• Journal of Power Electronics
• /
• 제9권3호
• /
• pp.377-385
• /
• 2009

In this paper, a diagnosis method for switch open-circuit faults in three-phase PWM inverters is proposed, which employs support vector machine (SVM) as classifying method. At first, a discrete wavelet transform (DWT) is used to detect a discontinuity of currents due to the fault, and then the features for fault diagnosis are extracted. Next, these features are employed as inputs for the SVM training. After training, the SVM produces an optimized boundary which is used identifying the fault. Finally, the fault classification is performed online with instantaneous features. The experimental results have verified the validity of the proposed estimation algorithm.

• 대한전기학회논문지:전력기술부문A
• /
• 제49권1호
• /
• pp.31-36
• /
• 2000

To enhance the fault diagnosis ability for the dissolved gas analysis(DGA) of the power transformer, this paper proposes a learning vector quantization(LVQ) for the incipient fault recognition. LVQ is suitable expecially for pattern recognition such as fault diagnosis of power transformer using DGA because it improves the performance of Kohonen neural network by placing emphasis on the classification around the decision boundary. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Korea Electrical Power Corporation.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.833-834
• /
• 2014

In recent years, a pattern recognition method has been widely used by researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov model has recently been used as pattern recognition methods in various fields. In this study, a HMM method for the fault diagnosis of a mechanical system is introduced, and a rotating machine with mass unbalance is selected for fault diagnosis. Moreover, a diagnosis procedure to identity the size of a defect is proposed in this study.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 1999년도 유체기계 연구개발 발표회 논문집
• /
• pp.317-323
• /
• 1999

The necessity of diagnosis of the rotating machinery which is widely used in the industry is increasing. Many research has been conducted to manipulate field vibration signal data for diagnosing the fault of designated machinery. As the pattern recognition tool of that signal, neural network which use usually back-propagation algorithm was used in the diagnosis of rotating machinery. In this paper, self-organizing feature map(SOFM) which is unsupervised learning algorithm is used in the abnormal vibration diagnosis of rotating machinery and then learning vector quantization(LVQ) which is supervised teaming algorithm is used to improve the quality of the classifier decision regions.

• 한국산림과학회지
• /
• 제99권2호
• /
• pp.186-196
• /
• 2010

Fertilization increases the crop productivity and produces high quality seedlings for plantation. We quantitatively measured both physical performances and nutrient responses of Fraxinus rhynchophylla, Fraxinus mandshurica, Pinus koraiensis, and Abies holophylla seedlings, which are commercially planted species in Korea, to nitrogen, phosphorus, and potassium fertilization. We analyzed the growth performances by using Dickson's quality index (QI) and the nutrient status by using vector diagnosis. Nitrogen or phosphorus treatment increased height and root collar diameter growth of F. rhynchophylla and F. mandshurica, however, did not increase those of P. koraiensis and A. holophylla. The order of QI was N > P > K > control for F. rhynchophylla, P ${\geq}$ N > Control ${\geq}$ P for F. mandshurica, P > Control ${\geq}$ K > N for P. koraiensis and A. holophylla. In F. rhynchophylla, fertilization diluted N concentration in tissues by 5-25% because growth responses were higher than fertilization uptake. P. koraiensis and A. holophylla showed N excess showing "toxic accumulation". F. rhynchophylla and F. mandshurica showed P deficiency with P fertilization, however, P. koraiensis and A. holophylla showed "luxury accumulation". Vector diagnosis indicated that more fertilization was applicable for F. rhynchophylla and F. mandshurica, and high fertilization rates were inefficient for P. koraiensis and A. holophylla. Both QI and vector diagnosis can be applied to verify seedling quality in the light of growth responses and nutrient status in fertilization trials.

• 전기전자학회논문지
• /
• 제24권3호
• /
• pp.883-889
• /
• 2020

본 논문에서는 CNN(Convolution Neural Network)을 이용한 유도전동기 고정자 고장진단에 PV(Park's Vector)패턴을 특징으로 활용하는 방법을 제안하였다. 기존의 CNN을 이용한 유도전동기 고장진단 방법은 3상 전류를 이미지화하여 진단을 수행하였으나, 이 방법은 인위적으로 전류의 시작점, 위상 등을 맞춰 정규화를 수행해야하는 번거러움이 존재하나, PV패턴을 이용할 경우 일정 원의 패턴을 나타내기 때문에 정규화의 문제를 해결 할 수 있었다. 또한 PV패턴을 이용할 경우, 특징벡터가 자동적으로 정규화됨에 따라 기존의 전류데이터를 이미지화한 결과보다 CNN의 정확도 측면에서 18.18[%] 우수함을 실험을 통해 확인할 수 있었다.

• 전기전자학회논문지
• /
• 제26권1호
• /
• pp.104-110
• /
• 2022

본 논문에서는 UAV의 BLDC 모터 진단방법과 AI진단을 위한 새로운 데이터 셋을 제안하였다. BLDC모터 진단에 있어서 PVA(Park's Vector Approach)는 주파수 성분의 많은 리플로 인해 적용이 어려움이 따르나, 리플의 성분이 3조파를 띄고 있음에 따라 3조파에 뛰어난 SG(Savitzky-Golay)필터를 적용하여 Circle fitting으로 PVA를 활용하는 방법을 제안하였다. 한편, 3상에서 2상으로 변환시키는 기법인 PVA는 변환과정 중 항상 원점을 기준으로 두게 된다. 이에 Circle fitting의 적용과정에서 원점과 측정된 중심점의 오차를 측정하여 고장진단이 가능하도록 하였다. 또한, 이때 측정된 오차의 offset 데이터 기반으로 AI기술의 새로운 데이터 셋으로 활용 가능함을 실험을 통해 입증하였다.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.559-568
• /
• 2014

Induction motors are critical components in industrial processes since their failure usually lead to an unexpected interruption at the industrial plant. The studies of induction motor behavior during abnormal conditions and the possibility to diagnose different types of faults have been a challenging topic for many electrical machine researchers. In this regard, an efficient and new method to detect the induction motor-fault may be the application of the Time Synchronous Averaging (TSA) to the stator current Park's Vector. The aim of this paper is to present a methodology by which defects in a three-phase wound rotor induction motor can be diagnosed. By exploiting the cyclostationarity characteristics of electrical signals, the TSA method is applied to the stator current Park's Vector, allowing the monitoring of the induction motor operation. Simulation and experimental results are presented in order to show the effectiveness of the proposed method. The obtained results are largely satisfactory, indicating a promising industrial application of the hybrid Park's Vector-TSA approach.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.358-360
• /
• 2007

In this paper, an auto-diagnosis method of the stator winding fault for small induction motor is suggested. 3-phase stator currents are sampled, filtered, and transformed with Park's vector transformation. After then Park's vector patterns are obtained. To detect the stator winding fault automatically, a distortion ratio (id/iq) is newly defined and compared with the one of healthy motor, and the threshold levels are suggested. The 2-turn, 4-turn, 8-turn winding fault are tested with no load, 25%, 50%, 75%, and 100% rated load. The distortion ratio of the Park's vector patterns are increased as the increase of the faulted turns, but are same as the increase of the load.

• 품질경영학회지
• /
• 제47권4호
• /
• pp.783-793
• /
• 2019

Purpose: The purpose of this study is to apply the machine and deep learning methodology on error terms which are continuously auto-generated on the sensors with specific time period and prove the improvement effects of power generator prediction diagnosis system by comparing detection ability. Methods: The SVM(Support Vector Machine) and MLP(Multi Layer Perception) learning procedures were applied for predicting the target values and sequentially producing the error terms for confirming the detection improvement effects of suggested application. For checking the effectiveness of suggested procedures, several detection methodologies such as Cusum and EWMA were used for the comparison. Results: The statistical analysis result shows that without noticing the sequential trivial changes on current diagnosis system, suggested approach based on the error term diagnosis is sensing the changes in the very early stages. Conclusion: Using pattern of error terms as a diagnosis tool for the safety control process with SVM and MLP learning procedure, unusual symptoms could be detected earlier than current prediction system. By combining the suggested error term management methodology with current process seems to be meaningful for sustainable safety condition by early detecting the symptoms.