• Journal of Advanced Marine Engineering and Technology
• /
• 제28권2호
• /
• pp.228-236
• /
• 2004

In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 추계학술대회 논문집
• /
• pp.345-351
• /
• 2004

This Paper describes a nonlinear adaptive noise filter using neural network for digital controller system. Back-Propagation Learning Algorithm based MLP (Multi Layer Perceptron)is used an adaptive filters. In this paper. it assume that the noise of primary input in the adaptive noise canceller is not the same characteristic as that of the reference input. Experimental reaults show that the neural network base noise canceller outperforms the linear noise canceller. Especially to make noise cancel close to realtime, Primary input is divided by unit and each divided part is processed for very short time than all the processed data are unified to whole data.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.225-226
• /
• 2014

In multi-story buildings, heavy-weight floor impact noise propagates through multiple layers. In order to evaluate the influence of structural vibration and propagation, the actual twelve-story building was excited by an impact ball. Sound and vibration responses of each floor was measured using accelerometers and a microphone. Vibration characteristics and its transfer paths were different depending on the excitation floor locations due to differences in the structural characteristics. From the measurement result, transfer characteristics were quantified by statistical energy analysis. It was confirmed that the heavy-weight floor impact noise influence not only adjacent floor. The impact noise transferred and affected multiple layers.

• Steel and Composite Structures
• /
• 제38권2호
• /
• pp.141-150
• /
• 2021

In the present paper we have investigated the Stoneley wave propagation at the interface of two dissimilar homogeneous nonlocal magneto-thermoelastic media under the effect of hall current applied to multi-dual-phase lag heat transfer. The secular equations of Stoneley waves have been derived by using appropriate boundary conditions. The wave characteristics such as attenuation coefficients, temperature distribution and phase velocity are computed and have been depicted graphically. Effect of nonlocal parameter and hall effect are studied on the attenuation coefficient, phase velocity, temperature distribution change, stress component and displacement component. Also, some particular cases have been discussed from the present study.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.896-899
• /
• 1991

This paper presents the neural network method to predict the Korea composition stock price index. The error back-propagation method is used to train the multi-layer perceptron network. Ten of the various economic indices of the past 7 Nears are used as train data and the monthly transition of the composition stock price index is represented by five output neurons. Test results of this method using the data of the last 18 months are very encouraging.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1998년도 추계종합학술대회
• /
• pp.141-145
• /
• 1998

This paper CMOS full adder design method based on carry-propagation-free addition trees and a circuit technique, so called multiple-valued current-mode (MVCM) circuits. The carry-paopagation-free addition method uses a redundant digit sets called redundant positive-digit number representations. The carry-propagation-free addition is by three steps, and the adder can be designed directly and efficiently from the algorithm using MVCM circuit. We demonstrate the effectiveness of the proposed method through simulation(SPICE).

• 전자공학회논문지A
• /
• 제33A권5호
• /
• pp.65-74
• /
• 1996

in this paper, the propagation characteristics of the dominant modes in multiple coupled microstrip lines on a magnetized ferrite substrate are analyzed. The propagation constants and characteristic impedances are calculated by using the spectral domain method. With the numerical results, multi-port impedance parameters as well as scattering parameters are derived from nonreciprocal transmission line equations which are consistent with conventional transmission line theory. In additon, the numerical resutls of nonreciprocal characteristics for various values of structural, material parameters, and external magnetic fields are also presented.

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 1996년도 재료학회 추계학술발표회
• /
• pp.184-184
• /
• 1996

• 대한기계학회논문집A
• /
• 제30권2호
• /
• pp.128-134
• /
• 2006

Topology optimization is an effective scheme to obtain the initial design concept: however, it is hard to apply in case of non-linear or multi-objective problems. In this study, a modified topology optimization method is proposed to generate a structure of a swing arm type actuator satisfying maximum compliance as well. as maximum stiffness using the multi-objective optimization. approach. The multi-objective function is defined to maximize the compliance in the direction of focusing of the actuator and the second eigen-frequency of the structure. The design of experiments are performed and the response surface functions are formulated to construct the multi-objective function. The weighting factors between conflicting functions are determined by the back-error propagation neural network and the solution of multi-objective function is acquired using the genetic algorithm.

• 한국지능시스템학회논문지
• /
• 제2권1호
• /
• pp.17-32
• /
• 1992

로보트 매니퓰레이터의 신경 제어기 구성에 널리 사용하는 다층 신경회로망은 로보트의 불확실한 동적 파라메터 변화에 대한 강건한 학습 적응능력, 그리고 병렬 처리를 통한 실시간 제어등의 장점들을 갖고있다. 그러나 대표적인 학습방법인 오차 역전파(error back propagation) 알고리즘은 그 학습 속도가 느리다는 문제점을 갖는다. 본 논문에서는 불확실하고 애매한 정보를 언어적인 방법에 의해 효율적으로 처리할 수 있는 퍼지 논리 (fuzzy logic)를 도입하여 로보트 매니퓰레이터 신경 제어기의 학습 속도를 개선하기위한 한 방법을 제안한다. 제안된 제어기의 효용성은 PUMA 560 로보트의 모의 실험을 통해 입증된다.