• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2977-2979
• /
• 1999

본 논문에서는 MEBP(Modified Error Back-Propagation) 학습 규칙을 간단한 비선형 회로를 이용하여 구현하였다. 인공 신경 회로망(ANNs : Artificial Neural Networks)은 많은 수의 뉴런을 필요하기 때문에 표준 CMOS 기술을 이용하는 간단한 비선형 시냅스(synapse) 회로는 인공 신경 회로망 구현에 적합하다. 학습회로는 비선형 시냅스 회로. 시그모이드(sigmoid) 회로. 그리고 선형 곱셈기로 구성되어 있다. 학습 회로의 출력은 각 입력 패턴에 따라 유일한 값으로 결정되어진다. 제안한 학술회로를 $2{\times}2{\times}1$과 $2{\times}3{\times}1$ 다층 feedforward 신경 회로망 모델에 적용하였다. MEBP 하드웨어 구현은 HSPICE 회로 시뮬레이터를 이용하여 검증하였다. 제안한 학술 회로는 on-chip 학습회로를 포함한 대규모 신경회로망 구현에 매우 적합하리라 예상된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2974-2976
• /
• 1999

본 논문에서는 단일패턴과 다중패턴 학습이 가능한 FNNs(Feedforward Neural Networks)을 하드웨어로 구현하는데 필요한 학습방안을 제안한다. 제안된 학습방안은 기존의 하드웨어 구현에 이용되는 방식과는 전혀 다른 방식이며, 오히려 기존의 소프트웨어 학습방식과 유사하다. 기존의 하드웨어 구현에서 사용되는 방법은 오프라인 학습이나 단일패턴 온 칩(on-chip) 학습방식인데 반해, 제안된 학습방식은 단일/다중패턴은 칩 학습방식으로 다층 FNNs 회로와 학습회로 사이에 스위칭 회로를 넣어 구현되었으며, FNNs의 학습회로는 선형 시냅스 회로와 선형 곱셈기 회로를 사용하여MEBP(Modified Error Back-Propagation) 학습규칙을 구현하였다. 제안된 방식은 기존의 CMOS 공정으로 구현되었고 HSPICE 회로 시뮬레이터로 그 동작을 검증하였다 구현된 FNNs은 어떤 학습패턴 쌍에 의해 유일하게 결정되는 출력 전압을 생성한다. 제안된 학습방안은 향후 학습 가능한 대용량 신경망의 구현에 매우 적합하리라 예상된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.835-837
• /
• 1996

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network(Back-propagation) is proposed. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.

• 한국항해학회지
• /
• 제21권4호
• /
• pp.21-28
• /
• 1997

Along with the rapid growth of shipping and transportation , the size of a ship larger and larger. Low speed maneuverabililty of a full ship has been received a great deal of attention concerting about the navigation safety, especially in the harbour area of waterway. And, the iperation of the full ship in harbour area is one fo tehmost difficult technique. Usually highly experienced experts can make a suitable decision considering various propeller ,rudder actions and environmental conditions. The Artificial Neural Network is applied to the automatic berthing control of a ship. The teaching data are made by the berthing simulation of a ship on the computer. And, the layer neural network is used and the 'Error Back-Propagation Algorithm' is used to teach the neural network. Finally, it is shown that the berthing control is successfully done by the established neural network.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2001년도 학술발표회 논문집(I)
• /
• pp.45-51
• /
• 2001

The daily inflow is apparently one of nonlinear and complicated phenomena. The nonlinear and complexity make it difficult to model the prediction of daily flow, but attractive to try the neural networks approach which contains inherently nonlinear schemes. The study focuses on developing the forecasting models of daily inflows to a large dam site using neural networks. In order to reduce the error caused by high or low outliers, the back propagation algorithm which is one of neural network structures is modified by combining a regression algorithm. The study indicates that continuous forecasting of a reservoir inflow in real time is possible through the use of modified neural network models. The positive effect of the modification using tole regression scheme in BP algorithm is showed in the low and high ends of inflows.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 1992년도 특별강연 및 추계학술발표 개요집
• /
• pp.91-95
• /
• 1992

The resistance spot welding process has been extensively used for joining of sheet metals, which are subject to variation of many process variables. Many qualitive analyses of sampled process variables have been attempted to predict nugget size. In this paper, dynamic resistance and electrode movement signal which is a good indicative of the nugget size was examined by introducing an artificial neural network estimator. An artificial neural feedforward network with back-propagation of error was applied for the estimation of the nugget size. The prediction by the neural network is in good agreement with the actual nugget size for resistance spot welding of galvanized steel. The results are quite promising in that the quantitative estimation of the invisible nugget size can be achieved without conventional destructive testing of welds.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2001년도 춘계학술대회 논문집
• /
• pp.243-248
• /
• 2001

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Thus, in this paper, an Evolving Neural Network Controller(ENNC) without Error Back Propagation(EBP) is presented. An ENNC is described simply by genetic representation using an encoding strategy for types and slope values of each active functions, biases, weights and so on. By an evolutionary programming which has three genetic operation; selection, crossover and mutation, the predetermine controller is optimally evolved by updating simultaneously the connection patterns and weights of the neural networks. The performances of the proposed ENNC(PENNC) are compared with the ones of conventional optimal controller and the conventional evolving neural network controller(CENNC) through the simulation and experimental results. And we showed that the finally optimized PENNC was very useful in the stabilization control of an IP system.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2001년도 추계학술대회논문집 II
• /
• pp.1067-1072
• /
• 2001

In this study, the vibration diagnosis program for onboard machinery has been developed. The developed program includes signal monitoring module, system diagnosis module, and system modification module. The signal monitoring module is to monitor the vibration signal in time and frequency domains. And the system diagnosis module, which is developed by using Neural Network with error back propagation algorithm, can detect the abnormal symptom indicating the malfunction of the machinery onboard ships. The investigations of the developed system are presented through the experiment using Rotor Kit. Abnormal vibration signals are created by adding additional weight, manually misaligning the shaft, and loosening the bolts.

• 융합신호처리학회논문지
• /
• 제16권4호
• /
• pp.134-138
• /
• 2015

본 논문은 심장질환을 비침습적 방법으로 빠르고 쉽게 진단할 수 있도록 심음을 이용하는 방법에 대한 가능성을 찾는 것이다. 일반적으로 심음의 분류를 위하여 심음을 분리한 후에 특징파라미터를 추출하는 과정을 거치지 않고, 심음 분리에 사용되는 Shannon 엔트로피로 정규화하여 신경회로망의 입력으로 사용하였다. 심장질환에 따른 심잡음 분류를 위하여 Scaled conjugate gradient 역전파 알고리즘을 이용하여 신경회로망 분류기를 구현하였다. 정상 심음과 심장 질환의 경우 5가지를 포함하여 6종류의 심잡음에 대하여 분류가 가능함을 확인하였다.

• International journal of advanced smart convergence
• /
• 제10권2호
• /
• pp.175-186
• /
• 2021

We have studied the speed regulation of the permanent magnet synchronous motor (PMSM) servo system in this paper. To optimize the PMSM servo system's speed-control performance with disturbances, a non-linear speed-control technique using a back-propagation neural network (BP-NN) algorithm forthe controller design of the PMSM speed loop is introduced. To solve the slow convergence speed and easy to fall into the local minimum problem of BP-NN, we develope an improved BP-NN control algorithm by limiting the range of neural network outputs of the proportional coefficient Kp, integral coefficient Ki of the controller, and add adaptive gain factor β, that is the internal gain correction ratio. Compared with the conventional PI control method, our improved BP-NN control algorithm makes the settling time faster without static error, overshoot or oscillation. Simulation comparisons have been made for our improved BP-NN control method and the conventional PI control method to verify the proposed method's effectiveness.