• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 D
• /
• pp.2528-2530
• /
• 2004

Neural network minimization problems are often conditioned and in this contribution way to handle this will be discussed. It is shown that a better conditioned minimization problem can be obtained if the problem is separated with respect to the linear parameters. This will increase the convergence speed of the minimization. One of the most powerful uses of neural networks is in function approximation(curve fitting)[1]. A main characteristic of this solution is that function (f) to be approximated is given not explicitly but implicitly through a set of input-output pairs, named as training set, that can be easily obtained from calibration data of the measurement system. In this context, the usage of Neural Network(NN) techniques for modeling the systems behavior can provide lower interpolation errors when compared with classical methods like polynomial interpolation. This paper solve of single-variable minimization using neural network.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.367-369
• /
• 2004

In this paper we propose an effective and reliable hand detection method using neural network with ICA(Independent Component Analysis) Features. Many algorithms of hand detection have been proposed yet. Among them, ICA is the one of the interesting topics in image processing. ICA can not only separate mixed signals but also efficiently extract low-dimensional features in signals. ICA features are able to represent the characteristic of the images well. The object of this paper is to use effectively ICA that has above advantage. That is, by the proper number of Independent component the arithmetic speed is faster and by normalization of ICA feature the performance of detection is more reliable. For this, we adopt the algorithm, the Proportion of variance, which select the ICA feature by comparing the ratio of variance of ICA feature. By this method, we can extract the feature that is good at classifying hand and non-hand. Our experimental results show that by using ICA features, we obtained a better performance in hand detection than by only training NN on the image. And we can use hand detection system effectively and reliably by our proposal.

• 전자공학회논문지T
• /
• 제35T권2호
• /
• pp.56-65
• /
• 1998

본 연구는 부하변동이 잦은 유도 전동기 속도제어 시스템에 적합한 신경망 알고리즘을 제안하고 구현을 위한 실제적인 파라미터 추정방법을 제안한다. 전동기 파라미터의 적응추정을 위하여 역전파 신경망 알고리즘을 도입한다. 기준 상태변수와 실제 상태변수와의 오차가 역전파되어 전동기 파라미터를 추정한다. 이의 구현을 위해 고속 연산 신호처리용 프로세서인 TMS320C25를 이용한 제어 시스템을 구성한다. 제어시스템은 알고리즘의 적용이 용이하도록 PC에 기초한 DSP제어 시스템으로 설계 제작한다. 시뮬레이션과 실험을 통하여, 본 연구의 신경망 제어 시스템이 부하변동에 강인한 구조를 갖고 있으며 유도전동기 제어에 실제적 구현이 가능함을 입증한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 춘계학술대회 및 임시총회
• /
• pp.1-5
• /
• 2002

본 논문은 수족이 불편한 장애인의 편리성을 위해 휠체어에 음성인식 모듈을 개발하는데 목표로 하고 있다. 본 시스템의 주프로세서는 TMS320C32를 이용하였고, 전처리단계에서 잡음환경의 특성을 고려하여 Winer 필터를 적용해서 잡음을 제거하였고 특징추출과정에서는 LPC&Cepstrum을 이용하여 프레임당 12차의 특징패턴을 추출하였다. 그 후 인식부에서는 기존의 알고리즘 중 고립단어에서 흔히 사용하는 DTW(Dynamic Time Warping)과 오인식률 발생을 방지하기 위해 NN(Neural Network)를 결합한 Hybrid 형태로 구현하였다. 본 연구에서는 DTW와 Hybrid형태를 각각 실험한 결과 잡음환경에서 고립단어 인식률이 평균 96%이상 나타났다.

• Journal of Power Electronics
• /
• 제2권3호
• /
• pp.220-229
• /
• 2002

In this paper, maximum efficiency operation of two types of permanent magnet synchronous motor drives, namely; surface type permanent magnet synchronous machine (SPMSM) and interior type permanent magnet synchronous motor(IPMSM), are investigated. The efficiency of both drives is maximized by minimizing copper and iron losses. Loss minimization is implemented using flux weakening. A neural network controller (NNC) is designed for each drive, to achieve loss minimization at difffrent speeds and load torque values. Data for training the NNC are obtained through off-line simulations of SPMSM and IPMSM at difffrent operating conditions. Accuracy and fast response of each NNC is proved by applying sudden changes in speed and load and tracking the UC output. The drives'efHciency obtained by flux weakening is compared with the efficiency obtained when setting the d-axis current component to zero, while varying the angle of advance "$\vartheta$" of the PWM inverter supplying the PMSM drive. Equal efficiencies are obtained at diffErent values of $\vartheta$, derived to be function of speed and load torque. A NN is also designed, and trained to vary $\vartheta$ following the derived control law. The accuracy and fast response of the NN controller is also proved.so proved.

• 디지털콘텐츠학회 논문지
• /
• 제2권1호
• /
• pp.51-61
• /
• 2001

퍼지 제어기(FLC)는 고전적인 제어기 보다 외란에 강하고 초기치에 대한 과도응답도 우수할 뿐만 아니라 시스템의 수학적 모델과 파라메터 값을 알지 못하더라도 적절한 제어가 가능하다. 그러나 퍼지 제어기의 제어 규칙 생성은 전문가의 경험과 일단 결정된 제어 규칙은 고정됨으로 인해 제어 시스템의 환경변화에 적응할 수 없는 한계성이 있다. 또한 제어기의 출력값은 미세한 오차를 가지곤 있어 정확한 목표 값에 수렴할 수 없다. 이러한 미세한 오차를 없애기 위하여 여러 가지 방법이 연구되고 있는데, 본 논문에서는 FLC에 NN(Neural Network)과 GA(Genetic Algorithm)를 결합한 GA-FNNIC(유전알고리즘-퍼지 신경망 지능 제어기 : Genetic Algorithm - Fuzzy Neural network Intelligence Controller)를 제안한다. 제안된 GA-FNNIC와 FLC 제어기 간의 출력 특성, 수렴속도, 과도특성과 상승시간에 대해 비교 분석하고, 최종적으로 본 GA-FNNIC가 오차없이 목표치에 정확하게 수렴하는 것을 보인다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.154-157
• /
• 2003

In order for testing faults of combinatorial logic circuit, the authors have developed a new diagnosis method: "Neural Network (NN) fault diagnosis", based on fm error back propagation functions. This method has proved the capability to test gate faults of wider range including so called SSA (single stuck-at) faults, without assuming neither any set of test data nor diagnosis dictionaries. In this paper, it is further shown that what kind of fault models can be detected in the NN fault diagnosis, and the simply modified one can extend to test delay faults, e.g. logic hazard as long as the delays are confined to those due to gates, not to signal lines.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.690-697
• /
• 2000

The objective of this study is to develop a method that is able to realize autonomous traveling for tractor-like robot on the slope terrain. A neural network (NN) and genetic algorithms (GAs) have been used for resolving nonlinear problems in this system. The NN is applied to create a vehicle simulator that is capable to describe the motion of the tractor robot on the slope, while it is impossible by the common dynamics way. Using this vehicle simulator, a control law optimized by GAs was established and installed in the computer to control the steering wheel of tractor robot. The autonomous traveling carried out on a 14-degree slope had initial successful results.

• The Journal of the Acoustical Society of Korea
• /
• 제21권2E호
• /
• pp.98-104
• /
• 2002

The present study describes a combination method to recognize the human affective states such as anger, happiness, sadness, or surprise. For this, we extracted emotional features from voice signals and facial expressions, and then trained them to recognize emotional states using hidden Markov model (HMM) and neural network (NN). For voices, we used prosodic parameters such as pitch signals, energy, and their derivatives, which were then trained by HMM for recognition. For facial expressions, on the other hands, we used feature parameters extracted from thermal and visible images, and these feature parameters were then trained by NN for recognition. The recognition rates for the combined parameters obtained from voice and facial expressions showed better performance than any of two isolated sets of parameters. The simulation results were also compared with human questionnaire results.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 Proceedings of the International Welding/Joining Conference-Korea
• /
• pp.295-300
• /
• 2002

In this paper, an intelligent system to determine welding parameters for each pass and welding position in pipeline welding based on one database and FEM model, two BP neural network models and a C-NN model was developed and validated. The preliminary test of the system has indicated that the developed system could determine welding parameters for pipeline welding quickly, from which good weldments can be produced without experienced welding personnel. Experiments using the predicted welding parameters from the developed system proved the feasibility of interface standards and intelligent control technology to increase productivity, improve quality, and reduce the cost of system integration.