• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권4호
• /
• pp.551-559
• /
• 2017

본 논문에서는 베어링 고장진단 성능을 개선하기 위해 실시간 학습 방법을 제안한다. 기존 베어링 고장진단의 문제점은 학습되지 않은 상태에 대해 올바른 분류를 할 수 없다는 점이다. 제안한 4단계 실시간 학습 방법은 새로운 상태를 실시간으로 인지 및 학습하여 새로운 상태의 데이터를 올바르게 분류할 수 있다. 1단계에서는 학습 정보에서 각 클래스의 무게중심과 그 클래스 내 각 특징벡터 사이의 유클리디안 거리를 계산하여 각 클래스별로 거리의 최대값을 계산한다. 2단계에서는 새로 취득된 데이터의 특징벡터와 각 클래스의 무게중심 사이의 유클리디안 거리를 계산하고 각 클래스별 최대 허용 거리와 비교한다. 3단계에서는 새로 취득된 데이터들과 각 클래스 내 무게중심 사이의 거리가 각 클래스의 최대 허용 거리보다 모두 클 경우 새로운 상태의 데이터로 인지하고 새로운 상태 인지 횟수를 증가시킨다. 마지막 4단계에서는 새로운 상태 인지 회수가 10보다 클 경우 새로운 상태의 클래스를 생성하기 위해 새로운 상태로 인지된 10개의 데이터를 새로운 상태의 클래스로 지정하고 분류기를 재학습시킨다. 제안한 방법의 성능을 검증하기 위해 실제 베어링 결함 데이터를 사용하여 제안한 실시간 학습 방법의 효율성을 검증하였다.

• 한국소음진동공학회논문집
• /
• 제14권12호
• /
• pp.1233-1240
• /
• 2004

Condition monitoring and fault diagnosis of machines are gaining importance in the industry because of the need to increase reliability and to decrease possible loss of production due to machine breakdown. By comparing the nitration signals of a machine running in normal and faulty conditions, detection of faults like mass unbalance, shaft misalignment and bearing defects is possible. This paper presents a novel approach for applying the fault diagnosis of rotating machinery. To detect multiple faults in rotating machinery, a feature selection method and support vector machine (SVM) based multi-class classifier are constructed and used in the faults diagnosis. The results in experiments prove that fault types can be diagnosed by the above method.

• Smart Structures and Systems
• /
• 제6권4호
• /
• pp.389-403
• /
• 2010

By using image recognition technology, this paper presents a new fault diagnosis method for rotating machinery with artificial immune algorithm. This method focuses on the vibration state parameter image. The main contribution of this paper is as follows: firstly, 3-D spectrum is created with raw vibrating signals. Secondly, feature information in the state parameter image of rotating machinery is extracted by using Wavelet Packet transformation. Finally, artificial immune algorithm is adopted to diagnose rotating machinery fault. On the modeling of 600MW turbine experimental bench, rotor's normal rate, fault of unbalance, misalignment and bearing pedestal looseness are being examined. It's demonstrated from the diagnosis example of rotating machinery that the proposed method can improve the accuracy rate and diagnosis system robust quality effectively.

• Journal of Advanced Marine Engineering and Technology
• /
• 제31권1호
• /
• pp.95-102
• /
• 2007

The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis and prognosis are of increasing importance. This study introduces a technique to detect and identify faults in induction motors. Stator currents were measured and stored by time domain. The time domain is not suitable for representing current signals, so wavelet transform is used to convert the signals onto frequency domain. The raw signals can not show the significant feature, therefore difference values between the signal of the health conditions and that of the fault conditions are applied. The difference values were transformed by wavelet transform and the features are extracted from the transformed signals. The dynamic time warping method was used to identify the fault type. This study describes the results of detecting fault using wavelet analysis.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 추계학술대회논문집
• /
• pp.537-543
• /
• 2003

Condition monitoring and fault diagnosis of machines are gaining importance in the industry because of the need to increase reliability and to decrease possible loss of production due to machine breakdown. By comparing the vibration signals of a machine running in normal and faulty conditions, detection of faults like mass unbalance, shaft misalignment and bearing defects is possible. This paper presents a novel approach for applying the fault diagnosis of rotating machinery. To detect multiple faults in rotating machinery, a feature selection method and support vector machine (SVM) based multi-class classifier are constructed and used in the faults diagnosis. The results in experiments prove that fault types can be diagnosed by the above method.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 추계학술대회논문집
• /
• pp.345-349
• /
• 2003

The dynamic behavior of CANDU nuclear fuel channel was analyzed by the use of 3-dimensional finite element method, under the various fault conditions such as a fault in the end fitting support and the removal/migration of the garter spring in the fuel channel, in order to predict the dynamic behavior for a degraded symptoms of CANDU nuclear fuel channel. Moreover, the frequency response analysis for possible fault conditions was also peformed considering the effects of the pressure tube vibration and flow-induced vibration by the coolant flow. From the analysis of the frequency responses, defects in the garter spring have influenced the changes of 2nd and 3rd modes and all the important modes are varied for the failure in the journal bearing in the end fitting body.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.84-89
• /
• 2014

Data-driven method for fault diagnostics system often use machine learning technique. To use such technique proper signal processing should be implemented such as time synchronous averaging (TSA) for ball bearing systems. However, for journal bearing diagnostics systems not much has been researched, and yet a proper signal processing method has not been studied. Therefore, in this research an optimal datum unit for a reliable journal bearing diagnostics system along with angular resampling process is being suggested. Before extracting time and frequency domain features, angular resampling is applied to each cycle of vibration data. As to preserve the characteristics of vibration signal, averaging method is replaced by finding the optimal datum unit which strengthens statistical characteristics of vibration signal. Then 20 features were extracted for various cases, and those features are being evaluated by two criteria, separability and classification accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집(한일합동학술편); 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.836-841
• /
• 1987

Many kinds of conditioning monitoring technique have been studied, so this study has investigated the possibility of checking the trend in the fault diagnosis of ball bearing, one of the elements of rotating machine, by applying the cepstral analysis method using the adaptive noise cancelling (ANC) method. And computer simulation is conducted in oder to identify obviously the physical meaning of ANC. The optimal adaptation gain in adaptive filter is estimated, the performance of ANC according to the change of the signal to noise ratio and convergence of LMS algorithm is considered by simulation. It is verified that cepstral analysis using ANC method is more effective than the conventional cepstral analysis method in bearing fault diagnosis.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2016년도 제53차 동계학술대회논문집 24권1호
• /
• pp.19-20
• /
• 2016

본 논문에서는 서포트 벡터 머신 (SVM)의 분류 성능에 영향을 주는 인수인 C와 ${\sigma}$ 값을 적응적으로 최적화할 수 있는 적응적 자가튜닝 SVM을 이용한 베어링의 상태 진단 방법을 제안한다. SVM의 각 인수의 변화에 따른 베어링 상태 진단의 성능 변화 패턴을 분석하여 적합한 인수를 적응적으로 찾을 수 있는 방법을 제안하고, 제안한 방법의 우수성을 검증하기 위해 실제 베어링 신호를 이용하여 기존방법인 격자탐색과의 성능을 비교하였다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 봄 학술발표회 논문집
• /
• pp.245-248
• /
• 2001

During the core drilling for the design of a railway bridge crossing over the inferred fault system along the river, fracture zone, extends vertically more than the bottom of borehole, filled with fault gouge was found. The safety of bridge could be threatened by the excessive subsidence or the reduced bearing capacity of bedrock, if a fault would be developed under or around the pier foundation. Thus, a close examination of the fault was required to rearrange pier locations away from the fault or to select a reinforcement method if necessary. Geophysical methods, seismic reflection method and electrical resistivity survey over the water covered area, were applied to delineate the weak zone associated with the fault system. The results of geophysical survey clearly showed a number of faults extending vertically more than 50m. Reinforcement was not desirable because of the high cost and the water contamination, etc. The pier locations were thus rearranged based on the results of geophysical surveys to avoid the undesirable situations, and additional core drillings on the rearranged pier locations were carried out. The bedrock conditions at the additional drilling sites turned out to be acceptable for the construction of piers.