• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2007.10a
• /
• pp.360-363
• /
• 2007

This paper deals with the dynamic tensile characteristics of the steel sheets for structural members of a train. Train accidents occurs rarely but lead to many casualties and economical loss. Therefore the safety of the train becomes important during the train crash. The dynamic tensile characteristics of the steel sheets are indispensable to analyze the structural crashworthiness. Current research reports the stress-strain curves, fracture elongation and strain rate sensitivities evaluated at the various strain rates especially for SUS304L-ST and SUS304L-LT steel sheets. The results include the difference in the dynamic tensile characteristics of both rolling and transverse directions. Dynamic tensile tests were performed at the strain rates ranging from 0.003/sec to 200/sec using High Speed Material Testing Machine. The materials tested in this research shows interesting behavior at the low strain rates. The strain hardening exponent decreases remarkably while the yield strength increases.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.1
• /
• pp.27-33
• /
• 2009

A study of fracture to material is getting interest in nuclear and aerospace industry as a viewpoint of safety. Acoustic emission (AE) is a non-destructive testing and new technology to evaluate safety on structures. In previous research continuously, all tensile tests on the pre-defected coupons were performed using the universal testing machine, which machine crosshead was move at a constant speed of 5mm/min. This study is to evaluate an AE source characterization of SM45C steel by using k-nearest neighbor classifier, k-NNC. For this, we used K-means clustering as an unsupervised learning method for obtained multi -variate AE main data sets, and we applied k-NNC as a supervised learning pattern recognition algorithm for obtained multi-variate AE working data sets. As a result, the criteria of Wilk's $\lambda$, D&B(Rij) & Tou are discussed.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.456-461
• /
• 2004

The dynamic behavior of sheet metals must be examined to ensure the impact characteristics of auto-body by a finite element method. An appropriate experimental method has to be developed to acquire the material properties at the intermediate strain rate which is under 500/s in the crash analysis of auto-body. In this paper, tensile tests of various different steel sheets for an auto-body were performed to obtain the dynamic material properties with respect to the strain rate which is ranged from 0.003/sec to 200/sec. A high speed material testing machine was made for tension tests at the intermediate strain rate and the dimensions of specimens that can provide the reasonable results were determined by the finite element analysis. Stress-strain curves were obtained for each steel sheet from the dynamic tensile test and used to deduce the relationship of the yield stress and the elongation to the strain rate. These results are significant not only in the crashworthiness evaluation under car crash but also in the high speed metal forming.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.1
• /
• pp.19-24
• /
• 2008

To reduce time-to-market, more and more embedded system developers and system-on-chip designers rely on microprocessor-based design methodology. ARM processor has been a major player in this industry over the last 10 years. However, there are many restrictions on developing embedded software using ARM processor in the early design stage. For those who are not familiar with embedded software development environment or who cannot afford to have an expensive embedded hardware equipment, testing their software on a real ARM hardware platform is a challenging job. To overcome such a problem, we have designed VMA (Virtual ARM Machine), which offers easier testing and debugging environment to ARM based embedded system developers. Major benefits that can be achieved by utilizing a virtual ARM platform are (1) reducing development cost, (2) lowering the entrance barrier for embedded system novices, and (3) making it easier to test and debug embedded software designs. Unlike many other purely software-oriented ARM simulators which are independent of real hardware platforms, VMA is specifically targeted on SYS-Lab 5000 ARM hardware platform, (designed by Libertron, Inc.), which means that VMA imitates behaviors of embedded software as if the software is running on the target embedded hardware as closely as possible. This paper will describe how VMA is designed and how VMA can be used to reduce design time and cost.

• Korean Journal of Food Science and Technology
• /
• v.17 no.5
• /
• pp.345-349
• /
• 1985

The textural properties of acorn flour gels were investigated with the variations in the concentraction, storage time and storage temperature by the use of Instron Universal Testing Machine. The experimental design was $3^3$ factorial experiment. TPA curves of acorn flour gels showed two sharp peaks in the first bite and no negative peak. The hardness and brittleness of acorn flour gels were very significantly affected by concentration, storage time and storage temperature. For the height difference between first peak and second peals, the main effects for concentration and storage temperature were very significant and the main effect for storage time was not negligible. For bend, the effect of concentration was more significant than the effect of storage temperature, and storage time effect was negligible. Springiness was affected only by the concentration.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.2 no.6
• /
• pp.1-8
• /
• 1994

To enhance the strength of gears for transmission, Generally caburizing heat treatment is applied. But there are some problems in this technology the distortion of gears during heat treatment process, and the discontinuity of manufacturing process. For these reasons, the high frequency induction hardening process is widely used. This method is one of the surface hardening process to improve the wear resistance and fatigue life of the machine components. In this study, to compare the bending fatigue strength of caburized gear with that of induction hardened gear, bending fatigue testing of gears with two different cases was performed by using an electrohydraulic servo-controlled fatigue testing machine and double tooth bending fatigue test fixture. Fatigue life distributions at constant stress levels were established directly from fatigue data. For gear design, the fatigue strength distribution at specified life is more important. This distribution is obtained by statical transformation from fatigue life distribution. Reliability of bending fatigue strength was estimated by P-S-N curves and Weibull distribution.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.4
• /
• pp.372-376
• /
• 2008

We report experimental results on the correlations between welding penetration depth and the frequencies of the radiation from the welding pool. Various welding samples such as SUS304, brass, SUS316, etc. have been investigated with 2 kW CW Nd:YAG laser welding machine. The radiation signals from the plume generated by the interactions between the welding sample and laser with respect to the defocusing length was measured with fiber system collecting the plume signal. Analysis of the frequencies by using fast Fourier transform (FFT) shows that the penetration depth is deep as plume signal frequencies are low, shallow penetration depth for high frequencies. Frequencies up to 250 Hz for obtained signals can be analyzed with the discrete FFT. This is the useful method fur closed loop control of the laser power with respect to the welding penetration depth and is used for real time inspection of the welding quality.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.549-555
• /
• 2021

Machine Learning(ML) splits data into 3 parts, which are usually 60% for training, 20% for validation, and 20% for testing. It just splits quantitatively instead of selecting each set of data by a criterion, which is very important concept for the adequacy of test data. ML measures a model's accuracy by applying a set of validation data, and revises the model until the validation accuracy reaches on a certain level. After the validation process, the complete model is tested with the set of test data, which are not seen by the model yet. If the set of test data covers the model's attributes well, the test accuracy will be close to the validation accuracy of the model. To make sure that ML's set of test data works adequately, we design an experiment and see if the test accuracy of model is always close to its validation adequacy as expected. The experiment builds 100 different SVM models for each of six data sets published in UCI ML repository. From the test accuracy and its validation accuracy of 600 cases, we find some unexpected cases, where the test accuracy is very different from its validation accuracy. Consequently, it is not always true that ML's set of test data is adequate to assure a model's quality.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.823-826
• /
• 2021

The recent COVID-19 pandemic has accentuated the need for faster and more accurate ways of diagnosing certain diseases for there to be safer and more effective early responses that help to prevent a total outbreak. In this work, we would like to approach this issue through machine learning algorithms to investigate whether or not they could serve as a viable replacement for conventional diagnosis. Through a process of training and testing various algorithms, we analyzed how successfully they can predict a patient's COVID-19 diagnosis based on a list of symptoms and also identified which algorithm is the most effective at doing so. If the necessary data, containing the symptoms and diagnoses of different cases, is provided, this method can be utilized to make a probable diagnosis of any disease besides COVID-19. This method can be used in conjunction with or in lieu of conventional diagnosis depending on the situation: if there is a lack of testing facilities or test kits, this method can be employed as it is inexhaustible and it could also be used in situations where a conventional diagnosis is proven to be inaccurate.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.443-452
• /
• 2020

Worker's awkward postures and unreasonable physical load can be corrected by monitoring construction activities, thereby increasing the safety and productivity of construction workers and projects. However, manual identification is time-consuming and contains high human variance. In this regard, an automated activity recognition system based on inertial measurement unit can help in rapidly and precisely collecting motion data. With the acceleration data, the machine learning algorithm will be used to train classifiers for automatically categorizing activities. However, input acceleration data are extracted either from designed experiments or simple construction work in previous studies. Thus, collected data series are discontinuous and activity categories are insufficient for real construction circumstances. This study aims to collect acceleration data during long-term continuous work in a construction project and validate the feasibility of activity recognition algorithm with the continuous motion data. The data collection covers two different workers performing formwork at the same site. An accelerator, as well as portable camera, is attached to the worker during the entire working session for simultaneously recording motion data and working activity. The supervised machine learning-based models are trained to classify activity in hierarchical levels, which reaches a 96.9% testing accuracy of recognizing rest and work and 85.6% testing accuracy of identifying stationary, traveling, and rebar installation actions.