• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.1
• /
• pp.103-110
• /
• 1998

The modeling of load characteristics is a difficult problem because of uncertainty of load. This research uses artificial neural networks which can approximate nonlinear problem to represent load characteristics. After the selection of typical load, active and reactive power for the variation of voltage and frequency is obtained from experiments. We constructed and learned ANN based on these data for component load identification. The learned ANN identified load characteristics for other voltage and/or frequency variation. In addition, the results of component load identification are presented to demonstrate the potentiality of the proposed method.method.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

• Journal of Aerospace System Engineering
• /
• v.13 no.6
• /
• pp.17-25
• /
• 2019

PHM (Prognostics and Health Management) of aircraft engines is applied to predict the remaining useful life before failure or the lifetime limit. There are two methods to establish a predictive model for this: The physics-based method and the data-driven method. The physics-based method is more accurate and requires less data, but its application is limited because there are few models available. In this study, the data-driven method is applied, in which a multi-layer perceptron based neural network algorithms is applied for the life prediction. The neural network is trained using the data sets virtually made by the C-MAPSS code developed by NASA. After training the model, it is applied to the test data sets, in which the confidence interval of the remaining useful life is predicted and validated by the actual value. The performance of proposed method is compared with previous studies, and the favorable accuracy is found.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.1
• /
• pp.32-42
• /
• 2000

This paper presents an on-line learning algorithm for sequential construction of generalized radial basis function networks (GRBFNs) to model nonlinear systems from empirical data. The GRBFN, an extended from of standard radial basis function (RBF) networks with constant weights, is an architecture capable of representing nonlinear systems by smoothly integrating local linear models. The proposed learning algorithm has a two-stage learning scheme that performs both structure learning and parameter learning. The structure learning stage constructs the GRBFN model using two construction criteria, based on both training error criterion and Mahalanobis distance criterion, to assign new hidden units and the linear local models for given empirical training data. In the parameter learning stage the network parameters are updated using the gradient descent rule. To evaluate the modeling performance of the proposed algorithm, simulations and their results applied to two well-known benchmarks are discussed.

• IE interfaces
• /
• v.10 no.1
• /
• pp.37-45
• /
• 1997

본 연구에서는 웨이퍼 팹공정에서 웨이퍼 로트들이 뱃치공정을 위해 확률적으로 도착되는 상황에서 최적 뱃치크기를 결정하는 뱃칭문제를 다루고 있다. 뱃치공정이란 여러 개의 웨이퍼 로트들을 기계의 용량을 넘지 않는 한도 내에서 하나의 뱃치로 구성하여 한꺼번에 가공하는 공정을 말한다. 목적함수는 생산율을 높이고 재공재고 및 사이클타임을 줄이기 위해 웨이퍼 로트들의 평균 대기시간의 최소화를 채택하였다. 문제의 해결을 위해서, 확률적인 상황변동 하에서 실시간 제어를 위해 많이 활용되고 있는 신경회로망 중 다층 퍼셉트론을 이용한 뱃치크기 결정 모델을 제시하였다. 제시한 모델의 효율성을 확인하기 위해 기존에 잘 알려져 있는 최저뱃치크기(MBS) 규칙과 실험, 비교하였다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.101-105
• /
• 2005

호남지역에 대한 대설특보 예보를 위한 통계모형 개발을 수행하였다. 일 신적설량에 따라 세법주(0: 비발생, 1: 대설주의보, 2: 대설경보)로 구분되는 순서형 자료 형태를 지니고 있다. 두가지 통계 모형(다등급 로지스틱 회귀모형, 신경회로망 모형)을 고려하였으며, 수치모델 출력자료를 이용한 역학-통계모형 기법의 하나인 MOS(model output statistics)를 적용하여 축적된 수치모델 예보자료와 관측치의 관계를 통계모형식으로 추정하여 예측모형을 개발하였다. 군집분석을 사용하여 훈련자료와 검증자료를 구분하였으며, 예보치 생성을 위하여 문턱치를 고려하였다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.5
• /
• pp.29-34
• /
• 2002

This study presents the process of the continuous-time system identification for unknown nonlinear systems. The Radial Basis Function(RBF) error filtering identification model is introduced at first. This identification scheme includes RBF network to approximate unknown function of nonlinear system which is structured by affine form. The neural network is trained by the adaptive law based on Lyapunov synthesis method. The identification scheme is applied to engine and the performance of RBF error filtering Identification model is verified by the simulation with a three-state engine model. The simulation results have revealed that the values of the estimated function show favorable agreement with the real values of the engine model. The introduced identification scheme can be effectively applied to model-based nonlinear control.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.2
• /
• pp.75-84
• /
• 1994

기계가공프로세스에서 절삭공구의 마멸과 채터진동은 공작기계의 가동율과 생산성을 크게 저해하는 요인이 되고 있다. 본 연구에서는 공구마멸과 채터현상이 혼재하는 상황에서, 이들 두 현상을 동시에 검출하는데, AE 및 가속도센서에서 검출된 신호와 AR계수 및 주파수대역 평균에너지를 특징입력으로 하는 인공신경회로망을 이용하였다. 그 결과, 공구마멸과 채터현상에 대응하는 서로 다른 신호특징의 차이를 동시에 식별하는 데 인공신경 회로망의 유용성을 입증하였으며, 시계열모델의 AR계수(70 .approx. 90%)보다는 주파수대역에너지법의 평균에너지 (80 .approx. 100%)를 신경회로망의 특징입력으로 하는 경우가 높은 성공률을 나타내었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.3
• /
• pp.197-205
• /
• 1992

In this paper object recognition using neural network is studied. The recognition is accomplished by matching linear line segments which are formed by local features extracted from the curvature points. Since there is similarities among segments. The boundary of models is not distinct in feature space. Due to these indistinctness the ambiguity of recognition occurs, and the recognition rate becomes degraded according to the limitation of boundary decision capability of neural network for similar of features. Object recognition and to improve recognition rate. Local features are used to represent the object effectively. The validity of the object recognition system is demonstrated by experiments for the occluded and varied objects.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.173-180
• /
• 2002

The virtual cell loss rate was introduced for the training pattern of the neural network in the VOB(Virtual Output Buffer) model. The VOB model shows that the neural network can find the connection admission boundary without the real cell loss rate. But the VOB model tends to overestimate the cell loss rate, so the utilization of network is low. In this paper, we uses the reference curve of the cell loss rate, which contains the information about the cell loss rate at the connection admission boundary. We process the patterns of the virtual cell loss rate using the reference curve, We performed the simulation with two major ATM traffic classes. One is On-Off traffic class that has the traffic characteristic of LAN data and other is Auto-Regressive traffic class that has the traffic characteristic of a video image communication.