• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.870-881
• /
• 2020

Because SCADA monitoring data of wind turbines are large and fast changing, the unbalanced proportion of data in various working conditions makes it difficult to process fault feature data. The existing methods mainly introduce new and non-repeating instances by interpolating adjacent minority samples. In order to overcome the shortcomings of these methods which does not consider boundary conditions in balancing data, an improved over-sampling balancing algorithm SC-SMOTE (safe circle synthetic minority oversampling technology) is proposed to optimize data sets. Then, for the balanced data sets, a fault diagnosis method based on improved k-nearest neighbors (kNN) classification for wind turbine blade icing is adopted. Compared with the SMOTE algorithm, the experimental results show that the method is effective in the diagnosis of fan blade icing fault and improves the accuracy of diagnosis.

• 지능정보연구
• /
• 제1권2호
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.645-651
• /
• 2002

we propose a k-nearest neighbors(k-NN) based pattern selection method. The method tries to select the patterns that are near the decision boundary and that are correctly labeled. The simulations over synthetic data sets showed promising results: (1) By converting a non-separable problem to a separable one, the search for an optimal error tolerance parameter became unnecessary. (2) SVM training time decreased by two orders of magnitude without any loss of accuracy. (3) The redundant SVM were substantially reduced.

• Journal of Power Electronics
• /
• 제14권5호
• /
• pp.1008-1027
• /
• 2014

An electric scooter with a V-belt continuously variable transmission (CVT) driven by a permanent magnet synchronous motor (PMSM) has a lot of nonlinear and time-varying characteristics, and accurate dynamic models are difficult to establish for linear controller designs. A PMSM servo-drive electric scooter controlled by a novel hybrid modified recurrent Legendre neural network (NN) control system is proposed to solve difficulties of linear controllers under the occurrence of nonlinear load disturbances and parameters variations. Firstly, the system structure of a V-belt CVT driven electric scooter using a PMSM servo drive is established. Secondly, the novel hybrid modified recurrent Legendre NN control system, which consists of an inspector control, a modified recurrent Legendre NN control with an adaptation law, and a recouped control with an estimation law, is proposed to improve its performance. Moreover, the on-line parameter tuning method of the modified recurrent Legendre NN is derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, two optimal learning rates for the modified recurrent Legendre NN are derived to speed up the parameter convergence. Finally, comparative studies are carried out to show the effectiveness of the proposed control scheme through experimental results.

• Smart Structures and Systems
• /
• 제16권6호
• /
• pp.1133-1145
• /
• 2015

A new neural network (NN) predictive controller (NNPC) algorithm has been developed and tested in the computer simulation of active control of a nonlinear structure. In the present method an NN is used as a predictor. This NN has been trained to predict the future response of the structure to determine the control forces. These control forces are calculated by minimizing the difference between the predicted and desired responses via a numerical minimization algorithm. Since the NNPC is very time consuming and not suitable for real-time control, it is then used to train an NN controller. To consider the effectiveness of the controller on probability of damage, fragility curves are generated. The approach is validated by using simulated response of a 3 story nonlinear benchmark building excited by several historical earthquake records. The simulation results are then compared with a linear quadratic Gaussian (LQG) active controller. The results indicate that the proposed algorithm is completely effective in relative displacement reduction.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1994년도 하계학술대회 논문집 C
• /
• pp.1540-1542
• /
• 1994

This paper describes an experimental study of pattern recognition of partial discharge for three different discharge sources by using neural network(NN) system. The NN system is three layer feedforward connections and its learning method is a backpropagation algorithm incorporating an external teacher signal. Input information for NN is a statistical parameters of a discharge magnitude and the number of pulse count. After learning three typical input patterns, NN system offers good discrimination between different defects.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1996년도 추계학술대회 논문집
• /
• pp.361-364
• /
• 1996

Aging diagnosis system using partial discharge(PD) is being highlighted as a research area. But the application of PD requires complicated analysis method because the PD has complex progressing forms. In this paper, It has been developed to the PD diagnosis system using neural network(NN). As a result after NN learning, the recognized rate was represented about 85%. The safety area is possible to express the second output of NN in this experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.187-190
• /
• 1995

A method is proposed which searches for optimal structures of Neural Networks (NN) using Genetic Algorithm (GA). The purpose of the method lies in not only finding an optimal NN structure but also leading us to the goal of self-organized control system that acquires its structure and its functionality by itself depending on its environment.

• 스마트미디어저널
• /
• 제3권2호
• /
• pp.14-19
• /
• 2014

본 논문에서는 스마트 TV, 스마트폰으로 대표되는 스마트 장치에서 비접촉식 전위계차 센서(CEPS)로부터 추출된 동작신호를 k-NN과 DTW 알고리즘을 이용하여 인식하는 방법을 제안한다. 먼저 CEPS 신호는 칼만 필터를 이용해서 잡음을 제거해주고 정규화를 시켜준다. 다음 인식 속도를 향상시키고 분류에 방해되는 성분제거 하기 위해 PCA 알고리즘을 사용해서 신호의 차원을 축소시켰다. 그리고 k-NN과 DTW 알고리즘을 사용하여 인식 작업을 수행하였다. 실험 결과에서는 앞서 언급된 2개의 스마트 장치 환경 셋팅에 대해서 설명하고 각각의 환경에서 추출된 신호를 제안된 알고리즘에 의해서 인식을 하였다. 기존 인식 알고리즘의 결합과 분해를 통해 다양한 결과를 비교 분석함하고 90% 이상의 인식률을 달성함으로써 제안된 방법의 우수성을 증명하였다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (2)
• /
• pp.160-162
• /
• 2005

무선 방송 방식은 부족한 대역폭의 효율적인 활용과 채널을 듣는 모든 사용자를 지원할 수 있다는 효율성 측면에서 각광받고 있다. 위치기반 서비스 중에서도 효율적인 방송기법을 이용하기 위한 연구 및 가장 기본적인 질의 중 하나인 NN 질의를 효율적으로 수행하기 위한 연구가 이루어져 왔다. 그러나 기존의 연구된 기법들은 NN 탐색 시 하나 이상의 방송주기를 필요로 하여 긴 접근 시간을 가진다는 단점이 있다. 이러한 단점을 모바일 환경에서 비효율적으로 자원을 사용한다는 문제를 발생시킨다. 이에 따라 본 논문에서는 한층 효율적인 자원 사용을 위해서 무선 기기에서 무선 방송 채널을 통해 NN 탐색을 수행할 수 있는 새로운 기법을 제안하고자 한다. 기존의 기법들에 비해서 접근 시간과 튜닝 시간을 줄임으로써 본 논문에서는 효율적으로 자원을 사용하고자 한다. 또한, 실험을 통해 본 논문에서 제안한 기법이 기존의 기법보다. 향상된 성능을 보이는 것을 증명한다.