead size in orbital TIG welding. Monitored welding process variables are fed into an artificial neural network estimator which has been trained with the monitored process variables (input patterns) and actual back bead size (output patterns). Experimental verification of the proposed estimation method was performed. The predicted results are in a good agreement with the actual back bead shape. The results are quite promising in that estimation of invisible back bead shape can be achieved by analyzing the welding parameters without any conventional NDT of welds.

• Nuclear Engineering and Technology
• /
• v.47 no.5
• /
• pp.624-632
• /
• 2015

A self-diagnostic monitoring system is a system that has the ability to measure various physical quantities such as temperature, pressure, or acceleration from sensors scattered over a mechanical system such as a power plant, in order to monitor its various states, and to make a decision about its health status. We have developed a self-diagnostic monitoring system for an air-operated valve system to be used in a nuclear power plant. In this study, we have tried to improve the self-diagnostic monitoring system to increase its reliability. We have implemented three different machine learning algorithms, i.e., logistic regression, an artificial neural network, and a support vector machine. After each algorithm performs the decision process independently, the decision-making module collects these individual decisions and makes a final decision using a majority vote scheme. With this, we performed some simulations and presented some of its results. The contribution of this study is that, by employing more robust and stable algorithms, each of the algorithms performs the recognition task more accurately. Moreover, by integrating these results and employing the majority vote scheme, we can make a definite decision, which makes the self-diagnostic monitoring system more reliable.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.393-404
• /
• 2012

After the Fukushima nuclear accident in 2011, there has been increasing concern regarding severe accidents in nuclear facilities. Severe accident scenarios are difficult for operators to monitor and identify. Therefore, accurate prediction of a severe accident is important in order to manage it appropriately in the unfavorable conditions. In this study, artificial intelligence (AI) techniques, such as support vector classification (SVC), probabilistic neural network (PNN), group method of data handling (GMDH), and fuzzy neural network (FNN), were used to monitor the major transient scenarios of a severe accident caused by three different initiating events, the hot-leg loss of coolant accident (LOCA), the cold-leg LOCA, and the steam generator tube rupture in pressurized water reactors (PWRs). The SVC and PNN models were used for the event classification. The GMDH and FNN models were employed to accurately predict the important timing representing severe accident scenarios. In addition, in order to verify the proposed algorithm, data from a number of numerical simulations were required in order to train the AI techniques due to the shortage of real LOCA data. The data was acquired by performing simulations using the MAAP4 code. The prediction accuracy of the three types of initiating events was sufficiently high to predict severe accident scenarios. Therefore, the AI techniques can be applied successfully in the identification and monitoring of severe accident scenarios in real PWRs.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• Journal of radiological science and technology
• /
• v.45 no.1
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.9-16
• /
• 2023

Technological advancement is being advanced in sports such as electronic protection of taekwondo competition and VAR of soccer. However, a person judges and guides the posture by looking at the posture, so sometimes a judgment dispute occurs at the site of the competition in Taekwondo Poomsae. This study proposes an artificial intelligence model that can more accurately judge and evaluate Taekwondo movements using artificial intelligence. In this study, after pre-processing the photographed and collected data, it is separated into train, test, and validation sets. The separated data is trained by applying each model and conditions, and then compared to present the best-performing model. The models under each condition compared the values of loss, accuracy, learning time, and top-n error, and as a result, the performance of the model trained under the conditions using ResNet50 and Adam was found to be the best. It is expected that the model presented in this study can be utilized in various fields such as education sites and competitions.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.593-602
• /
• 2014

One of the purposes of an artificial neural netowrk(ANNet) is to implement the largest number of functions as possible with the smallest number of nodes and layers. This paper presents a CoreNet which has a multi-leveled input value and a multi-leveled output value with a 2-layered ANNet, which is the basic structure of an ANNet. I have suggested an equation for calculating the capacity of the CoreNet, which has a p-leveled input and a q-leveled output, as $a_{p,q}={\frac{1}{2}}p(p-1)q^2-{\frac{1}{2}}(p-2)(3p-1)q+(p-1)(p-2)$. I've applied this CoreNet into the simulation model 1(5)-1(6), which has 5 levels of an input and 6 levels of an output with no hidden layers. The simulation result of this model gives, the maximum 219 convergences for the number of implementable functions using the cot(${\sqrt{x}}$) input leveling method. I have also shown that, the 27 functions are implementable by the calculation of weight values(w, ${\theta}$) with the multi-threshold lines in the weight space, which are diverged in the simulation results. Therefore the 246 functions are implementable in the 1(5)-1(6) model, and this coincides with the value from the above eqution $a_{5,6}(=246)$. I also show the implementable function numbering method in the weight space.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.1-7
• /
• 2018

The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.21-28
• /
• 2019

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.