• The Transactions of the Korean Institute of Power Electronics
• /
• 제22권4호
• /
• pp.360-368
• /
• 2017

This paper proposes the 80-kW high-efficiency bidirectional hybrid SiC boost/buck converter using droop control for DC nano-grid. The proposed converter consists of four 20-kW modules to achieve fault tolerance, ease of thermal management, and reduced component stress. Each module is constructed as a cascaded structure of the two basic bi-directional converters, namely, interleaved boost and buck converters. A six-pack hybrid SiC intelligent power module (IPM) suitable for the proposed cascaded structure is adopted for high-efficiency and compactness. The proposed converter with hybrid switching method reduces the switching loss by minimizing switching of insulated gate bipolar transistor (IGBT). Each module control achieves smooth transfer from buck to boost operation and vice versa, since current controller switchover is not necessary. Furthermore, the proposed parallel control using DC droop with secondary control, enhances the current sharing accuracy while well regulating the DC bus voltage. A 20-kW prototype of the proposed converter has been developed and verified with experiments and indicates a 99.3% maximum efficiency and 98.8% rated efficiency.

• Nutrition Research and Practice
• /
• 제13권6호
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• Korean Journal of Agricultural Science
• /
• 제50권3호
• /
• pp.415-424
• /
• 2023

The task of sorting and excluding blemished apples and others that lack commercial appeal is currently performed manually by human eye sorting, which not only causes musculoskeletal disorders in workers but also requires a significant amount of time and labor. In this study, an automated apple-sorting machine was developed to prevent musculoskeletal disorders in apple production workers and to streamline the process of sorting blemished and non-marketable apples from the better quality fruit. The apple-sorting machine is composed of an arm-rest, a main body, and a height-adjustable part, and uses object detection through a machine learning technology called 'You Only Look Once (YOLO)' to sort the apples. The machine was initially trained using apple image data, RoboFlow, and Google Colab, and the resulting images were analyzed using Jetson Nano. An algorithm was developed to link the Jetson Nano outputs and the conveyor belt to classify the analyzed apple images. This apple-sorting machine can immediately sort and exclude apples with surface defects, thereby reducing the time needed to sort the fruit and, accordingly, achieving cuts in labor costs. Furthermore, the apple-sorting machine can produce uniform quality sorting with a high level of accuracy compared with the subjective judgment of manual sorting by eye. This is expected to improve the productivity of apple growing operations and increase profitability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제13권11호
• /
• pp.5542-5550
• /
• 2012

Third-order shear deformation theory is reformulated using the nonlocal elasticity of Eringen. The equation of equilibrium of the nonlocal elasticity are derived. This theory has ability to capture the both small scale effects and quadratic variation of shear strain through the plate thickness. Navier's method has been used to solve the governing equations for all edges simply supported boundary conditions. Analytical solutions of buckling of nano-scale plates are presented using this theory to illustrate the effect of nonlocal theory on buckling load of the nano-scale plates. The relations between nonlocal third-order and local theories are discussed by numerical results. Further, effects of (i) length (ii) nonlocal parameter, (iii) aspect ratio and (iv) mode number on nondimensional buckling load are studied. In order to validate the present solutions, the reference solutions are used and discussed. The present results of nano-scale plates using the nonlocal theory can provide a useful benchmark to check the accuracy of related numerical solutions.

• Advances in nano research
• /
• 제16권4호
• /
• pp.375-394
• /
• 2024

The extensive utilization of concrete has given rise to environmental concerns, specifically concerning the depletion of river sand. To address this issue, waste deposits can provide manufactured-sand (MS) as a substitute for river sand. The objective of this study is to explore the application of machine learning techniques to facilitate the production of manufactured-sand concrete (MSC) containing stone nano-powder through estimating the splitting tensile strength (STS) containing compressive strength of cement (CSC), tensile strength of cement (TSC), curing age (CA), maximum size of the crushed stone (Dmax), stone nano-powder content (SNC), fineness modulus of sand (FMS), water to cement ratio (W/C), sand ratio (SR), and slump (S). To achieve this goal, a total of 310 data points, encompassing nine influential factors affecting the mechanical properties of MSC, are collected through laboratory tests. Subsequently, the gathered dataset is divided into two subsets, one for training and the other for testing; comprising 90% (280 samples) and 10% (30 samples) of the total data, respectively. By employing the generated dataset, novel models were developed for evaluating the STS of MSC in relation to the nine input features. The analysis results revealed significant correlations between the CSC and the curing age CA with STS. Moreover, when delving into sensitivity analysis using an empirical model, it becomes apparent that parameters such as the FMS and the W/C exert minimal influence on the STS. We employed various loss functions to gauge the effectiveness and precision of our methodologies. Impressively, the outcomes of our devised models exhibited commendable accuracy and reliability, with all models displaying an R-squared value surpassing 0.75 and loss function values approaching insignificance. To further refine the estimation of STS for engineering endeavors, we also developed a user-friendly graphical interface for our machine learning models. These proposed models present a practical alternative to laborious, expensive, and complex laboratory techniques, thereby simplifying the production of mortar specimens.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 한국소성가공학회 2003년도 추계학술대회논문집
• /
• pp.97-100
• /
• 2003

Globally, the various machine components, as in electronics and communications, are demanded to being high-performance and micro-scale with abrupt development of the fields of computers, mobile communications. As this current tendency, production of the parts that must have high accuracy, so called milli-structure, are accomplished by the method of top-down, differently as in the techniques of MEMS, NANO. But, in the case of milli-structure, production procedure is highly costs, difficult and demands more accurate dimension than the conservative forming, processing technique. In this paper, forming analysis of the micro-former as the milli-structure are performed and then calculate the punch force etc. This information calculated is applied to decide the forming capacity of micro-former and design the process of forming stage, dimension of dies in another forming bodies. And, for the better precise forming analysis, elasto-plastic analysis is to be performed, then the consideration about effect of elastic recovery when punch and die are unloaded, have to be discussed in change of dimensions.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• 제22권4호
• /
• pp.735-739
• /
• 2013

The error motion of a machine tool spindle directly affects the surface errors of machined parts. Spindle motion errors such as three translational motions and two rotational motions are undesirable. These are usually due to the imperfectness of bearings, stiffness of spindle, assembly errors, and external force or unbalance of rotors. The error motions of the spindle need to be reduced for achieving the desired performance. Therefore, the level of error motion needs to be estimated during the design and assembly process of the spindle. In this study, an estimation method for five degree-of-freedom (5 DOF) error motions for a spindle with an angular contact ball bearing is suggested. To estimate the error motions of the spindle, the waviness of the inner-race of bearings and an external force model were used as input data. The estimation model considers the geometric relationship and force equilibrium of the five DOFs. To calculate the error motions of the spindle, not only the imperfections of the shaft and bearings but also driving elements such as belt pulley and direct driving motor systems are considered.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• 제17권4호
• /
• pp.51-58
• /
• 2008

This paper presents a new design of the precision stage for the reticle in lithography process and a low hunting control method for the stage. The stage has three axes for X, Y, ${\theta}_z$ those actuated by three voice coil motors individually. The designed reticle stage system has three gap sensors and voice coil motors, and supported by four air bearings and the forward/inverse kinematics of the stage were solved to get an accurate reference position. When a stage is in regulating control mode, there always exist small fluctuations(stage hunting) in the stage movement. Because the low stage hunting characteristic is very important in recent lithography and nano-level applications, a special regulating controller for ultra low hunting is proposed in this paper. Also this research proposed the 2-step transmission system for preventing the noise infection from environmental devices. The experimental results showed the proposed regulating control system reduced hunting noise as 35nm(rms) when a conventional PID generates 77nm(rms) in the same mechanical system. Besides the reticle stage has 100nm linear accuracy and $1{\mu}rad$ rotation accuracy at the control frequency of 8kHz.

• Journal of Korea Multimedia Society
• /
• 제25권1호
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Advances in nano research
• /
• 제12권2호
• /
• pp.223-239
• /
• 2022

Object detection has always been to pursue objects with particular properties or representations and to predict details on objects including the positions, sizes and angle of rotation in the current picture. This was a very important subject of computer vision science. While vision-based object tracking strategies for the analysis of competitive videos have been developed, it is still difficult to accurately identify and position a speedy small ball. In this study, deep learning (DP) network was developed to face these obstacles in the study of tennis motion tracking from a complex perspective to understand the performance of athletes. This research has used CNN-VGG 16 to tracking the tennis ball from broadcasting videos while their images are distorted, thin and often invisible not only to identify the image of the ball from a single frame, but also to learn patterns from consecutive frames, then VGG 16 takes images with 640 to 360 sizes to locate the ball and obtain high accuracy in public videos. VGG 16 tests 99.6%, 96.63%, and 99.5%, respectively, of accuracy. In order to avoid overfitting, 9 additional videos and a subset of the previous dataset are partly labelled for the 10-fold cross-validation. The results show that CNN-VGG 16 outperforms the standard approach by a wide margin and provides excellent ball tracking performance.