• 한국기계가공학회지
• /
• 제18권2호
• /
• pp.22-28
• /
• 2019

In this study, we describe the mechanical design of the cylindrical workpiece inspection system which that can inspect the workpiece machined in the CNC lathe. The workpiece automatic measuring device is composed of a workpiece aligning mechanism, a workpiece diameter measuring mechanism, and a workpiece height measuring mechanism. If the workpiece machined on the CNC lathe is placed on the pedestal of the cylindrical workpiece inspection system, the workpiece aligning mechanism moves the workpiece to the diameter-measuring position and the height- measuring positions, and the diameter-measuring mechanism and the height- measuring mechanisms sequentially measure the diameter and the height of the workpiece. The cylindrical workpiece inspection system was designed and manufactured. The characteristic experiment was conducted to confirm the operation of the machine tool of the cylindrical workpiece inspection system. As a The result of the characteristic test shows that, the workpiece automatic measuring device operated safely.

• 열처리공학회지
• /
• 제36권2호
• /
• pp.69-76
• /
• 2023

In this study, we present a system for identifying equivalent grades of standardized wire rod steel based on alloy composition using machine learning techniques. The system comprises two models, one based on a supervised multi-class classification algorithm and the other based on unsupervised autoencoder algorithm. Our evaluation showed that the supervised model exhibited superior performance in terms of prediction stability and reliability of prediction results. This system provides a useful tool for non-experts seeking similar grades of steel based on alloy composition.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.499-501
• /
• 2021

최근 전 세계적으로 인공지능과 SW는 4차산업혁명 시대의 기반 기술로서 중요한 위치를 점하고 있고, COVID-19로 인한 학습 환경의 변화로 웹브라우저 기반 프로그래밍 학습 시스템이 일반화되고 있다. 본 고에서는 이러한 트렌드에 따라 인공지능과 SW의 근간이 되는 알고리즘을 학습하기 위한 도구로서의 온라인 평가 시스템에 대해 기능별 확장 가능한 마이크로서비스 기반 시스템 구조를 제안한다. 그리고, 제안한 시스템 구조하에서 자동 평가 기능에 대해 머신러닝을 적용하기 위한 기능적 구조에 대해 또한 제안한다.

• 한국분말야금학회:학술대회논문집
• /
• 한국분말야금학회 2006년도 Extended Abstracts of 2006 POWDER METALLURGY World Congress Part2
• /
• pp.1276-1277
• /
• 2006

The ever increasing requirements on today's compacts with regard to their geometry and precision call for flexible high-precision and most capable production systems. DORST Technologies has coped with these requirements by developing the new HP series for pressing forces between 1600 kN and 16000 kN and the new HS series for pressing forces between 150 kN and 1200 kN. These fully hydraulic presses featuring upper ram, lower ram, core rod, filler, up to 4 lower tool levels and up to 4 upper tool levels with closed-loop controlled movements. Thanks to latest servo technology and an electronic bus system it is possible to have all movements closed-loop controlled in the desired relation to each other. Thus, today's hydraulic presses provide high stroke rates, low energy consumption and a user-friendly interface. The input of data is carried out via clearly arranged screen masks on a touch-screen. The innovative DORST $IPG^{(R)}$ (Intelligent Program Generator) has been designed to support the set-up staff in preparing and optimizing the toolprogram. The combination of the machine type with the hydraulic unit determines the productivity in consideration of the specific application and the part to be pressed. Thanks to the closed-loop control circuits, DORST hydraulic automatic presses of the latest generation ensure unmatched precision and repeatability - and consequently process reliability - often without necessitating subsequent machining steps.

• 융합정보논문지
• /
• 제7권1호
• /
• pp.55-60
• /
• 2017

사물인터넷 환경에서 인간의 개입 없는 지능화된 서비스를 위해서는 IoT 디바이스에서 생성되는 빅데이터로 부터 정상 패턴을 학습하고 이를 기반으로 불량, 오작동과 같은 이상 징후에 대해 예측하는 과정이 요구된다. 본 연구의 목적은 제품 공정의 다양한 기기에서 발생되는 빅데이터를 분석함으로써 제품 불량을 예측할 수 있는 기계 학습모델을 구현하는 것이다. 기계 학습 모델은 어느 정도 볼륨을 가진 기존 데이터를 기반으로 분석을 해야 하므로 빅데이터 분석도구 R을 사용하였으며, 제품 공정에서 수집된 데이터에는 제품에 대한 불량 여부가 포함되어 있으므로 지도 학습 모델을 활용하였다. 연구의 결과, 제품 불량에 영향을 주는 변수 및 변수 조건을 분류하였고, 의사결정 트리를 기반으로 제품의 불량 여부에 대한 예측 모델을 제시하였다. 또한, ROC Curve를 이용한 모델의 적합성 및 성능평가 분석에서 모델의 예측력은 상당히 높게 나타났다.

• 지능정보연구
• /
• 제11권3호
• /
• pp.69-81
• /
• 2005

고객관계관리는 치열한 경쟁환경에서 각 기업이 생존하기 위해 반드시 필요한 하나의 기업전략이 되었다. 고객관계관리의 방법은 다양하지만 가장 기본적인 방법은 특정 고객이 어떤 상품 혹은 상품군을 구매할 것인지를 정확히 예측하는 것이다. 이미 국내외 실무현장에서 전통적인 데이터마이닝 기법을 활용한 고객구매예측모형이 널리 적용되고 있다. 하지만 전통적인 기법의 경우, 정확도가 상대적으로 떨어지거나 혹은 모형의 구축 및 유지관리가 어렵다는 문제가 종종 제기되어 왔다. 이에 본 연구에서는 기존 모형의 문제점을 개선하기 위한 대안으로, 매우 높은 예측력을 나타내면서 동시에 일반화 능력이 우수한 것으로 알려진 Support Vector Machine(SVM)을 이용하여 고객구매예측모형을 구축하고자 한다. 본 연구에서는 고객구매예측의 도구로써 SVM의 적합성을 판단하기 위하여 전통적인 기법인 로지스틱 회귀분석, 인공신경망과 그 성과를 비교하였다. 그 결과, SVM이 다른 기법들에 비해 상대적으로 우수한 성과를 나타냄을 확인할 수 있었다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.199-205
• /
• 2002

This application study presents a solution to control a Permanent Magnet Synchronous Motor without sensors. The use of this system yields enhanced operations, fewer system components, lower system cost , energy efficient control system design and increased efficiency. The control method presented is field oriented control (FOC). The sinusoidal voltage waveforms are generated by the power module using the space vector modulation technique. A practical solution is described and results are given in this application Study. The performance of a Sensorless architecture allows an intelligent approach to reduce the complete system costs of digital motion control applications using cheaper electrical motors without sensors. This paper deals with an overview of sensorless solutions in digital motor control applications whereby the focus will be the new Controller without sensors and its applications.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.637-642
• /
• 2002

Generally, the use of robots in manufacturing industry has been increased during the past decade. GMA(Gas Metal Are) welding is an actively growing area and many new procedures have been developed for use with high strength alloys. One of the basic requirement for welding applications is to study relationships between process parameters and bead geometry. The objective of this paper is to develop a new approach involving the use of neural network and multiple regression methods in the prediction of bead geometry for GMA welding process and to develop an intelligent system that enables the prediction of bead geometry using Rapid Prototyping(RP) in order to employ the robotic GMA welding processes. This system developed using MATLAB/SIMULINK, could be effectively implemented not only for estimating bead geometry, but also employed to monitor and control the bead geometry in real time.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.247-252
• /
• 2004

Developed shape awareness technology and vision technology for optical ten slant in this research and including external form state of lens for the performance verification developed so that can be good achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data md standard reflex data mutually. Developed system to smallest 1pixel unit though measuring is possible 1pixel as 3.7$\mu\textrm{m}$${\times}$3.7$\mu\textrm{m}$(0.1369${\times}$10/sub-1/$\textrm{mm}^2$) the accuracy to 10/sub-1/mm minutely measuring is possible performance verification and trust ability through an experiment prove.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.354-358
• /
• 2004

There was not the evident analysis about the cutting process of CNC machining, and wouldn't be difficult to estimate the result of machining for the various cutting conditions. Therefore they were not founded the systemic technology about the optimum cutting conditions and selection of cutting tools. So this study have investigated the common facts for needs through the end-mill cutting machining by Machining-Centers or High-speed cutting machines, and developed the user-centered intelligent decision system to selection of the methodology about cutting conditions to improve the machining efficiency of end-mill cutting process.