• 대한전기학회논문지
• /
• 제45권3호
• /
• pp.444-450
• /
• 1996

A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). refs., figs., tabs.

• 한국생산제조학회지
• /
• 제6권1호
• /
• pp.7-17
• /
• 1997

During the past decade, there were many well-established theories for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of industrial robot control. Neural network computing methods provide one approach to the development of adaptive and learning behavior in robotic system for manufacturing. Computational neural networks have been demonstrated which exhibit capabilities for supervised learning, matching, and generalization for problems on an experimental scale. Supervised learning could improve the efficiency of training and development of robotic systems. In this paper, a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital signal processors is proposed. Digital signal processors, DSPs, are micro-processors that are developed particularly for fast numerical computations involving sums and products of variables. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be an efficient control scheme for implementation of real-time control for SCARA robot with four-axes by experiment.

• 소음진동
• /
• 제8권5호
• /
• pp.832-840
• /
• 1998

Experimental studies on the adaptive vibration control of composite beams have been performed using a piezoelectric actuator and the neuro-controller. The variations in natural frequencies of the specimen and the actuation characteristics of the piezoelectric actuator according to the delamination in the bonding layer have been studied. In addition, the simulation of adaptive vibration control has been performed for the composite specimens with delaminated piezoelectric actuator using neuro-controller. The hardware for the adaptive vibration control experiment was prepared. A DSP(digital signal processor) has been used as a digital controller. Using neuro-controller, the adaptive vibration control experiment has been performed. The vibration control results using the neuro-controller show that the present neuro-controller has good performance and robustness with the system parameter variations.

• 정보처리학회 논문지
• /
• 제13권2호
• /
• pp.13-17
• /
• 2024

본 논문에서는 규칙의 수를 줄여 간결한 지식 기반을 보장할 수 있는 합 기반의 전건부를 가지는 뉴로-퍼지 제어기를 제안하였다. 제안된 뉴로-퍼지 제어기는 모든 입력 변수의 AND 조합을 전건부로 하는 구조의 퍼지 규칙보다 더 큰 입력 영역을 커버하기 위해 전건부에 입력 퍼지 집합의 합집합 연산을 허용하였다. 이러한 뉴로-퍼지 제어기를 구성하기 위해 본 논문에서는 OR 및 AND 퍼지 뉴런으로 구성된 multiple-term unified logic processor (MULP)를 고려하였다. 이러한 OR 및 AND 퍼지 뉴런은 조정 가능한 연결 강도 집합을 가지므로 학습을 통하여 최적의 연결 강도 집합을 찾을 수 있다. 초기 최적화 단계에서 유전 알고리즘은 제안된 뉴로 퍼지 제어기의 최적화된 이진 구조를 구성하고, 이후 확률에 기반한 강화 학습은 성능 지수를 더욱 향상시켜서 유전 알고리즘에 의해 최적화된 제어기의 이진 연결을 개선하였다. 역진자 시스템을 제어하기 위한 모의실험 및 실험을 통해 제안된 방법의 유효성을 검증하였다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 춘계학술대회 논문집
• /
• pp.305-311
• /
• 2003

We propose a new technique of adaptive-neuro controller design to implement real-time control of robot manipulator, Unlike the well-established theory for the adaptive control of linear systems, there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of robot control. The proposed neuro control algorithm is one of loaming a model based error back-propagation scheme using Lyapunov stability analysis method. Through simulation, the proposed adaptive-neuro control scheme is proved to be a efficient control technique for real time control of robot system using DSPs(TMS320C50)

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.101-103
• /
• 2004

Expansible & Reconfigurable Neuro Informatics Engine(ERNIE) is effective in reconfigurability and extensibility. But ERNIE have the problem which have limited performance in initial network. To solve this problem, the constructive module using the reconfigurable ERNIE is implemented in simulation model. In this paper, simulation results on sonar data are showed that ERNIE using the constructive module obtains the better performance compared to ERNIE without it.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권12호
• /
• pp.804-810
• /
• 2004

There are two important things for the general purpose neural network processor. The first is a capability to build various structures of neural network, and the second is to be able to support suitable learning method for that neural network. Some way to process various learning algorithms is required for on-chip learning, because the more neural network types are to be handled, the more learning methods need to be built into. In this paper, an improved hardware structure is proposed to compute various kinds of learning algorithms flexibly. The hardware structure is based on the existing modular neural network structure. It doesn't need to add a new circuit or a new program for the learning process. It is shown that rearrangements of the existing processing elements can produce several neural network learning modules. The performance and utilization of this module are analyzed by comparing with other neural network chips.

• 한국정밀공학회지
• /
• 제14권6호
• /
• pp.90-98
• /
• 1997

A time-optimal control law for quick, strongly nonlinear systems has been developed and demonstrated. This procedure involves the utilzation of neural networks as state feedback controllers that learn the time-optimal control actions by means of an iterative minimization of both the final time and the final state error for the systems with constrained inputs and/or states. A neural identifier or a genetic algorithm identifier could be utilized for modeling the partially known systems and the unknown systems. The nature of neural networks as a parallel processor would circumvent the problem of "curwe of dimensionality". The control law has been demonstrated for both a torque input motor and a velocity input motor identified by a genetic algorithm called GENOCOPed GENOCOP.

• 정보처리학회논문지B
• /
• 제9B권4호
• /
• pp.429-436
• /
• 2002

인공 신경망을 실제적인 응용 분야에 적용하기 위하여 하드웨어 시스템으로 구현하는 것이 필요하다. 하드웨어로 구현하는 방법에는 현재 하이브리드 VLSI 신경망 칩으로 구현하는 것이 가장 유망하다. 이미 학습된 신경망을 하이브리드 신경망 칩을 사용하여 구현하는 경우 뉴런 출력과 가중치 값의 양자화 과정이 필수적이다. 이러한 과정은 신경망의 출력층 뉴런의 이미 학습된 출력에 비해 왜곡을 야기한다. 본 논문에서는 이러한 신경망의 출력 왜곡에 대한 통계적 특성을 자세하게 분석하였다. 분석 결과는 신경망의 출력 왜곡을 줄이기 위해서는 입력 벡터의 정규화와 가중치 값들이 작아야 한다는 사실을 보여 주었다. 시계열 데이터에 대한 실험 결과는 분석 결과를 고려하여 학습된 신경망들의 경우 실제로 뉴런 출력 및 가중치 값의 양자화로 인한 출력층 뉴런의 출력 왜곡이 상당히 줄어들 수 있음을 명확히 보여 주었다.

• Journal of Magnetics
• /
• 제17권1호
• /
• pp.27-32
• /
• 2012

Transcranial magnetic stimulation requires an electric field composed of dozens of V/m to achieve stimulation. The stimulation system is composed of a stimulation coil to form the electric field by charging and discharging a capacitor in order to save energy, thus requiring high-pressure kV. In particular, it is charged and discharged in capacitor to discharge through stimulation coil within a short period of time (hundreds of seconds) to generate current of numerous kA. A pulse-type magnetic field is formed, and eddy currents within the human body are triggered to achieve stimulation. Numerous pulse forms must be generated to initiate eddy currents for stimulating nerves. This study achieved high internal pressure, a high number of repetitions, and rapid switching of elements, and it implemented numerous control techniques via introduction of the half-bridge parallel load method. In addition it applied a quick, accurate, high-efficiency charge/discharge method for transcranial magnetic stimulation to substitute an inexpensive, readily available, commercial frequency condenser for a previously used, expensive, high-frequency condenser. Furthermore, the pulse repetition rate was altered to control energy density, and grafts compact, one-chip processor with simulation to stably control circuit motion and conduct research on motion and output characteristics.