• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.615-620
• /
• 2001

This paper addresses the design of sliding model fuzzy-model-based controller using genetic algorithms. In general, the construction of fuzzy logic controllers has difficulties for the lack of systematic design procedure. To release this difficulties, the sliding model fuzzy-model-based controllers was presented by authors. In this proposed method, the fuzzy model, which represents the local dynamic behavior of the given nonlinear system, is utilized to construct the controller. The overall controller consists of the local compensators which compensate the local dynamic linear model and the feed-forward controller which is designed via sliding mode control theory. Although, the stability and the performance is guaranteed by the proposed method, some design parameters have to be chosen by the designer manually. This problem can be solved by using genetic algorithms. The proposed method tunes the parameters of the controller, by which the reasonable accuracy and the control effort is achieved. The validity and the efficiency of the proposed method are verified through simulations.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 추계학술대회 논문집 학회본부
• /
• pp.186-190
• /
• 1989

A Study for Bad Data Processing in state estimation by a Neural Network is presented. State estimation is the process of assigning a value to an unknown system state variable based on measurement from that system according to some criteria. In this case, the ability to detect and identify bad measurements is extremely valuable, and much time in oder to achieve the state estimation is needed. This paper proposed new bad data processing using Neural Network in order to settle it. The concept of neural net is a parallel distributed processing. In this paper, EBP (Error Back Propagation) algorithm based on three layered feed forward network is used.

• 대한전기학회논문지
• /
• 제32권12호
• /
• pp.441-449
• /
• 1983

Recently, various kinds of computers with architecture different from the usual type of Neumann and Data flow machine have been studied for inproving computational speed. Among them, Feed Forward Computer(F.F.C.) has been remarkably developed. F.F.C. is a computer different from usual digital one in operating system. The usual computer executes operation and operand Fetch after executing instruction fetch and instruction decode. But conceptually, F.F.C. excutes instruction fetch, instruction decode operand fetch and combinational execution simultaneously. Accordingly, a suitable software is needed to operate high reliability and efficiency of this F.F.C. system. In this study, I aim at developing characteristics on highly reliable computer system which should be a blueprint of F.F.C. system in the future.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 D
• /
• pp.2161-2163
• /
• 2004

This paper focuses on congestion control for ATM network with uncertain time-variant delays. The time-variant delays can be distinguished into two distinct components. The first one that is represented by time-variant queueing delays in the intermediate switches is occurred in the return paths of RM cells. The next one is a forward path delay. It is solved by the VBR Model which quantifies the data propagation from the sources to the switch. Robust $H_{\infty}$ control is studied for solving congestion problem with norm-bounded time-varying uncertain parameters. The suitable robust $H_{\infty}$ controller is obtained from the solution of a convex optimization problem including terms of LMIs.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.883-884
• /
• 2008

This paper presents a method for classification of underwater transient signals using, which employs a binary image pattern of the mel-frequency cepstral coefficients(MFCC) as a feature vector and a neural network as a classifier. A feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the MFCC sequences. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with some underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.121.1-121
• /
• 2002

Calculation unit and peripheral units that are used to make the position controller are embedded to one chip FPGA. $\textbullet$ Feed-forward PID controller and interpolator in the calculation unit mitigate frequent context switching. $\textbullet$ The peripheral units reduce the size of the joints position control board. $\textbullet$ Because the calculation unit is designed with pipeline structure, it has the advantages to apply to the multi joints.

• 전자통신동향분석
• /
• 제9권4호
• /
• pp.131-138
• /
• 1994

최근 무선통신의 활성화에 따라, V/UHF(very/ultra high Frequency) 대역에서 한정된 주파수를 효율적으로 이용하기 위한 방법의 하나로서, 점차 점유 주파수 대역의 폭을 축소하여 보다 많은 이용자를 수용하도록 무선 채널의 협대역화가 추진되고 있다. 본 고에서는 먼저 V/UHF 대역 무선 통신에서 채널의 협대역화에 관련된 기술 중에서 현재까지 사용되고 있는 FM(frequency modulation), AM(amplitude modulation) 변조 방식의 장,단점을 살펴본후, 새로운 LM(linear modulation) 변조 방식에 대한 기술적 배경 및 특성을 알아보았다. LM은 SSR(single side band)-AM이 발전한 것으로서, TTIB(transparent tone-in-band), CLT(Cartesian loop transmitter), FFSR(feed-forward signal regeneration), DSP(digital signal processing)등 4가지의 기술이 결합하여 만들어진 것이다. LM 방식에 사용된 4가지 기술을 소개하고, 기존의 변조 방식에 비해 개선된 사항에 대해 서술한다.

• 한국공작기계학회논문집
• /
• 제17권1호
• /
• pp.77-85
• /
• 2008

The objective of the study is to construct a sensor fusion system for tool-condition monitoring (TCM) that will lead to a more efficient and economical drill usage. Drill-wear monitoring has an important attribute in the automatic machining processes as it can help preventing the damage of tools and workpieces, and optimizing the drill usage. In this study, we present the architectures of a multi-layer feed-forward neural network with Levenberg-Marquardt training algorithm based on sensor fusion for the monitoring of drill-wear condition. The input features to the neural networks were extracted from AE, vibration and current signals using the wavelet packet transform (WPT) analysis. Training and testing were performed at a moderate range of cutting conditions in the dry drilling of steel plates. The results show good performance in drill- wear monitoring by the proposed method of sensor fusion and neural network analysis.

• Structural Engineering and Mechanics
• /
• 제51권2호
• /
• pp.299-313
• /
• 2014

In the first part of this paper, the influences of some of crack parameters on natural frequencies of a cracked cantilever Functionally Graded Beam (FGB) are studied. A cantilever beam is modeled using Finite Element Method (FEM) and its natural frequencies are obtained for different conditions of cracks. Then effect of variation of depth and location of cracks on natural frequencies of FGB with single and multiple cracks are investigated. In the second part, two Multi-Layer Feed Forward (MLFF) Artificial Neural Networks (ANNs) are designed for prediction of FGB's Cracks' location and depth. Particle Swarm Optimization (PSO) and Back-Error Propagation (BEP) algorithms are applied for training ANNs. The accuracy of two training methods' results are investigated.

• Structural Engineering and Mechanics
• /
• 제46권6호
• /
• pp.853-868
• /
• 2013

The comparison of the effectiveness of artificial neural network (ANN) and linear regression (LR) in the prediction of strain in tie section using experimental data from eight high-strength-self-compact-concrete (HSSCC) deep beams are presented here. Prior to the aforementioned, a suitable ANN architecture was identified. The format of the network architecture was ten input parameters, two hidden layers, and one output. The feed forward back propagation neural network of eleven and ten neurons in first and second TRAINLM training function was highly accurate and generated more precise tie strain diagrams compared to classical LR. The ANN's MSE values are 90 times smaller than the LR's. The correlation coefficient value from ANN is 0.9995 which is indicative of a high level of confidence.