• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.3
• /
• pp.89-100
• /
• 2021

This paper deals with the construction of a combustion test facility and preliminary tests for hot-firing tests of a methane engine. First, the combustion test facility for a 1 kN-class thrust chamber using liquid oxygen/gas methane as propellants was designed and built. Before hot-firing tests, the cold-flow tests of each propellant line and the ignition tests of torch igniter/afterburner were performed to verify propellant supply stability of the combustion test facility, operation of the control and measurement system, and successful ignition. Finally, a preliminary hot-firing test was conducted to measure the combustion efficiency, heat flux, and combustion stability of a thrust chamber prototype. The constructed combustion test facility will be helpfully used for basic research and development of methane engine thrust chambers.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.269-275
• /
• 2021

The turbine rotor, one of the main facilities in a power plant, it generates electricity while rotating at 3600 RPM. Because it rotates at high speed, it requires careful management because high vibration occurs even if it is deformed by only 0.1mm. However, bending occurs due to various causes during turbine operating. If turbine rotor bending occurs, the power plant must be stopped and repaired. In the past, straightening was carried out using a heating torch and furnace in the field. In case of straightening in this way, it is impossible to proceed systematically, so damage to the turbine rotor may occur and take long period for maintenance. Long maintenance period causes excessive cost, so it is necessary to straighten the rotor by minimizing damage to the rotor in a short period of time. To solve this problem, we developed a turbine rotor straightening equipment using high-frequency induction heating equipment. A straightening was validated for 500MW HIP rotor, and the optimal parameters for straightening were selected. In addition, based on the experimental results, finite element analysis was performed to build a database. Using the database, a straightening amount prediction model available for rotor straightening was developed. Using the developed straightening equipment and straightening prediction model, it is possible to straightening the rotor with minimized damage to the rotor in a short period of time.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.3
• /
• pp.54-65
• /
• 2022

We are developing a compact ignition device that can provide a multi-ignition capability for an upper stage methane engine of a two staged small satellite launch vehicle. Firstly, the multi-ignition device is designed and built as an integral part of an additively manufactured mixing head. Secondly, the ignition device requires no separate high-pressure vessels to store ignition propellants as they are branched out from the main feed lines for the mixing head. We performed experiments at various levels, including igniter autonomous tests, thrust chamber ignition and combustion tests on the new compact ignition device which is integrated in the thrust chamber of one-tonf class liquid oxygen/liquid methane engine, and confirmed stable ignition performance.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.5
• /
• pp.63-73
• /
• 2022

Investigation on operation of the test apparatus for the M4 semi-freejet tests with a full-scale vehicle model was carried out utilizing domestic facilities. An integrated design of the experimental apparatus and the vehicle model was obtained through iterative computational fluid dynamics (CFD) analysis. The test results showed that the M4 nozzle of the apparatus was fully expanded to provide required test conditions. It was also found that the intake of the vehicle model successfully started, and the corresponding shadowgraph images were recorded during the test. A variable nozzle of the model was set to adjust the back pressure of the model combustor, and wall-static pressures were measured to obtain the pressure distribution at the main locations of the model. The flame of torch ignitors and pilot fuel ignition were observed in a flame-holder of the combustor.

• Korean Journal of Culture and Social Issue
• /
• v.21 no.3
• /
• pp.481-496
• /
• 2015

The purpose of this study was to search for empirical evidence between internalized shame with self-control, aggression, and addiction potential. Also examine the differences between clinical group and normal group. The data was collected from 100 AA participants and 380 Non-AA participants. For measuring each variable, internalizes shame scale(ISS), self-control rating scale(SCRS), Buss-Durkee Hostility inventory(BDH), addiction potential scale(APS) were used. The survey result was analyzed with Pearson Correlation, Partial correlation and t-test. The results shows: Frist, the internalized shame and the aggression, the addiction potential shows a positive correlation but the self-control shows negative correlation. Second, after control self-control, internalized shame positively correlate to addiction potential and aggression. Third, clinical group recorded a higher level in internalized shame, aggression and addiction potential than normal group; a lower level in self-control. Based on the finding, the implications of understandings, the interventions, the limitations of this study, and the suggestions were discussed.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.6
• /
• pp.21-27
• /
• 2022

C_f/SiC composites have low density, high mechanical strength, and good thermal stability, making them promising materials for high-temperature applications such as rocket propulsion and military fields. However, the remaining Si deteriorates physical and thermal properties. In this paper, the de-siliconization was introduced as a method to remove the Si of the C_f/SiC composite fabricated through Liquid Silicon Infiltration(LSI) process. The stability of composite has been tested under an oxyacetylene torch flame for up to 5 minutes. The oxidized surface and cross section of specimens were characterized by 3D scanning, X-ray diffraction(XRD), Optical microscope(OM) and Scanning electron microscope(SEM).

• The korean journal of orthodontics
• /
• v.52 no.2
• /
• pp.112-122
• /
• 2022

Objective: This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. Methods: The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. Results: The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. Conclusions: The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.17-22
• /
• 2024

This paper introduces the implementation of a secondhand clothing trading system equipped with virtual fitting functionality based on deep learning. The proposed system provides users with the ability to visually try on secondhand clothing items online and assess their fit. To achieve this, it utilizes the Convolutional Neural Network (CNN) algorithm to create virtual representations of users considering their body shape and the design of the clothing. This enables buyers to pre-assess the fit of clothing items online before actually wearing them, thereby aiding in their purchase decisions. Additionally, sellers can present accurate clothing sizes and fits through the system, enhancing customer satisfaction. This paper delves into the CNN model's training process, system implementation, user feedback, and validates the effectiveness of the proposed system through experimental results.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.