• 정보학연구
• /
• 제2권2호
• /
• pp.13-22
• /
• 1999

본 논문에서, 부분방전 메카니즘을 진단하고 그리고 신경망을 도입하여 수명을 예측하기 위한 기초연구로서, 온라인상에서 자동진단을 제안했다. 제안한 방법에서 우리는 음향방출 감지시스템과 그리고 펄스 수와 펄스진폭에 의해서 정량적인 통계파라메타를 사용하였다. 통계적인 파라메타인 가령, 무게중심(G)와 방전분포 경도(C)를 이용하였고 그리고 초기단계와 중기단계에 대해서 분석하였다. 정량적인 통계파라메타들은 신경망에 의해서 학습되어졌다. 초기단계에 의해서 수명예측과 절연열화의 진단이 이루어졌다. 열화가 진행하는 동안 신경망 학습을 통한 휼륭한 진단능력이 있음이 근본적으로 드러났고, 신경망이 부분방전에 있어서 절연진단 및 수명예측을 위해서 적절하다는 것이 증명되었다.

• 대한임베디드공학회논문지
• /
• 제14권6호
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.134-143
• /
• 2017

Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines. Generally, it is very difficult to diagnose a machine fault by conventional methods based on mathematical models because of the complexity of the real world systems and the obvious existence of nonlinear factors. This study develops an automatic machine fault diagnosis system that uses pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The sounds emitted by the operating machine, a drill in this case, are obtained and analyzed for the different operating conditions. The specific machine conditions considered in this research are the undamaged drill and the defected drill with wear. Principal component analysis is first used to reduce the dimensionality of the original sound data. The first principal components are then used as the inputs of a neural network based classifier to separate normal and defected drill sound data. The results show that the proposed PCA-ANN method can be used for the sounds based automated diagnosis system.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 춘계학술대회
• /
• pp.173-178
• /
• 1995

This paper relates the occidental constitutional theory to the oriental one, concluding their origins to be similar, and demonstrates a new method of constitutional diagnosis by O-Ring Measurement System Of Muscular Meridians and Laser Constitutional Diagnosis. It establishes Laser Constitutional Diagnosis(L.C.D) using laser beams according to the principles of acupuncture and Sa-Sang constitutional physiology under the effect of spatial morphological energy of geometric isomers. Finally, hypothetical theory of L.C.D. was experimented by the O-Ring Measurement Systems of Muscular Meridians(O-R MSMM). O-R MSMM has been specially devised to improve the manual O-Ring Test prevailing to distinguish energetic response by muscle tonicity. Statistically, it has been proved that the constitutional diagnosis with O-R MSMM was highly effective and objective in the clinical experiences.

• 전기학회논문지P
• /
• 제64권1호
• /
• pp.29-34
• /
• 2015

DC bus electrolytic capacitors are used in variety of equipments as smoothing element of the power converters because it has high capacitance for its size and low price. It is responsible for frequent breakdowns of many static converters and inverter drive systems. Therefore it is important to diagnosis monitoring the condition of an electrolytic capacitor in real-time to predict the failure of power converter. In this paper, the on-line remote diagnosis monitoring system for DC BUS electrolytic capacitors of power converter using low-cost type Zigbee communication modules is developed. To estimate the health status of the capacitor, the equivalent series resistor(ESR) of the component has to be determined. The capacitor ESR is estimated by using RMS computation using AC coupling method of DC link ripple voltage/current. The Zigbee communication-based experimental results show that the proposed remote DC capacitor diagnosis monitoring system can be applied to DC/DC converter and UPS successfully.

• 한국지능시스템학회논문지
• /
• 제18권4호
• /
• pp.518-523
• /
• 2008

본 논문에서는 저압 배선 진단 시스템 개발에서 핵심 파트 중 하나인 지능형 차단 시스템 구축을 목표로 한다. 제안된 진단 시스템은 TFDR (Time-Frequency Domain Reflectometry) 알고리즘을 바탕으로 하여 실제 전압이 흐르는 배선에 대해 이상 거리 측정을 하게 된다. 그리고 배선으로부터 얻은 정보를 바탕으로 배선 이상의 종류를 분석하는 것이 지능형 차단 시스템의 목표이다. 효율적인 분석을 위해, 본 논문에서는 퍼지-베이시안 (Fuzzy-Bayesian) 알고리즘을 바탕으로 하여 시스템을 구성하였다. 실제 저압 배선에서 실험된 데이터를 바탕으로 한 실험을 통해 제안된 기술의 우수성을 입증하고자 한다.

• 조명전기설비학회논문지
• /
• 제25권8호
• /
• pp.30-38
• /
• 2011

This paper proposes a new intelligent diagnosis equipment for the partial discharge, which keeps deteriorating the insulating materials inside electric machineries, ultimately leading to electrical breakdown. In order to simulate experimentally the partial discharge inside the electric machinery, the tip-to-plate, the sphere-to-plate, the sphere-to-sphere and the plate-to-plate electrodes are used respectively, of which the gaps are 1[mm], 3[mm] or 5[mm] and the applied voltages are 3[kV], 5[kV] or 7[kV]. Ceramic coupler sensor and FIR digital filter are used to measure the partial discharge and the artificial neural network is used for the deterioration diagnosis of the electric machinery. The microprocessor of PD diagnosis equipment is DSP (TMS320C6713) with FPGA (Cyclone II). The results of the real-time and on-line experiments performed with the developed equipment are also explained.

• 대한한의진단학회지
• /
• 제13권1호
• /
• pp.72-80
• /
• 2009

Objective: We performed this study to check relationship of Cold-Heat attribute analyzed quantitatively by questionnaire with acoustic analysis index. Method : We checked a questionnaire composed of 15 items about the contents of Cold-Heat and asked 83 subjects to answer in the form Likert-like 7-points score. And then, we extracted Cold-Heat attribute from heat score, cold score, heat index and cold index. we measured the acoustic analysis indexes of cardinal vowels by Dr. speech program. Afterward, the data were analyzed by correlation analysis. Results : All cardinal vowels is positive correlated with cold score, heat score and cold index. NNE of vowel /a/ is negative correlated with cold index. Shimmer and F0 tremor of vowel /e/ is negative correlated with cold index. Jitter of vower /u/ is positive correlated with Cold score.

• 한국콘텐츠학회논문지
• /
• 제17권9호
• /
• pp.466-475
• /
• 2017

스트레스는 매일 살아가면서 사소한 일부터 큰 충격을 받는 삶의 주요한 사건까지 다양한 요인으로부터 온다. 이는 어느 한 시기에만 나타나는 것이 아니라, 생애에 거쳐 나타나므로 지속적으로 스트레스를 관리할 수 있는 연구가 필요하다. 본 연구에서는 사용자 스스로 스트레스를 진단, 관리할 수 있는 홍채 분석기반 시스템을 개발하였다. 그리고 홍채진단에 의한 스트레스 지수와 설문기반의 스트레스 지수의 상관성을 분석한 후, 사용자의 스트레스 지수를 정량화하였다. 본 연구에서 제안하는 시스템은 사용자가 쉽게 현재 자신이 느끼고 있는 스트레스 정도를 알 수 있고, 이에 상응하여 예측되는 질병에 대한 조기 진단 및 질병예방의 하나의 방법으로 사용할 수 있을 것이다.

• Journal of Chest Surgery
• /
• 제33권2호
• /
• pp.179-182
• /
• 2000

Background: A pleural effusion is not a disease entity but a clincial sign of systemic or pleural disease. Although the diagnosis of pleural effusion can often be done by toracentesis and pleural needle biopsy the yeild of positive diagnosis is low.