• Proceedings of the KIEE Conference
• /
• 1998.07f
• /
• pp.1922-1924
• /
• 1998

In this paper, the robust vector control method of Induction Motor for the purpose of improving the system performance deterioration caused by parameter variations is proposed. The full order state observer estimates the stator current and the rotor flux by using the state prediction of state variables. And, the motor speed is estimated without speed sensor using the full order state observer. Also, the parameter variation is compensate by the Sliding Observer. By using this method, speed sensorless control and current contol with no affection of the parameter variation can be obtained simultaneously.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.1
• /
• pp.1-5
• /
• 2020

In this paper, a predictive maintenance of the robot trouble using the machine learning method, so called MT(Mahalanobis Taguchi), was studied. Especially, 'MD(Mahalanobis Distance)' was used to compare the robot arm motion difference between before the maintenance(bearing change) and after the maintenance. 6-axies vibration sensor was used to detect the vibration sensing during the motion of the robot arm. The results of the comparison, MD value of the arm motions of the after the maintenance(bearing change) was much lower and stable compared to MD value of the arm motions of the before the maintenance. MD value well distinguished the fine difference of the arm vibration of the robot. The superior performance of the MT method applied to the prediction of the robot trouble was verified by this experiments.

• Korean Journal of Food Science and Technology
• /
• v.37 no.6
• /
• pp.1048-1064
• /
• 2005

Detection of specific compounds influencing food flavor quality is not easy. Electronic nose, comprised of electronic chemical sensors with partial specificity and appropriate pattern recognition system, is capable of recognizing simple and complex volatiles. It provides fast analysis with simple and straightforward results and is best suited for quality control and process monitoring of flavor in food industry. This review examines application of electronic nose in food analysis with brief explanation of its principle. Characteristics of different sensors and sensor drift. and solutions to related problems are reviewed. Applications of electronic nose in food industry include monitoring of fermentation process and lipid oxidation, prediction of shelf life, identification of irradiated volatile compounds, discrimination of food material origin, and quality control of food and processing by principal component analysis and neural network analysis. Electronic nose could be useful for quality control in food industry when correlating analytical instrumental data with sensory evaluation results.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.11 no.3
• /
• pp.384-390
• /
• 1999

A vibrating U-Tube decimeter has been evaluated as a sensor for measuring the concentration of oil in the liquid line of a refrigeration system. Calibration and performance tests were conducted under simulated liquid-line conditions for R-407C/POE oil and R-410A/POE oil mixtures in oil concentration from 0 to 15 weight percent. Test temperatures ranged from 20 to 5$0^{\circ}C$. As a result of test, oil concentration correlations are presented in terms of specific gravity at each constant temperature. These equations enable to predict the oil concentration without any extraction of the mixture, and can be applied for R-407C/POE oil and R-410A/POE oil mixtures.

• Journal of Mechanical Science and Technology
• /
• v.15 no.11
• /
• pp.1482-1489
• /
• 2001

Thermally-induced errors originating from machine tool errors have received significant attention recently because high speed and precise machining is now the principal trend in manufacturing proce sses using CNC machine tools. Since the thermal error model is generally a function of temperature, the thermal error compensation system contains temperature sensors with the same number of temperature variables. The minimization of the number of variables in the thermal error model can affect the economical efficiency and the possibility of unexpected sensor fault in a error compensation system. This paper presents a thermal error model with minimum number of variables using a fuzzy logic strategy. The proposed method using a fuzzy logic strategy does not require any information about the characteristics of the plant contrary to numerical analysis techniques, but the developed thermal error model guarantees good prediction performance. The proposed modeling method can also be applied to any type of CNC machine tool if a combination of the possible input variables is determined because the error model parameters are only calculated mathematically-based on the number of temperature variables.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.8 no.3 s.22
• /
• pp.24-32
• /
• 2005

This paper describes the tracking filter performance for Naval Gun Ballistic Computation Unit(BCU). BCU needs tracing filter for gun firing. Using data of tracking sensor, BCU calculates the future position of Target and Gun order in the time of flight. In this paper, tracing filter is designed with interacting multiple model(IMM). The tracking algorithm based on the IMM requirers a considerable number of sub-model for the various maneuvering target in order to have a good performance. But, in the case of ship target, the maneuvering is restricted compared with the air target. Considering the maneuvering properties and adjusting the mode transition probabilities and the process noise of sub-model, We designed the IMM3 algorithm for Naval tracking filter with three sub-model.

• Annual Conference of KIPS
• /
• 2006.11a
• /
• pp.429-432
• /
• 2006

기존의 u-HealthCare 서비스는 환자에 대해서 일정한 공간에서의 센서의 on/off 타입에 대한 모니터링/환자관리의 서비스를 제공하였다. 이러한 환경하에서의 주된 서비스는 현재 환자의 상태에 대한 수동적인 형태이다. 이러한 문제점들을 해결하기 위해 센서 데이터에 대한 연속센서 데이터마이닝 기법을 이용한다. USN의 응용서비스인 u-HealthCare 서비스는 센서데이터로부터 생체정보 및 위치정보를 이용하여 환자/보호자/관련 의료진에게 필요한 정보를 제공한다. 이것은 환자에 대한 관리/모니터링뿐만 아니라 환자의 상태에 따른 센싱(sensing)된 데이터를 이용한 패턴(pattern), 예측-(prediction), 이상치(outlier)를 분석함으로써 보다 나은 서비스를 제공할 수 있다. 본 논문에서는 센서 데이터에 대해 새로운 연속 센서데이터 마이닝 기법을 적용하여 질의를 통해 지식을 추출하고 보다 지능화된 서비스를 제공할 수 있는 응용서비스 기법을 제안한다.

• Proceedings of the KIPE Conference
• /
• 2017.07a
• /
• pp.76-77
• /
• 2017

본 논문에서는 DC링크 전류센서를 가진 고주파 신호 주입 센서리스 드라이브에서 전류 예측을 이용한 전류 재구축 방법을 제안한다. DC링크 전류센서를 가진 드라이브에서 DC링크 전류로부터 재구축된 3상 전류는 재구축 오차를 포함하고 있다. 이 오차는 고주파 신호 주입 주파수가 높아질수록 커지며, 센서리스 성능을 저하시킨다. 본 논문은 전류 예측을 통하여 재구축 오차를 줄임으로써 센서리스 성능을 향상시켰다. 이는 실험을 통하여 제안한 방법의 유효성을 검증하였다.

• Journal of Sensor Science and Technology
• /
• v.29 no.6
• /
• pp.433-439
• /
• 2020

Recently, the need for IoT-based intelligent systems is increasing in various fields. In this study, we implemented the system that automatically measures the sugar content of fruits without damage to fruit's marketability using near-infrared radiation and machine learning. The spectrums were measured several times by passing a broadband near-infrared light through a fruit, and the average value for them was used as the input raw data of the machine-learned DNN(Deep Neural Network). Using this system, he sugar content value of fruits could be predicted within 5 s, and the prediction accuracy was about 93.86%. The proposed non-destructive sugar content measurement system can predict a relatively accurate sugar content value within a short period of time, so it is considered to have sufficient potential for practical use.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1368-1370
• /
• 2003

Conventional methods investigating soil Hg contamination are time-consuming and expensive. A quicker method is developed to predict soil Hg content with convolved HyMap, ASTER, and TM spectra. The prediction accuracy for each sensor is satisfactory and similar. It suggests that low spectral resolution is not a limitation for predicting soil Hg content. Correlation analysis reveals that Hg -sorption by iron oxides is the mechanism by which to predict spectrally featureless Hg with reflectance spectra. Future study with field measurements and remote sensing data is recommended.