• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.717-719
• /
• 2003

Recently Neural Network techniques have widely used in adaptive and learning control schemes for production systems. However, generally it costs a lot of time for learning in the case applied in control system. Furthermore, the physical meaning of neural networks constructed as a result is not obvious. And in practice since it is difficult to the PID gains suitably lots of researches have been reported with respect to turning schemes of PID gains. A Neural Network-based PID control scheme is proposed, which extracts skills of human experts as PID gains. This controller is designed by using three-layered neural networks. The effectiveness of the proposed Neural Network-based PID control scheme is investigated through an application for a production control system. This control method can enable a plant to operate smoothy and obviously as the plant condition varies with any unexpected accident.

• 전기전자학회논문지
• /
• 제25권3호
• /
• pp.540-543
• /
• 2021

본 논문에서는 비행체의 궤적 예측에 적절한 순환 신경망 기반 기법을 탐구하기 위하여 정량적인 비교 평가 연구를 수행하였다. 이를 위해 본 논문에서는 비행체의 궤적 예측 작업을 수행하기 위한 다양한 입력 및 출력 관계들을 정의하고 동일한 실험 환경에서 비교 평가하였다. 특히 비행체 위치의 상대값 기반 입출력 관계를 제안하여 비행체의 궤적 예측에 적합함을 보였다. 또한 비행체 궤적 예측에 효율적인 네트워크 구조 및 하이퍼파라미터를 결정하기 위한 다양한 ablation study(비교 실험)를 진행하였다. 본 논문에서 제시된 정량적 비교 평가 결과는 비행체의 궤적 예측을 위해 순환 신경망 기반 기법을 이용하거나 비행체의 궤적 예측에 특화된 딥러닝 기법을 연구하고자 하는 연구자 및 개발자들에게 실질적인 도움이 될 것으로 예상된다.

• 지능정보연구
• /
• 제5권1호
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• 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 1993년도 정기총회 및 추계학술대회 논문집 학회본부
• /
• pp.3-5
• /
• 1993

This paper presents a identification techniques of coherent generators for dynamic equivalents using artificial neural networks. In the developed neural network, inputs are the power system parameters which have a property of coherency. Outputs of the neural network are coherency and error indices which are derived from density measure concept. The learning of developed neural network is carried out by means of error back-propagation algorithm. Identification of coherent generators are implemented by proposed grouping algorithm using coherency and error indices. The proposed method is confirmed by simulations for 39-bus New England system.

• 한국기계가공학회지
• /
• 제4권3호
• /
• pp.57-62
• /
• 2005

Neural networks, which have learning and self-organizing abilities, can be advantageously used in the pattern recognition. Neural network techniques have been widely used in monitoring and diagnosis, and compare favourable with traditional statistical pattern recognition algorithms, heuristic rule-based approaches, and fuzzy logic approaches. In this study the fault diagnosis of the face-milling using the artificial neural network was investigated. After training, the sample which measure load current was monitored by constant output results.

• 한국경영과학회지
• /
• 제20권3호
• /
• pp.17-29
• /
• 1995

Recently, neural network models have been employed as an alternative to regression analysis for point estimation or function fitting in various field. Thus far, however, no theoretical or empirical guides seem to exist for selecting the tool which the most suitable one for a specific function-fitting problem. In this paper, we evaluate performance of three major function-fitting techniques, regression analysis and two neural network models, back-propagation and linear-Hebbian-learning neural networks. The functions to be fitted are simple linear ones of a single independent variable. The factors considered are size of noise both in dependent and independent variables, portion of outliers, and size of the data. Based on comutational results performed in this study, some guidelines are suggested to choose the best technique that can be used for a specific problem concerned.

• International Journal of Advanced Culture Technology
• /
• 제8권2호
• /
• pp.231-238
• /
• 2020

Generally, sequential data refers to data having continuity. Text data, which is a representative type of unstructured data, is also sequential data in that it is necessary to know the meaning of the preceding word in order to know the meaning of the following word or context. So far, many techniques for analyzing sequential data such as text data have been proposed. In this paper, four methods of 1d-CNN, LSTM, BiLSTM, and C-LSTM are introduced, focusing on neural network techniques. In addition, by using this, IMDb movie review data was classified into two classes to compare the performance of the techniques in terms of accuracy and analysis time.

• Smart Structures and Systems
• /
• 제6권1호
• /
• pp.39-56
• /
• 2010

Structural Control relies, with a great deal, on the ability of the control algorithm to identify the current state of the system, at any given point in time. When such algorithms are designed to perform in a smart manner, several smart technologies/devices are called upon to perform tasks that involve pattern recognition and control. Smart pattern recognition is proposed to replace/enhance traditional state identification techniques, which require the extensive manipulation of intricate mathematical equations. Smart pattern recognition techniques attempt to emulate the behavior of the human brain when performing abstract pattern identification. Since these techniques are largely heuristic in nature, it is reasonable to ensure their reliability under real life situations. In this paper, a neural network pattern recognition scheme is explored. The pattern identification of three structural systems is considered. The first is a single bay three-story frame. Both the second and the third models are variations on benchmark problems, previously published for control strategy evaluation purposes. A Neural Network was developed and trained to identify the deformed shape of structural systems under earthquake excitation. The network was trained, for each individual model system, then tested under the effect of a different set of earthquake records. The proposed smart pattern identification scheme is considered an integral component of a Smart Structural System. The Reliability assessment of such component represents an important stage in the evaluation of an overall reliability measure of Smart Structural Systems. Several studies are currently underway aiming at the identification of a reliability measure for such smart pattern recognition technique.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2001년도 추계학술대회 논문집
• /
• pp.91-96
• /
• 2001

This paper presents a neural net based nonlinear adaptive controller for an autonomous underwater vehicle (AUV). AUV's dynamics are highly nonlinear and their hydrodynamic coefficients vary with different operational conditions, so it is necessary for the high performance control system of an AUV to have the capacities of learning and adapting to the change of the AUV's dynamics. In this paper a linearly parameterized neural network is used to approximate the uncertainties of the AUV's dynamics, and a sliding mode control is introduced to attenuate the effects of the neural network's reconstruction errors and the disturbances of AUV's dynamics. The presented controller is consist of three parallel schemes; linear feedback control, sliding mode control and neural network. Lyapunov theory is used to guarantee the asymptotic convergence of trajectory tracking errors and the neural network's weights errors. Numerical simulations for motion control of an AUV are performed to illustrate to effectiveness of the proposed techniques.