• Nuclear Engineering and Technology
• /
• 제56권1호
• /
• pp.100-105
• /
• 2024

In this study, we propose an alternative approach using Artificial Neural Networks (ANN) for determining Mass Attenuation Coefficients (MAC) in various glass systems. This method takes into account the weights of glass compositions, density, and photon energy as input features. The ANN model was trained and tested on a dataset consisting of 650 data points and subsequently validated through a K-fold cross-validation procedure. Our findings demonstrate a high level of accuracy, with R² values ranging from 0.90 to 0.99. Additionally, the model exhibits robust extrapolation capabilities with an R² score of 0.87 for predicting MAC values in a new glass system. Furthermore, this approach significantly reduces the need for costly and time-consuming computations and experiments, making it a potential tool for selecting materials for effective radiation protection.

• 디지털융복합연구
• /
• 제17권7호
• /
• pp.285-292
• /
• 2019

PC, SNS, IoT의 대중화로 수많은 데이터가 생성되고 그 양은 기하급수적으로 증가하고 있다. 거대한 양의 데이터를 활용하는 방법으로 인공신경망 학습은 최근 많은 분야에서 주목받는 주제이다. 인공신경망 학습은 음성인식, 이미지 인식에서 엄청난 잠재력을 보였으며 더 나아가 의료진단, 인공지능 게임 및 얼굴인식 등 다양하고 복잡한 곳에 광범위하게 적용된다. 인공신경망의 결과는 실제 인간을 능가할 정도로 정확성을 보이고 있다. 이러한 많은 이점에도 불구하고 인공신경망 학습에는 여전히 프라이버시 문제가 존재한다. 인공신경망 학습을 위한 학습 데이터에는 개인의 민감한 정보를 포함한 다양한 정보가 포함되어 악의적인 공격자로 인해 프라이버시가 노출될 수 있다. 공격자가 학습하는 도중 개입하여 학습이 저하되거나 학습이 완료된 모델을 공격할 때 발생하는 프라이버시 위험이 있다. 본 논문에서는 최근 제안된 신경망 모델의 공격 기법과 그에 따른 프라이버시 보호 방법을 분석한다.

• Earthquakes and Structures
• /
• 제14권5호
• /
• pp.425-436
• /
• 2018

The design of seismically isolated structures considering the stochastic nature of excitations, base isolators' design parameters, and superstructure properties requires robust reliability analysis methods to calculate the failure probability of the entire system. Here, by applying artificial neural networks, we proposed a robust technique to accelerate the estimation of failure probability of equipped isolated structures. A three-story isolated building with susceptible facilities is considered as the analytical model to evaluate our technique. First, we employed a sensitivity analysis method to identify the critical sources of uncertainty. Next, we calculated the probability of failure for a particular set of random variables, performing Monte Carlo simulations based on the dynamic nonlinear time-history analysis. Finally, using a set of designed neural networks as a surrogate model for the structural analysis, we assessed once again the probability of the failure. Comparing the obtained results demonstrates that the surrogate model can attain precise estimations of the probability of failure. Moreover, our proposed approach significantly increases the computational efficiency corresponding to the dynamic time-history analysis of the structure.

• Computers and Concrete
• /
• 제24권6호
• /
• pp.555-560
• /
• 2019

During the application of shotcrete, a part of the concrete bounces back after hitting to the surface, the reinforcement or previously sprayed concrete. This rebound material is definitely not added to the mixture and considered as waste. In this study, a deep neural network model was developed to predict the rebound material during shotcrete application. The factors affecting rebound and the datasets of these parameters were obtained from previous experiments. The Long Short-Term Memory (LSTM) architecture of the proposed deep neural network model was used in accordance with this data set. In the development of the proposed four-tier prediction model, the dataset was divided into 90% training and 10% test. The deep neural network was modeled with 11 dependents 1 independent data by determining the most appropriate hyper parameter values for prediction. Accuracy and error performance in success performance of LSTM model were evaluated over MSE and RMSE. A success of 93.2% was achieved at the end of training of the model and a success of 85.6% in the test. There was a difference of 7.6% between training and test. In the following stage, it is aimed to increase the success rate of the model by increasing the number of data in the data set with synthetic and experimental data. In addition, it is thought that prediction of the amount of rebound during dry-mix shotcrete application will provide economic gain as well as contributing to environmental protection.

• 대한기계학회논문집A
• /
• 제37권11호
• /
• pp.1397-1405
• /
• 2013

본 연구에서 탑승자 머리 보호를 위한 센터 필라 트림의 리브 패턴 최적설계는 두 가지 방법에 의해 수행된다. 첫째는 실험계획법과 반응표면법을 이용한 근사최적화 기법으로써, 상대적으로 큰 비중을 차지하는 해석비용 저감을 위하여 근사모델 구성에 필요한 최소한의 해석만을 수행하고 실제 최적화 과정에는 구성된 모델을 이용함으로써 근사적으로 최적 점을 찾아가는 방법이다. 하지만 이러한 방법은 시행착오적인 반복과정을 거쳐야 하는 단점이 있다. 따라서 저자들의 선행연구에서 제안한 순차적 실험계획법과 인공신경망을 이용하여 인자의 상한 또는 하한에 걸리지 않는 근사최적 해를 체계적인 반복과정을 통해 도출하고자 하며, 이를 수학적인 예제와 구조물 문제에 적용함으로써 실용성을 확인하고자 한다.

• 조명전기설비학회논문지
• /
• 제17권5호
• /
• pp.43-50
• /
• 2003

본 논문은 신경회로망을 이용하여 변압기 사고검출 기법을 제안하였다. 계전기 정동작을 위하여 전력용 변압기의 외부사고와 돌입현상은 포화현상이 고려된 EMTP/ATP를 이용하였고, 내부사고는 EMTP/BCTRAN를 이용하여 얻은 전류 데이타를 신경회로망의 사고검출 성능으로 평가하였다. 신경회로망의 입력지수로는 변압기 양단전류를 FFT로 주파수 분석하여 얻은 억제전류와 동작전류의 고조파 비의 크기를 이용하였고, 외부사고 시 억제전류값이 크게 나타나는 것을 이용하기 위해 억제전류를 동작전류로 나눈값을 계전기 입력으로 사용하였고, 학습알고리즘은back-propagation을 사용하였다. 실 계통에 적용하고 있는 변압기 보호용 계전기의 특성을 신경회로망의 검출성능으로 테스트한 결과 제안된 기법이 뛰어남이 확인되었다.

• 조명전기설비학회논문지
• /
• 제18권6호
• /
• pp.37-44
• /
• 2004

전력계통분야의 복합 대형화에 유연한 대처와 전력조류의 최적화 도모를 위해 사용되는 FACTS(Flexible AC Transmission System)기기 중 가장 유용한 UPFC(Unified Power Flow Controller)는 선로의 전압을 임의의 크기와 위상을 갖도록 제어하여 선로로 전송되는 유ㆍ무효전력을 총체적으로 보상하는 기능을 갖는다. 이런 UPEC가 계통에 연계되어 운영된다면 송전선로 매개변수가 변하기 때문에 계통의 영향을 많이 받는 거리계전기는 불필요한 오동작이 발생하게 된다. 즉 거리계전기에서 바라본 임피던스 영역(Impedance Zone)이 송전선로에 UPFC 연계시 각각의 보상 값에 의해 상당한 변화를 보임으로, 기존의 방식으로 정정된 Relay Setting Zone과 Adaptive Setting Zone은 현저한 오차가 발생하게 된다. 그러므로 계통에 연계된 UPFC의 운전 조건을 고려한 거리계전기 보호구간의 재설정이 필요하게 된다. 따라서 본 논문의 목적은 학습이 가능한 신경회로망(ANN)을 이용하여 거리계전기 동작의 신속성(Speed)을 기본으로 전력계통의 다양한 환경에 대해 거리계전기 응동 특성을 향상시키는데 있다. 학습 방법으로는 정적 및 동적인 비선형 시스템의 인식과 다변수 시스템에 적용 가능한 역전파 알고리즘(Back-propagation Algorithm)을 사용했다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.687-690
• /
• 2000

Lately, many studies have been progressed for the protection human's lives and property as holding in check accidents happened by human's carelessness or mistakes. One part of these is the development of an autonomouse vehicle. General control method of vision-based autonomous vehicle system is to determine the navigation direction by analyzing lane images from a camera, and to navigate using proper control algorithm. In this paper, characteristic points are abstracted from lane images using lane recognition algorithm with sobel operator. And then the vehicle is controlled using two proposed auto-steering algorithms. Two steering control algorithms are introduced in this paper. First method is to use the geometric relation of a camera. After transforming from an image coordinate to a vehicle coordinate, a steering angle is calculated using Ackermann angle. Second one is using a neural network algorithm. It doesn't need to use the geometric relation of a camera and is easy to apply a steering algorithm. In addition, It is a nearest algorithm for the driving style of human driver. Proposed controller is a multilayer neural network using Levenberg-Marquardt backpropagation learning algorithm which was estimated much better than other methods, i.e. Conjugate Gradient or Gradient Decent ones.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.685-686
• /
• 2007

This paper presents an application of power system fault diagnostic algorithm for the PEFP Proton Accelerator Research Center using neural network. Proposed fault diagnostic system is constructed by the radial basis function (RBF) neural network because it has the capabilities of the pattern classification and function approximation of any nonlinear function. Proposed system identifies faulted section in the power system based on information about the operation of protection devices such as relays and circuit breakers. In this paper, parameters of the RBF neural networks are tuned by the GA-TS algorithm, which has the global optimal solution searching capabilities. To show the validity of the proposed method, proposed algorithm has been tested with a practical power system in Proton Accelerator Research Center of PEFP.

• Smart Structures and Systems
• /
• 제30권4호
• /
• pp.421-432
• /
• 2022

Regarding the high significance of correct pan evaporation modeling, this study introduces two novel neuro-metaheuristic approaches to improve the accuracy of prediction for this parameter. Vortex search algorithms (VSA), sunflower optimization (SFO), and stochastic fractal search (SFS) are integrated with a multilayer perceptron neural network to create the VSA-MLPNN, SFO-MLPNN, and SFS-MLPNN hybrids. The climate data of Arcata-Eureka station (operated by the US environmental protection agency) belonging to the years 1986-1989 and the year 1990 are used for training and testing the models, respectively. Trying different configurations revealed that the best performance of the VSA, SFO, and SFS is obtained for the population size of 400, 300, and 100, respectively. The results were compared with a conventionally trained MLPNN to examine the effect of the metaheuristic algorithms. Overall, all four models presented a very reliable simulation. However, the SFS-MLPNN (mean absolute error, MAE = 0.0997 and Pearson correlation coefficient, R_P = 0.9957) was the most accurate model, followed by the VSA-MLPNN (MAE = 0.1058 and R_P = 0.9945), conventional MLPNN (MAE = 0.1062 and R_P = 0.9944), and SFO-MLPNN (MAE = 0.1305 and R_P = 0.9914). The findings indicated that employing the VSA and SFS results in improving the accuracy of the neural network in the prediction of pan evaporation. Hence, the suggested models are recommended for future practical applications.