• 한국공작기계학회논문집
• /
• 제16권2호
• /
• pp.50-56
• /
• 2007

Wire forming machine is widely used in industries to make a variety of wire products such as coil springs and links. Along with the rapid development of CNC technologies, the usage of wire forming machine varies from single-purpose machinery to universal CNC machinery. Rotating the wires while feeding them simultaneously, we can improve the performance of the machines with aspects of efficient tooling and complicated geometric forming. In this study, a new gear train is developed for the control of both feeding and rotating wires independently at the same time. The developed mechanism has many benefits as following, making more complicated geometric and precision products, easier tooling, and simpler programming.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.97-100
• /
• 2004

In recent years, a demand for micro-structure machining is increasing by the development of information and optics industries. Micro machining technology is in general well known in the field of lithograghy. However, the requirement of producing micro machine and/or micro mechanism with metal materials will be increased since a variety of workpiece configurations can be easily made. In this paper, ultra precision machine is developed to obtain micro groove and mirror surface using single crystal diamond tool. According to the cutting experiment, no burr was found at the edge of V-grooves, and the surface roughness of copper is about 1～3nm Ra. It is verified that ultra precision machine is effective to high precision machining.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.880-884
• /
• 1995

Manufacturing environment is getting characterized by unstable market demand,short product life cycle and timebased competition. For adapting this environment,machine tools have to be further versatile functionally in order to reduce part's set-up time. Unlike existing manufacturing systems mainly to focus on part flow, it is important to control tool flow using fast tool change device and tool delivery device in parallel machines consisting of versatile machine tools, because complete operations on a part can be performed on one machine tool in a single machine set-up. In this paper, under dynamic tool allocation strategy to share tools among machine tools, we propose a real-time tool allocation and operation esequence model with an objective of minimizing flow time using autonomy and negotiation of agents in parallel machines

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2001년도 제34회 추계학술대회 개최
• /
• pp.252-259
• /
• 2001

Integrated condition monitoring is required to monitor effectively the machine conditions since machine failures could not be monitored accurately by any single measurement parameter. Application of various condition monitoring techniques is therefore preferred in many cases in order to diagnosis the machine condition. However it inevitably requires lots of maintenance cost and sometimes it could be proved to over-maintenance unnecessarily. This could happen especially when one measurement parameter closely correlates to another. Therefore correlation analysis of various monitoring parameters has to be performed to improve the reliability of diagnosis. In this work, Pearson correlation coefficient was used to analyze the correlation between condition monitoring parameters of an over-loaded machine system where the vibration, wear and temperature were monitored simultaneously. The result showed that Pearson correlation coefficient could be regarded as a good measure for evaluating the availability of condition monitoring technology.

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1715-1723
• /
• 2018

This work investigates the performance of fully complex- valued radial basis function network(FC-RBF) and complex extreme learning machine (CELM) based neural approaches for classification of power quality disturbances. This work engages the use of S-Transform to extract the features relating to single and combined power quality disturbances. The performance of the classifiers are compared with their real valued counterparts namely extreme learning machine(ELM) and support vector machine(SVM) in terms of convergence and classification ability. The results signify the suitability of complex valued classifiers for power quality disturbance classification.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.149-155
• /
• 2023

In urban areas it can be difficult to utilize global navigation satellite systems (GNSS) due to signal reflections and blockages. It is thus crucial to detect reflected or blocked signals because they lead to significant degradation of GNSS positioning accuracy. In a previous study, a classifier for global positioning system (GPS) signal reception conditions was developed using three features and the support vector machine (SVM) algorithm. However, this classifier had limitations in its classification performance. Therefore, in this study, we developed an improved machine learning based method of classifying GPS signal reception conditions by including an additional feature with the existing features. Furthermore, we applied various machine learning classification algorithms. As a result, when tested with datasets collected in different environments than the training environment, the classification accuracy improved by nine percentage points compared to the existing method, reaching up to 58%.

• 한국생산제조학회지
• /
• 제22권4호
• /
• pp.747-754
• /
• 2013

This study introduces a recently designed desktop-sized NC turning system and its components. This machine is designed for the ultra-precise turning of parts with a diameter of 0.5-20 mm with minimum space usage for the machine. This study aims to achieve submicron-level accuracy of movements and good rigidity of the machine for precision machining using the desktop-sized machine. The components such as the main machine structure, air bearing servo spindle, and XZ stage with needle roller guides are designed, and the designed machine is built with a PC-based CNC controller. Its static and dynamic stiffness performances and positioning resolutions are tested. Through machining tests with single-crystal diamond tools, a form error less than $0.8{\mu}m$ and surface roughness (Ra) of $0.03{\mu}m$ for workpieces are obtained.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.129-138
• /
• 1993

The shortage of agricultural labour due to industrial growth has greatly induced the mechanization in Korean agriculture. However small and scattered land holdings have been the main constraints in the process of mechanization. This paper describes the interrelationships of farm land structure, machinery selection and machinery operation areas. The sandy silt loam irrigated paddy land having single crop a year was selected as a target areas for this study. Machine operation cost is greatly influenced by operation period, plot geometry and operation area. On the improved geometry plots, optimal machine size increases slowly with increase in operation area. Operable area increases due to increased effective machine capacity on better geometry plot. The difference between the effects of operation period and plot geometry is that in the former case, the cost reduction is caused by delay in increase of machine size, whereas in the latter case timeliness cost is reduced by increase ffective capacity. The effect of farmland consolidation is greater on small plots than that on big plots. Increasing wage rates have induced the adoption of more labor saving machinery. Bigger labor saving machines require enlargement of operation area and larger plots through improvement in farm land structure. Machine cost on poor plot geometry increases more rapidly than that on the good plot geometry and as operation area increases machine cost reduces significantly. It is concluded that the development of agricultural mechanization ion Korea will depend on the improvement in farm land structure and enlargement of operation area.

• 한국해양공학회지
• /
• 제34권2호
• /
• pp.147-154
• /
• 2020

Underwater acoustics that is the study of the phenomenon of underwater wave propagation and its interaction with boundaries, has mainly been applied to the fields of underwater communication, target detection, marine resources, marine environment, and underwater sound sources. Based on the scientific and engineering understanding of acoustic signals/data, recent studies combining traditional and data-driven machine learning methods have shown continuous progress. Machine learning, represented by deep learning, has shown unprecedented success in a variety of fields, owing to big data, graphical processor unit computing, and advances in algorithms. Although machine learning has not yet been implemented in every single field of underwater acoustics, it will be used more actively in the future in line with the ongoing development and overwhelming achievements of this method. To understand the research trends of machine learning applications in underwater acoustics, the general theoretical background of several related machine learning techniques is introduced in this paper.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.672-675
• /
• 2005

To imprint 70-nm wide line-patterns, we used a newly developed ultraviolet nanoimprint lithography (UV-NIL) process in which an elementwise patterned stamp (EPS), a large-area stamp, and pressurized air are used to imprint a wafer in a single step. For a single-step UV-NIL of a 4' wafer, we fabricated two identical $5'\times5'\times0.09'(W{\times}L{\times}H)$ quartz EPSs, except that one is with nanopatterns and the other without nanopatterns. Both of them consist of 16 small-area stamps, called elements, each of which is $10\;mm\;\times\;10\;mm$. UV-curable low-viscosity resin droplets were dispensed directly on each element of the EPSs. The volume and viscosity of each droplet are 3.7 nl and 7 cps. Droplets were dispensed in such a way that no air entrapment between elements and wafer occurs. When the droplets were fully pressed between ESP and wafer, some incompletely filled elements were observed because of the topology mismatch between EPS and wafer. To complete those incomplete fillings, pressurized air of 2 bar was applied to the bottom of the wafer for 2 min. Experimental results have shown that nanopatterns of the EPS were successfully transferred to the resin layer on the wafer.