• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.898-906
• /
• 1999

A control structure is introduced for the purpose of rejecting periodic (or repetitive) disturbances on a tracking system. The objective of the proposed structure is to drive the output of the system to the reference input that will result in perfect following without any changing the inner configuration of the system. The structure includes an adaptation block which learns the dynamics of the periodic disturbance and forces the interferences, caused by disturbances, on the output of the system to be reduced. Since the control structure acquires the dynamics of the disturbance by on-line adaptation, it is possible to generate control signals that reject any slowly varying time-periodic disturbance provided that its amplitude is bounded. The artificial neural network is adopted as the adaptation block. The adaptation is done at an on-line process. For this , the real-time recurrent learning (RTRL) algoritnm is applied to the training of the artificial neural network.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.11
• /
• pp.987-994
• /
• 2000

A Linear Pulse Motor (LPM) is a direct drive motor that has good performance in terms of accuracy, velocity and acceleration compared to the conventional rotating system with toothed belts and ball screws. However, since an LPM needs supporting devices which maintain constant air-gap and has strong nonlinearity caused by leakage magnetic flux, friction and cogging, etc., there are many difficulties in improvement on accuracy with conventional control theory. Moreover, when designing the position controller of LPM, the modeling error and load variations has not been considered. In order to compensate these components, the neural network with conventional feedback controller is introduced. This neural network of feedback error learning type changes the current commands to improve position accuracy. As a result of experiments, we observes that more accurate position control is possible compared to conventional controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.838-841
• /
• 2005

DNA Chip is able to show DNA-Data that includes diseases of sample to User by using complementary characters of DNA. So this paper studied Neural Network algorithm for Image data processing of DNA-chip. DNA chip outputs image data of colors and intensities of lights when some sample DNA is putted on DNA-chip, and we can classify pattern of these image data on user pc environment through artificial neural network and some of image processing algorithms. Ultimate aim is developing of pattern classifying algorithm, simulating this algorithm and so getting information of one's diseases through applying this algorithm. Namely, this paper study artificial neural network algorithm for classifying pattern of image data that is obtained from DNA-chip. And, by using histogram, gradient edge, ANN and learning algorithm, we can analyze and classifying pattern of this DNA-chip image data. so we are able to monitor, and simulating this algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1624-1627
• /
• 2005

We proposed a design technique for auto-landing guidance and control system. This technique utilizes linear controller and neural network. Main features of this technique is to use conventional linear controller and compensate for the error coming from the model uncertainties and/or reference model mismatch. In this study, the multi-perceptron neural network with single hidden layer is adopted to compensate for the errors. Glide-slope capture logic for auto-landing guidance and control system is designed in this technique. From the simulation results, it is observed that the responses of velocity and pitch angle to commands are fairly good, which are directly related to control inputs of throttle and elevator, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1530-1533
• /
• 2005

In this paper, we design a Linear Quadratic Gaussian controller for the active suspension. We can improve the inherent suspension problem, trade-off between the ride quality and the suspension travel by selecting appropriate weights in the LQ-objective function. Because any definite rules for selecting weights do not exist, we use an optimization-algorithm, Evolution Strategy (ES) to find the proper control gains for selected frequencies, which have major effects on the vibrations of the vehicle's state variables. The frequencies and proper control gains are used for the neural network data. During a vehicle running, the trained on-line neural network is activated and provides the proper gains for non-trained frequencies. For the full-state feedback control, Kalman filter observes the full states and Fourier transform is used to detect the frequency of the road.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2198-2202
• /
• 2005

In this paper we have presented a condition monitoring method of check valve using neural network. The acoustic emission sensor was used to acquire the condition signals of check valve in direct vessel injection (DVI) test loop. The acquired sensor signal pass through a signal conditioning which are consisted of steps; rejection of background noise, amplification, analogue to digital conversion, extract of feature points. The extracted feature points which represent the condition of check valve was utilized input values of fault diagnosis algorithms using pre-learned neural network. The fault diagnosis algorithm proceeds fault detection, fault isolation and fault identification within limited ranges. The developed algorithm enables timely diagnosis of failure of check valve’s degradation and service aging so that maintenance and replacement could be preformed prior to loss of the safety function. The overall process has been experimented and the results are given to show its effectiveness.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.121-128
• /
• 2005

On the research field for speech signal, neural network mainly uses for the category classification in speech recognition and applies to signal processing. Accordingly, this paper proposes a noise reduction system using a time-delay neural network, which implements the mapping from the space of speech signal degraded by noise to the space of clean speech signal. It is confirmed that this method is effective for speech degraded not only by white noise but also by colored noise using the noise reduction system, which restores the amplitude component of fast Fourier transform.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6B
• /
• pp.1120-1126
• /
• 2000

Recently, in order to analyze the time series problems that occur in the nature word, and analyzing method using a neural electric network is being studied more than a typical statistical analysis method. A neural electric network has a generalization performance that is possible to estimate and analyze about non-learning data through the learning of a population. In this paper, after collecting weather datum that was collected from 1987 to 1996 and learning a population established, it suggests the weather forecasting system for an estimation and analysis the future weather. The suggested weather forecasting system uses 28*30*1 neural network structure, raises the total learning numbers and accuracy letting the selecting concentration learning about the pattern, that is not collected, using the descending epsilon learning method. Also, the weather forecasting system, that is suggested through a comparative experiment of the typical time series analysis method shows more superior than the existing statistical analysis method in the part of future estimation capacity.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.3-8
• /
• 2015

In this paper, we investigate an input dimension reduction method using continuous word vector in deep neural network language model. In the proposed method, continuous word vectors were generated by using Google's Word2Vec from a large training corpus to satisfy distributional hypothesis. 1-of-${\left|V\right|}$ coding discrete word vectors were replaced with their corresponding continuous word vectors. In our implementation, the input dimension was successfully reduced from 20,000 to 600 when a tri-gram language model is used with a vocabulary of 20,000 words. The total amount of time in training was reduced from 30 days to 14 days for Wall Street Journal training corpus (corpus length: 37M words).

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.7
• /
• pp.82-91
• /
• 1997

In this paper, we analyze the dynamics of langevine competitive learning neural network based on its fokker-plank equation. From the viewpont of the stochastic differential equation (SDE), langevine competitive learning equation is one of langevine stochastic differential equation and has the diffusin equation on the topological space (.ohm., F, P) with probability measure. We derive the fokker-plank equation from the proposed algorithm and prove by introducing a infinitestimal operator for markov semigroups, that the weight vector in the particular simplex can converge to the globally optimal point under the condition of some convex or pseudo-convex performance measure function. Experimental resutls for pattern recognition of the remote sensing data indicate the superiority of langevine competitive learning neural network in comparison to the conventional competitive learning neural network.