범밀도이론함수(Density Functional Theory, DFT) 기반의 제일원리전산모사는 기저상태의 DFT 에너지를 구하는데 많은 시간소요 및 전산자원을 소모하였다. 이러한 막대한 전산자원의 소모는 DFT 계산에서 고려할 원자수를 수 백개 이 하로 제한되게 되었으며, 이를 해결하기 위해서는 전자구조 계산이 아닌 원자의 환경 내에 원자간 상호작용을 정의 (Force Field, 힘장)하고 이를 통해 주어진 조성 혹은 구조에 따른 에너지를 빠르게 예측 할 수 있어야 한다. 본 논문에서 는 Behler-Parrinello가 제시한 인공신경망 모델을 활용해 인공지능 다원계 힘장을 개발하고 코발트-구리 산화물의 조성에 따른 에너지를 예측하고 안정한 구조를 탐색하는 연구를 수행하였다. 인공신경망 기술로 부터 구리-코발트 산화물에 대 해 15.7 meV/atom의 에너지 오차와 단위거리당 힘 103.6 meV/Å의 정확도를 가지는 인공신경망 포텐셜을 개발하였다. 이 방법으로 빠르고 정확하게 CuCoO 표면구조의 산소 결함률에 따른 생성에너지를 계산할 수 있었고, 에너지 컨벡스 홀을 도시 조성에 따른 안정한 구조를 예측하였다.

Final disposal of radioactive waste generated from Nuclear Power Plant (NPP) requires the detailed information about the characteristics and the quantities of radionuclides in waste package. Most of these radionuclides are difficult to measure and expensive to assay. Thus it is suggested to the indirect method by which the concentration of the Difficult-to-Measure (DTM) nuclide is estimated using the correlations of concentration - it is called the scaling factor - between Easy-to-Measure (Key) nuclides and DTM nuclides with the measured concentration of the Key nuclide. In general, the scaling factor is determined by the log mean average (LMA) method and the regression method. However, these methods are inadequate to apply to fission product nuclides and some activation product nuclides such as 14 and 90 . In this study, the artificial neural network (ANN) method is suggested to improve the conventional SF determination methods - the LMA method and the regression method. The root mean squared errors (RMSE) of the ANN models are compared with those of the conventional SF determination models for 14 and 90 in two parts divided by a training part and a validation part. The SF determination models are arranged in the order of RMSEs as the following order: ANN model

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.