• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.9-23
• /
• 2019

In this paper, we propose a layer structure of a pest image classifier model using CNN (Convolutional Neural Network) and background removal image processing algorithm for improving classification accuracy in order to build a smart monitoring system for pine wilt pest control. In this study, we have constructed and trained a CNN classifier model by collecting image data of pine wilt pest mediators, and experimented to verify the classification accuracy of the model and the effect of the proposed classification algorithm. Experimental results showed that the proposed method successfully detected and preprocessed the region of the object accurately for all the test images, resulting in showing classification accuracy of about 98.91%. This study shows that the layer structure of the proposed CNN classifier model classified the targeted pest image effectively in various environments. In the field test using the Smart Trap for capturing the pine wilt pest mediators, the proposed classification algorithm is effective in the real environment, showing a classification accuracy of 88.25%, which is improved by about 8.12% according to whether the image cropping preprocessing is performed. Ultimately, we will proceed with procedures to apply the techniques and verify the functionality to field tests on various sites.

• Structural Engineering and Mechanics
• /
• v.78 no.5
• /
• pp.637-649
• /
• 2021

Great efforts have been conducted to investigate the seismic performances of the arch and rectangular underground structures, however, the differences between seismic responses of these two types of underground structures, especially the vault radian influencing the seismic responses of arch structures are not clarified. This paper presents a detailed numerical investigation on the seismic responses of arch underground structures with different vault radians, and aims to illustrate the rule that vault radian affects the seismic responses of underground structures. Five arch underground structures are built for nonlinear soil-structure interaction analysis. The internal forces of the structural components of the underground structures only under gravity are discussed detailedly, and an optimum vault radian for perfect load-carrying functionality of arch underground structures is suggested. Then the structures are analyzed under seven scaled ground motions, amounting to a total of 35 dynamic calculations. The numerical results show that the vault radian can have beneficial effects on the seismic response of the arch structure, compared to the rectangular underground structures, causing the central columns to suffer smaller axial force and horizontal deformation. The conclusions provide some directive suggestions for the seismic design of the arch underground structures.

• Journal of Aerospace System Engineering
• /
• v.16 no.6
• /
• pp.18-23
• /
• 2022

This paper examines the electromagnetic shielding structure of ultra-high frequency (UHF) RF modules used in aircraft. Advances in electrical and electronic technologies have increased the need for electronic equipment in aircraft. High-frequency wireless devices have become integrated circuits in the form of UHF integrated circuits to support a wide range of frequencies and miniaturisation. To ensure the functionality and performance of these integrated devices in aviation, shielding is necessary to prevent unexpected electromagnetic interference, which could be detrimental to aircraft safety. A shield structure was designed to protect the RF chipset from malfunctioning, and the shielding effectiveness was improved through the application of various geometric shapes.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.407-416
• /
• 2022

Multiple AMRs have been proved to be effective in improving warehouse productivity by eliminating workers' wasteful walking time. Although Multi-agent Path Finding (MAPF)-based solution is an optimal approach for this task, its deployment in practice is challenging mainly due to its imperfect plan-execution capabilities and insufficient computing resources for high-density environments. In this paper, we present a MAPF-based fleet management system architecture that robustly manages multiple robots by re-computing their paths whenever it is necessary. To achieve this, we defined four events that trigger our MAPF solver framework to generate new paths. These paths are then delivered to each AMR through ROS2 message topic. We also optimized a graph structure that effectively captures spatial information of the warehouse. By using this graph structure we can reduce computational burden while keeping its rescheduling functionality. With proposed MAPF-based fleet management system, we can control AMRs without collision or deadlock. We applied our fleet management system to the real logistics warehouse with 10 AMRs and observed that it works without a problem. We also present the usage statistic of adopting AMRs with proposed fleet management system to the warehouse. We show that it is useful over 25% of daily working time.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.1
• /
• pp.169-179
• /
• 2010

iA-Canvas is HMI program which is the industrial automation application developed based on the Java language, and can run on any OS such as Windows, UNIX, Linux. The iA-Canvas is built on object-oriented open structure and consider network functionality and user experience as a system of centralized management and distributed management. iA-Canvas is composed of several components such as Builder, IO Server, Viewer, and Web Service Module and provides a GUI control environment. This paper explains design and implementation of iA-Canvas that is a tool for development of integrated management system, and shows practical examples of integrated management system that use iA-Canvas.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.05a
• /
• pp.452-457
• /
• 2003

As a fundamental study on developing elements with micro shape, micro mold parts machining and experiment of injection molding using it were performed. The ultra precision micro machining system with high functionality was fabricated, and utilized in the machining of micro parts. By using this machining system and micro end-mill tool, a micro circle column structure of high aspect ratio, diameter 60 $\mu\textrm{m}$, height 500 $\mu\textrm{m}$, was fabricated. And a micro lens molds were fabricated by using ball end-mill tool of 300 $\mu\textrm{m}$ diameter and diamond fly-cut tool of 150 $\mu\textrm{m}$ radius. A micro injection molding machine, which is clamping force 1.75 ton, injection capacity 2.8cc, was fabricated for injection molding experiment using micro molds. The injection molding experiment was performed by using the injection molding machine, micro cylinder structures and lens molds. This paper introduces these micro machining system and injection molding machine and demonstrates examples of injection molding using fabricated molds.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.4
• /
• pp.458-464
• /
• 2008

The structural health monitoring has been gaining more importance in civil engineering areas such as earthquake and wind engineering. The use of health monitoring system can also provide tools for the validation of structural analytical model. However, only few structures such as historical buildings and some important long bridges have been instrumented with structural monitoring system due to high cost of installation, long and complicated installation of system wires. In this paper, the structural monitoring system based on cheap and wireless monitoring system is investigated. The use of advanced technology of micro-electro-mechanical system(MEMS) and wireless communication can reduce system cost and simplify the installation. Further the application of wireless MEMS system can provide enhanced system functionality and due to low noise densities. Identification results are compared to ones using data measured from traditional accelerometers and results indicate that the system identification using wireless MEMS system estimates system parameters accurately.

• Structural Engineering and Mechanics
• /
• v.37 no.5
• /
• pp.459-473
• /
• 2011

The study of the early age concrete properties is becoming more important, as the thermal effects and the shrinkage, even in the first hours, could generate cracks, increasing the permeability of the structure and being able to induce problems of durability and functionality in the same ones. The detailed study of the stresses development during the construction process can be decisive to keep low the cracking levels. In this work a computational model, based on the finite element method, was implemented to simulate the early age concrete behavior and, specially, the evaluation of the cracking risk. The finite element analysis encloses the computational modeling of the following phenomena: chemical, thermal, moisture diffusion and mechanical which occur at the first days after the concrete cast. The developed software results were compared with experimental values found in the literature, demonstrating an excellent approach for all the implemented analysis.

• Macromolecular Research
• /
• v.8 no.5
• /
• pp.231-237
• /
• 2000

The polymerization of 3-ethynylphenol, phenylacetylene having hydroxy functionality, was carried out by tungsten and molybdenum-based transition metal catalysts. The polymerization proceeded to give a moderate yield of polymer. The effects on the mole ratio of monomer to catalyst (M/C), initial monomer concentration ((Mb), and the polymerization temperature for the polymerization of 3-ethynylphenol were investigated. The catalytic activity of W-based catalysts was found to be greater than that of Mo-based catalysts. The resulting polymers were brown or black powders and mostly insoluble in organic solvents. Structural analysis of the polymer by instrumental methods revealed the conjugated polymer backbone structure carrying hydroxyphenyl moieties. Thermal and morphological properties of the resulting poly(3-ethynylphenol) were also discussed.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.37-42
• /
• 1992

This Introductory talk of neural networks broadly covers the concepts, basic theory and some example problems. Neural network methods are compared with the AI technology. The structure, functionality as well as learning paradigms of the neural networks are introduced.