• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.7
• /
• pp.105-112
• /
• 2021

Reduction of weld distortions and increase in productivity are some of the major goals of the shipbuilding industry. To address these issues, many researchers have attempted to apply new welding processes. In the shipbuilding industry, steel is the candidate material of choice owing to its good weldability. However, conventional welding techniques are not feasible for avoiding welding problems. Tip-rotating arc welding is one of the high-efficiency welding process that has several advantages, such as high welding speed, high melting rate, low heat input, and less distortion. The present study investigates the influence of the welding variables on the weld characteristics of tip-rotating arc welding. Welding was performed using EH36 as the base metal and SM-70s as the filler metal, which are widely used in shipbuilding. Basic experiments were conducted to understand the effects of the major welding variables, such as welding and tip-rotating speeds. The distortion and mechanical properties of the optimal welding conditions were used to evaluate the tip-rotating arc welding performance. Consequently, the feasibility of the tip-rotating arc welding process for joining steel components was investigated, so that the optimized welding conditions could be applied directly to ship body welding to enhance the quality of the welded joints.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Journal of the International Relations & Interdisciplinary Education
• /
• v.3 no.1
• /
• pp.87-103
• /
• 2023

In the era of self-media, short videos are developing strongly. In addition to its rapid development, it has brought new development opportunities for the dissemination of Chinese traditional culture through innovative cultural expressions. In this environment, the video blogger Li ziqi has rapidly become popular among many other types of self-media, which provides good material for us to analyze the reshaping and dissemination of Chinese traditional culture in the age of self-media. This paper discusses the reshaping and dissemination of Chinese traditional culture in the age of self-media by combining the case of the famous short video blogger "Li ziqi", reveals the problems of the current traditional culture dissemination through the content analysis of the reshaping and dissemination of traditional culture in the age of self-media, and puts forward the optimization strategies.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.1
• /
• pp.51-60
• /
• 2023

Unlike the vertical drilling in the directional drilling should be minimized torque and drag in the well trajectory that avoided problems such as drillstring transformation, casing wear and key-seating. These torque and drag magnitude is determined by variations such as the well trajectory geometry, drilling mud, drillstring type and kick-off point. Therefore, it is essential to consider these variations for designing directional well trajectory. In this study, it was selected well trajectory by the most common build-hold type well and calculated torque and drag on each section by Analytical friction model. Analysis indicates that torque and drag could be minimized by using high lubricity drilling mud, kick-off point appropriate according to the well geometry and possible minimize dogleg severity. The results of this study is useful to minimize torque and drag from directional well trajectory design.

• Nuclear Engineering and Technology
• /
• v.54 no.11
• /
• pp.4134-4145
• /
• 2022

The collimator is one of the high-heat-flux components used to avoid a series of vacuum and thermal problems. In this paper, the heat load distribution throughout the collimator is first calculated through experimental data, and a transient thermodynamic simulation analysis of the original model is carried out. The error of the pipe outlet temperature between the simulated and experimental values is 1.632%, indicating that the simulation result is reliable. Second, the model is optimized to improve the heat transfer performance of the collimator, including the contact mode between the pipe and the flange, the pipe material and the addition of a twisted tape in the pipe. It is concluded that the convective heat transfer coefficient of the optimized model is increased by 15.381% and the maximum wall temperature is reduced by 16.415%; thus, the heat transfer capacity of the optimized model is effectively improved. Third, to adapt the long-pulse steady-state operation of the experimental advanced superconducting Tokamak (EAST) in the future, steady-state simulations of the original and optimized collimators are carried out. The results show that the maximum temperature of the optimized model is reduced by 37.864% compared with that of the original model. The optimized model was changed as little as possible to obtain a better heat exchange structure on the premise of ensuring the consumption of the same mass flow rate of water so that the collimator can adapt to operational environments with higher heat fluxes and long pulses in the future. These research methods also provide a reference for the future design of components under high-energy and long-pulse operational conditions.

• Korean Journal of Materials Research
• /
• v.33 no.3
• /
• pp.106-114
• /
• 2023

The carbon concentration in the carburized steels was measured by electron probe microanalysis (EPMA) for a range of soluted carbon content in austenite from 0.1 to 1.2 wt%. This study demonstrates the problems in carbon quantitative analysis using the existing calibration curve derived from pure iron (0.008 wt%C) and graphite (99.98 wt%C) as standard specimens. In order to derive an improved calibration curve, carbon homogenization treatment was performed to produce a uniform Kα intensity in selected standard samples (AISI 8620, AISI 4140, AISI 1065, AISI 52100 steel). The trend of detection intensity was identified according to the analysis condition, such as accelerating voltage (10, 15, 30 keV), and beam current (20, 50 nA). The appropriate analysis conditions (15 keV, 20 nA) were derived. When the carbon concentration depth profile of the carburized specimen was measured for a short carburizing time using the improved calibration curve, it proved to be a more reliable and accurate analysis method compared to the conventional analysis method.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.3
• /
• pp.202-211
• /
• 2023

The profile shops in shipyards produce section steels required for block production of ships. Due to the limitations of shipyard's production capacity, a considerable amount of work is already outsourced. In addition, the need to improve the productivity of the profile shops is growing because the production volume is expected to increase due to the recent boom in the shipbuilding industry. In this study, a scheduling optimization was conducted for a parallel welding line of the profile process, with the aim of minimizing tardiness and the number of set-up changes as objective functions to achieve productivity improvements. In particular, this study applied a dynamic scheduling method to determine the job sequence considering variability of processing time. A Markov decision process model was proposed for the job sequence problem, considering the trade-off relationship between two objective functions. Deep reinforcement learning was also used to learn the optimal scheduling policy. The developed algorithm was evaluated by comparing its performance with priority rules (SSPT, ATCS, MDD, COVERT rule) in test scenarios constructed by the sampling data. As a result, the proposed scheduling algorithms outperformed than the priority rules in terms of set-up ratio, tardiness, and makespan.

• Nuclear Engineering and Technology
• /
• v.55 no.7
• /
• pp.2628-2641
• /
• 2023

Nuclear safety is the lifeline for the development and application of nuclear energy. In severe accidents of pressurized water reactor (PWR), aerosols, as the main carrier of fission products, are suspended in the containment vessel, posing a potential threat of radioactive contamination caused by leakage into the environment. The gas-phase aerosols suspended in the containment will settle onto the wall or sump water through the natural deposition mechanism, thereby reducing atmospheric radioactivity. Aiming at the low accuracy of the aerosol model in the ISAA code, this paper improves the natural deposition model of aerosol in the containment. The aerosol dynamic shape factor was introduced to correct the natural deposition rate of non-spherical aerosols. Moreover, the gravity, Brownian diffusion, thermophoresis and diffusiophoresis deposition models were improved. In addition, ABCOVE, AHMED and LACE experiments were selected to validate and evaluate the improved ISAA code. According to the calculation results, the improved model can more accurately simulate the peak aerosol mass and respond to the influence of the containment pressure and temperature on the natural deposition rate of aerosols. At the same time, it can significantly improve the calculation accuracy of the residual mass of aerosols in the containment. The performance of improved ISAA can meet the requirements for analyzing the natural deposition behavior of aerosol in containment of advanced PWRs in severe accident. In the future, further optimization will be made to address the problems found in the current aerosol model.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.129-137
• /
• 2022

With the development of the 4th industry, the logistics industry is evolving into a smart logistics system. However, ship work that transports vehicles is progressing slowly due to various problems. In this paper, we propose an stowage automation algorithm that can be used for cargo loading of vehicle carriers that shortens loading and unloading work time. The stowage automation algorithm returns the shortest distance by searching for a loading space and a movable path in the ship in consideration of the structure of the ship. The algorithm identifies walls, ramps and vehicles that have already been shipped, and can work even with randomly placed. In particular, it is expected to contribute to developing a smart logistics system for vehicle carriers by referring to the ship's master plan to search for vehicle loading and unloading space in each port and predict the shortest movable path.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.