• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.883-887
• /
• 2002

We should maintain the maximum operation capacity for production facilities and find properly out the fault of each equipment rapidly in order to decrease a loss caused by its failure. The acoustic and vibration signals of a machine always carry the dynamic information of the machine. These signals are very useful fur the feature extraction and fault diagnosis. We performed a fundamental study which develops a system of fault diagnosis for a pump. We experimented vibrations by acceleration sensors and noises by microphones, compared and analysed for normal products, artificially deformed products. We tried to search a change of the dynamic signals according to machine malfunctions and analyse the type of deformation or failure. The results showed that acoustic signals as well as vibration signals can be used as a simple method lot a detection of machine malfunction or fault diagnosis.

• 동력기계공학회지
• /
• 제11권1호
• /
• pp.45-50
• /
• 2007

Acoustic emission technology is applied to diagnosis the internal leak and operating conditions of the major valves at nuclear power plants. The purpose of this study is to verify availability of the acoustic emission as in-situ diagnosis method. In this study, acoustic emission tests are performed when the pressurized high temperature steam flowed through gate valve(1st stage reheater valve) and glove valve(main steam dump valve) on the normal size of 4 and 8". The valve internal leak diagnosis 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, signal level analysis and RMS(root mean square) analysis of acoustic signal emitted from the valve operating condition internal leak.

• 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.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회B
• /
• pp.3383-3388
• /
• 2007

To compare the sensor performance of AE leak diagnosis system which can measure valve leak conditions, AE activities such as RMS voltage level, AE signal trend, leak rate degree according to AE database, FFT spectrum were measured on valve of the simulated test system for power plant. AE activities were recorded and analyzed from various operating conditions including different temperature, pressure difference, valve size and fluid using both piezoelectric acoustic emission sensor and Pb-Free acoustic emission sensor. The results of this 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 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.

• 한국공작기계학회논문집
• /
• 제13권5호
• /
• pp.81-86
• /
• 2004

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method for a detection of machine malfuction or fault diagnosis.

• 전기학회논문지
• /
• 제57권5호
• /
• pp.881-888
• /
• 2008

We present a novel fault diagnosis methodology using acoustic sensor systems and neural independent component analysis for large-scaled power machines. Acoustic sensors are carried out to measure sounds generated from power machines whose signal is used to determine whether fault is occurred or not. Acoustic measurements are independently mixed and deteriorated from original source signals. We propose a demixing algorithm against such mixed signals by means of independent component analysis which is achieved based on information theory and higher-order statistics to derive learning mechanism.

• 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.

• Journal of Mechanical Science and Technology
• /
• 제20권12호
• /
• pp.2079-2086
• /
• 2006

A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.137-142
• /
• 2003

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer, Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method far a detection of machine malfunction or fault diagnosis.

• 조명전기설비학회논문지
• /
• 제13권4호
• /
• pp.68-74
• /
• 1999

본 연구는 고분자재료에서 음향센서를 이용한 부분방전의 음향적 탐지를 행했다. 저밀도 폴리에틸렌에 대한 트리잉파괴 실험에서 음향센서로 얻어진 음향방출 특성의 시간순서대로 측정하여 통계처리를 행했다. 또한 5가지 특성량을 도입하고 $\psi$-AEA-n(위상-음향진폭-펄스수) 패턴을 분석한 결과, 보이드 시료의 AE평균개시진폭 $(\overline{AEA_{inc}})$과 AE 평균최대진폭$(\overline{AEA_{max}})$은 열화중기, AE펄스수, AE평균최대위상각$(\overline{\theta{max}})$은 열화말기를 진단하기 위해서 유용한 음향방출량임을 알 수 있다. 이들 음향방출량은 보이드 시료의 열화진단을 구별하는데 유용한 음향방출량임을 실험결과로부터 얻었다.