• 응용통계연구
• /
• 제34권1호
• /
• pp.99-114
• /
• 2021

반도체 제조 산업에서는 Big Data에 기초한 Smart Factory 도입과 적용이 가시화되면서 생산 공정의 각 단계에서 수집 가능한 다양한 센서(sensor) 데이터를 활용하여 공정 이상 탐지 및 최종 수율 예측 등에 다양한 분석 방법을 시도하고 있다. 현재 반도체 공정은 원료인 잉곳(ingot)에서 패키징(packaging) 작업 이전의 웨이퍼(wafer) 생산까지 500 600개 이상의 세부 공정과 이와 연계된 수천 개의 계측 공정으로 구성된다. 개별 계측 공정 내의 실제 계측 비율은 대상 제품 대비 0.1%에서 최대 5%를 넘지 못하고 계측 시점별로 일정하게 유지할 수 없다. 이러한 이유로 공정 각 단계의 정상 상태를 간접적으로 판단할 수 있는 장비 센서(sensor) 데이터를 활용하여 관리 여부를 판단하고자 하는 노력이 계속되고 있다. 본 연구에서는 장비 센서 데이터 기반의 공정 이상 탐지 프로세스를 정의하고 현재 적용 되고 있는 기술 통계량 기반 진단 방법의 단점을 보완하기 위해 FDA(Functional Data Analysis)방법을 활용하였다. 실제 현장 사례 데이터에 머신러닝을 이용하여 이상 탐지 정확도 비교를 통해 효과성을 검증하였다.

• 전기학회논문지
• /
• 제59권1호
• /
• pp.82-87
• /
• 2010

A measurement system of contact force between overhead contact line and pantograph of train is developed which measures the contact force by using four sets of full-bridge strain gauges instead of load cells and accelerometers. The sensors are installed on the pan head of pantograph and the measured data from the sensors are transmitted to a server system in the train by way of wireless Lan. This configuration of the measuring system makes it easy to install on the trains without any alteration of train system. The measurement system is applied to KTX on the Kyungbu high speed line, and the measured contact force data shows good agreement with those measured by load cell and accelerometers. The waveform of the contact force between overhead contact line and pantograph contains essential information about their conditions. The proposed measurement system can probe any defects on overhead contact lines with train running at high speed, which will be a powerful solution for the maintenance of long-distance overhead contact lines.

• 한국공작기계학회논문집
• /
• 제17권6호
• /
• pp.8-13
• /
• 2008

At present many research projects on high-speed spindles are being conducted. These projects require a measurement technique which includes heat expansion, vibration and displacement measurement according to angular velocity. This paper presents the development of a measurement system for high-speed spindle displacement. The measurement system is based on $LabView^{(R)}$ and features the following sensors: optical sensor which reacts to the position of a marker on the spindle and enables two Laser Displacement Sensors(LDS). These Laser Displacement Sensors send their data to a DAQ(Data Acquisition Device). It is important that the delay time caused by the response times of the sensors as well as the sampling rate of the DAQ is considered because the spindle revolves at very high speeds.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.179-186
• /
• 2022

In this paper, we design a heart rate measurement system using a web camera. In order to measure the heart rate, face image information is acquired and classified. The face image data is collected from web camera. The heart rate is measured using the collected face image data. We design a function to measure heart rate using input of face information using a web camera in non-contact manner. We design a function that reads face information and estimates heart rate by analyzing face color. An experiment was performed to compare the non-contact heart rate with the actual measured heart rate. The heart rate measurement system using a web camera proposed in this paper is a technology that can be used in various fields. It will be used in sports fields that require heart rate measurement at a low cost.

• Journal of Astronomy and Space Sciences
• /
• 제23권3호
• /
• pp.259-268
• /
• 2006

우주 공간에서 GPS 수신기의 사용은 지구저궤도에서 일반화가 되었다. 최근 대부분의 위성은 위성 위치를 찾기 위한 항법 해로써 GPS 수신기를 사용한다. 그러나, GPS 수신기로부터 직접 획득한 항법 해의 정확도는 지도 제작과 같은 위성 활용에서 충분하지가 않다. 정밀궤도결정과 같은 후처리 개념이 위성 위치 정확도를 향상시키기 위해서 위성 자료 처리에 최근 적용되고 있다. 정밀궤도결정은 GPS 수신기의 항법 해가 아닌 원시 측정 자료를 사용한다. 원시 측정 자료의 성능은 GPS 수신기의 원시 측정 자료 정확도 및 추적 루프 알고리듬에 의해서 결정된다. 이 논문에서는 원시 측정 자료의 성능을 평가할 수 있는 기법을 제안하였다. GPS 수신기의 항법 해와 정밀궤도결정의 항법 해를 얻기 위한 지구저궤도위성의 시험 환경 및 절차를 기술하였다. 추가로, GPS수신기의 항법 해, 원시 측정 자료, 정밀궤도결정의 항법 해에 대한 정확도를 분석하였다. 제안된 기법은 일반적인 저궤도 위성에 적용 가능하다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.819-826
• /
• 2000

This study was performed to develop a measurement system of tractor field performance for plow and rotary operations. Measurement system for tractor consisted of torque sensors to measure torque of drive axles and PTO axle, speed sensors to measure rotational speed of drive axles and engine, microcomputer to control data logger, and data logger as I/O interface system. The measurement system was installed on four-wheel-drive tractor. Four-element full-bridge type strain gages were used for torque measurement of drive axles and optical encoders were used to measure speeds of drive axles and engine. Slip rings were mounted on the rotational axles. Signals from sensors were inputted to data logger that was controlled by microcomputer with parallel communication. Sensors were calibrated before the field tests. Regression equations were found on completion of the calibrations. The field experiment was performed at paddy fields and uplands. Rotary and plow were used when the tractor was operated in the field. Travelling speeds of the tractor were 1.9 km/h, 2.7 km/h, 3.7 km/h, 5.5 km/h, 8.2 km/h, and 11.8 km/h. Operating depths of implements were maintained approximately 20cm during the tests. Torque data of drive axles were different at each location during plow and rotary operations. Results showed that torque of rear axles were greater than those of front axles. Total torque were 6860 - 11064 Nm at the upland and 7360 - 14190 Nm at the paddy field for plow operations. It was found that torque at the paddy field were about 20% greater than those at the upland for plow operations. Torque data showed that rotary operations required less power than plow operation at the paddy field and the upland. Torque measurements at each axle for rotary operations were only 8 - 16% of plow operations in the upland and 15 - 20% in the paddy field.

• 한국정밀공학회지
• /
• 제4권4호
• /
• pp.36-42
• /
• 1987

Very accurate calibration is needed to index tables which are necessary for precision angle measurement. The repeatability of index table is less than 0.2 second, so that attentions should be paid to choosing devices to be used in the calibration of index tables. The auto- collimators have been used in the calibration of index tables, but the repeatability of auto- collimators is bad compared with that of index table. In place of autocollimators, we described a method which uses electric comparators which are possessed by most precision measurement laboratories. Electric comparators are set to measure small angle displacement without interrupting the rotation of index tables and the signals of two electric comparators are added to remove the run-out errors of the shafts of index tables. Two index tables have been calibrated simulataneously by this method and the measurement data have been analyzed by the least squares method. We compare the calibration results with those of methods using autocollimator and auto- matic autocollimator and are able to know that the data of electric comparator method lie between the data of autocollimator methods. The repeatability of measurement is less than 0.02 second. The electric comparator method is economical and capable of reducing the uncertainty of the measurement.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.864-875
• /
• 2018

In this paper, we propose a measurement method for height of white light scanning interferometer using deep learning. In order to measure the fine surface shape, a three-dimensional surface shape measurement technique is required. A typical example is a white light scanning interferometer. In order to calculate the surface shape from the measurement image of the white light scanning interferometer, the height of each pixel must be calculated. In this paper, we propose a neural network for height calculation and use virtual data generation method to train this neural network. The accuracy was measured by inputting 57 actual data to the neural network which had completed the learning. We propose two new functions for accuracy measurement. We have analyzed the cases where there are many errors among the accuracy calculation values, and it is confirmed that there are many errors when there is no interference fringe or outside the learned range. We confirmed that the proposed neural network works correctly in most cases. We expect better results if we improve the way we generate learning data.

• 방송공학회논문지
• /
• 제25권3호
• /
• pp.418-427
• /
• 2020

축산 판매장에서 판매하는 고기들의 신선도 측정은 소비자의 건강을 위해 필요한 기술이다. 신선도 측정을 목적으로 다양한 센서가 연구 개발되고 있다. 센서는 다양한 고기의 신선도 상태 때문에 측정 오류가 발생한다. 따라서 강인성을 가지는 센서를 검증한 후에, 사용하는 과정이 필요하다. 본 논문에서는 10개의 고기 신선도 측정 센서로 얻은 데이터의 분석을 통해서, 각 측정 센서의 성능을 심층신경망을 이용하여 조사한다. 고기 종류로는 소고기, 돼지고기, 닭고기를 대상으로 검증한다. 또한 토리미터보다 성능이 우수한 다중센서를 찾기 위해서 PCA를 이용하여 3개의 센서를 찾는다. 실험에서는 심층신경망으로 3개의 센서가 토리미터보다 우수함을 증명하였다.

• 터널과지하공간
• /
• 제27권5호
• /
• pp.295-302
• /
• 2017

본 연구에서는 폐광지역 지반침하 관리시 토목분야(도로, 철도 등)의 계측관리기준을 그대로 준용하고 있는 현행 계측수행 상의 문제점을 개선하기 위해 광산분야에서 적용할 수 있는 새로운 정량적 계측관리기준을 제시하였다. 광해관리공단의 협조를 얻어 폐광지역에서 수행된 지반침하 관련 자료들을 수집하였고, 이 중 현장에서 실측된 수동계측자료들을 토대로 새로운 계측관리기준치 설정에 대한 여러 기법들에 대해 연구하였다. 그 결과, 계측치들의 평균값, 3사분위수, 95% 신뢰도, 최대값 등의 통계량을 통해 계측항목별 계측관리기준치를 설정, 제안하였다.