• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 춘계학술대회논문집
• /
• pp.996-1001
• /
• 2006

Automatic washing machines have been improved and popularized steadily since the first electric washing machine was produced in the early 1900's. Appliance industry has tried to obtain the performance of washing machine with large capacity, high energy efficiency, low vibration and low noise levels. As the installation peace of a washer becomes closer to the living space, vibration and noise problems become more important challenges. In general, a washing machine has four legs to support its body. Four legs of the washing machine should be attached on a floor. If not so, it may cause severe vibration or walking in the spin-drying process. Unfortunately, the floor of an ordinary house is bumpy in general, and the consumers will not accept bolting washing machines to a foundation; moreover, sometimes they move the location of their washing machines to utility rooms or bath rooms or kitchens and don't care for leveling the legs exactly. In this study, we devise an auto-leg system that prevents the occurrence of abnormal vibration and walking of washing machines. It is simply composed of a spring and a friction damper. Some experiments are implemented to show the dynamic characteristics of the three-dimensional auto-legged washing machine model that is located on the even or uneven ground. A spring parameter is optimized to adjust the length of the auto-leg system automatically up to 10 mm irregularity, and the friction damper is designed to decrease a resonance induced by the spring of the auto-leg system. Some numerical results show that placing the proposed auto-leg system in a washing machine makes good performance with low vibration, as well as low noise, regardless of the unevenness of the floor.

• 동력기계공학회지
• /
• 제7권2호
• /
• pp.29-35
• /
• 2003

The monitoring and diagnostics of the rotating machinery have been received considerable attention for many years. The objectives are to classify the machinery condition and to find out the cause of abnormal condition. This paper describes a classification method of diagnosing the small reciprocating compressor for refrigerators using the artificial neural network and the wavelet transform. In order to extract salient features, the wavelet transform are used from primary noise signals. Since the wavelet transform decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, more and better features can be obtained easier than time-waveform analysis. In the training phase for classification, self-organizing feature map(SOFM) and learning vector quantization(LVQ) are applied, and the accuracies of them ate compared with each other. This paper is focused on the development of an advanced signal classifier to automatize the vibration signal pattern recognition. This method is verified by small reciprocating compressors, for refrigerator and normal and abnormal conditions are classified with high flexibility and reliability.

• Journal of Welding and Joining
• /
• 제20권2호
• /
• pp.102-108
• /
• 2002

Resistance spot welding of aluminum alloys is based upon Joule heating of the components by passing a large current in a short duration. Since aluminum alloys have the potential to replace steels fur automobile body assemblies, it is important to study the process robustness of aluminum spot welding process. In order to evaluate the effects of process parameters on the weld quality, major process variables and abnormal process conditions were selected and analyzed. A newly developed two-stage, sliding-level experiment was adopted fur effective parameter design and analysis. Suitable ranges of welding current and button diameters were obtained through the experiment. The effects of the factors and their levels on the variation of acceptable welding current were considered in terms of main effects. From the results, it is concluded that any abnormal process condition decreases the suitable current range in the weld lobe curve. Pareto analysis of variance was also introduced to estimate the significant factors on the signal-to-noise (S/N) ratio. Among the six factors studied, fit-up condition is found to be the most significant factor influencing the SM ratio. Using a Pareto diagram, the optimal condition is determined and the SM ratio is significantly improved using the optimal condition.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.1021-1024
• /
• 2001

Out of all metal-cutting processes, the hole-making process is the most widely used. It is estimated to be more than 30% of the total metal-cutting process. It is therefore desirable to monitor and detect drill wear during the hole-drilling process. In this paper, the vision system of the sensing methods of drill flank wear on the basis of image processing is used to detect the wear pattern by non-contact and direct method and get the reliable wear information about drill. In image processing of acquired image, median filter is applied for noise removal. The vision flank wear area of the drill was measured. Backpropagation neural networks (BPns) were used for no-line detection of drill wear. The neural network consisted of three layers: input, hidden and output. The input vectors comprised of spindle rotational speed, feed rates, vision flank wear, thrust and torque signals. The output was the drill wear state which was either usable or failure. Drilling experiments with various spindle rotational speed and feed rates were carried out. The learning process was peformed effectively by utilizing backpropagation. The detection of the abnormal states using BPNs achieved 96.4% reliability even when the spindle rotational speed and feedrate were changed.

• 한국컴퓨터정보학회논문지
• /
• 제23권10호
• /
• pp.65-72
• /
• 2018

In this paper, we used LSTM as a method to detect abnormal behavior of motors. We fixed the high layout size to 1 and changed the range of the input values and the neural network structure to see what change in power consumption prediction. Now, as the fourth industrial revolution era, smart factories are attracting attention. All the physical actions of smart factories are done using motors. Continuous monitoring of motor malfunctions helps to detect malfunctions and efficient operation. However, it is difficult to acquire the power consumption constantly due to the influence of the noise. We have experimented with a simple experimental environment, a method of predicting similarity to input data by adjusting the range of the input data or by changing the neural network structure.

• 한국전자통신학회논문지
• /
• 제13권4호
• /
• pp.751-756
• /
• 2018

스마트 팩토리나 산업용 IoT에서는 공장 내 모든 기기와 장비가 인터넷으로 연결되어 모니터링 됨으로써, 장비나 기기가 고장 나기 전에 예지보전을 통해 설비의 다운타임을 줄이고, 생산성과 가용성을 높일 수 있다. 공장내 주요 설비의 이상 상태는 온도의 이상 상승, 진동과 소음의 변화를 수반하여 나타나게 되므로, 좁은 공간에 쉽게 설치하여 설비의 진동상태를 실시간으로 모니터링 할 수 있는 초소형 스마트 디바이스 개발은 매우 중요하다. 본 연구에서는 WiFi 기능이 있는 초소형 마이크로컨트롤러와 MEMS 가속도 센서를 이용하여 스마트 펙토리의 이상 고장 예지 및 건전성 관리를 위한 스마트 디바이스를 개발하고 그 성능을 분석하였다.

• 한국멀티미디어학회논문지
• /
• 제14권7호
• /
• pp.884-894
• /
• 2011

본 논문에서는 심음에서 제 1심음(S1)과 제 2심음(S2)을 찾기 위한 새로운 알고리듬을 제안하였다. 심음의 주성분을 찾기 위한 기존의 알고리듬들은 심 잡음이 없는 정상 심음 신호에서는 높은 성능을 보이지만 심 질환에 의해 발생하는 심 잡음이 섞여 있는 신호에서는 현저한 성능저하를 보인다. 따라서 본 논문에서는 심 질환이 있는 심음에서 제 1심음과 제 2심음의 검출 성능 향상을 위해 3차 샤논 에너지 변화량을 이용한 알고리듬을 제안하였다. 제 1심음과 제 2심음의 에너지 변화량이 심 잡음에 비해 더 크게 나타나는 특징을 이용하여, 심 잡음을 감쇄시키고 제 1심음, 제 2심음을 검출하였다. 제안한 알고리듬은 정상 심음 뿐 아니라 대동맥 협착증, 승모판막 협착증과 같은 비정상 심음에서도 높은 검출 성능을 가질 수 있도록 개발하였으며 실험 결과 기존의 검출방법에 비하여 높은 검출 성능을 보였다.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.244-251
• /
• 2014

본 논문에서, 가스절연개폐장치(GIS)의 정상상태와 비정상상태에 대해 예방진단기술을 이용하여 자세하게 서술하였다. 이 기술은 지능형 GIS 감시시스템에 의해 저장된 GIS의 데이터의 분석과 진단에 근거한다. GIS음의 파형은 방전과 자체내의 코로나 방전음에 의해 발생되는 것으로 잡음과 비슷하다. 그러므로, 본 논문에서, GIS음의 정상 상태와 비정상 상태로 분류하는데, 정상과 비정상 상태를 레벨교차율(LCR)과 스펙트로그램 에너지비율로 이용하여 구분하였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2008년도 춘계학술대회논문집
• /
• pp.425-430
• /
• 2008

To verify the system performance of portable AE leak diagnosis system which can measure with moving conditions, AE activities such as RMS voltage level, AE signal trend, leak rate degree according to AE database, FFT spectrum were measured during operation on total 11 valves of the secondary system in nuclear power plant. AE activities were recorded and analyzed from various operating conditions including different temperature, type of valve, pressure difference, valve size and fluid. The results of this field study are utilized to select the type of sensors, the frequency band for filtering and thereby to improve the signal-to-noise ratio for diagnosis for diagnosis or monitoring of valves in operation. As the final result of application study above, portable type leak diagnosis system by AE was developed. The outcome of the study can be definitely applied as a means of the diagnosis or monitoring system for energy saving and prevention of accident for power plant valve. The purpose of this study is to verify availability of the acoustic emission in-situ monitoring method to the internal leak and operating conditions of the major valves at nuclear power plants. In this study, acoustic emission tests are performed when the pressurized temperature water and steam flowed through glove valve(main steam dump valve) and check valve(main steam outlet pump check valve) on the normal size of 12 and 18 ". The valve internal leak monitoring system for practical field was designed. The acoustic emission method was applied to the valves at the site, and the background noise was measured for the abnormal plant condition. To improve the reliability, a judgment of leak on the system was used various factors which are AE parameters, trend analysis, frequency analysis, voltage analysis and amplitude analysis of acoustic signal emitted from the valve operating condition internal leak.

• 대한공간정보학회지
• /
• 제19권2호
• /
• pp.63-73
• /
• 2011

DGPS(Differential Global Positioning System) 측위에 보정정보로 사용되는 의사거리 보정치(PRC, Pseudo Range Correction)에는 불규칙적으로 이상점, 노이즈, 이상현상이 발생한다. 이러한 의사거리 보정치를 보정정보로 사용한 DGPS 측위의 경우 측위 오차는 증가하게 된다. 따라서 이 연구에서는 발생되는 의사거리 보정치의 이상점, 노이즈, 이상현상을 다항식 곡선 접합을 적용한 모델링을 통해 검출 및 보정하는 기법을 제안하였다. 또한 의사거리 보정치 모델의 검증을 위해 보정 전 후의 의사거리 보정치를 DGPS 측위에 사용하여 측위오차를 분석하였다. 분석 결과, 이상점, 노이즈, 이상현상이 발생하는 의사거리 보정치를 사용한 측위의 RMS 오차는 수평방향으로 3.84m로 나타났고, 보정된 의사거리 보정치를 사용한 측위에서는 RMS 오차가 수평방향으로 1.49m로 나타나서 측위 정확도가 향상되는 것을 확인하였다.