• Structural Engineering and Mechanics
• /
• 제67권2호
• /
• pp.105-113
• /
• 2018

To improve the prediction accuracy of the strong-unloading rock slope performance and obtain the range of variation in the slope displacement, a new displacement time-series prediction model is proposed, called the fuzzy information granulation (FIG)-genetic algorithm (GA)-back propagation neural network (BPNN) model. Initially, a displacement time series is selected as the training samples of the prediction model on the basis of an analysis of the causes of the change in the slope behavior. Then, FIG is executed to partition the series and obtain the characteristic parameters of every partition. Furthermore, the later characteristic parameters are predicted by inputting the earlier characteristic parameters into the GA-BPNN model, where a GA is used to optimize the initial weights and thresholds of the BPNN; in the process, the numbers of input layer nodes, hidden layer nodes, and output layer nodes are determined by a trial method. Finally, the prediction model is evaluated by comparing the measured and predicted values. The model is applied to predict the displacement time series of a strong-unloading rock slope in a hydropower station. The engineering case shows that the FIG-GA-BPNN model can obtain more accurate predicted results and has high engineering application value.

• 한국산학기술학회논문지
• /
• 제22권2호
• /
• pp.651-658
• /
• 2021

풀림 방지 코팅 볼트는 주로 자동차 안전 관련 부품을 결합하는 데 사용되므로 안전성 유지를 위해 코팅 결함을 사전에 감지해야 한다. 이를 위해 이전 연구 [CNN 및 모델 시각화 기법을 사용한 코팅 볼트 불량 판별]에서는 합성곱 신경망을 사용했다. 이때 합성곱 신경망은 데이터 수가 많을수록 이미지 패턴 및 특성 분석 정확도가 증가하지만 그에 따라 학습시간이 증가한다. 또한 확보 가능한 코팅 볼트 샘플이 한정적이다. 본 연구에서는 이전 연구에 전이학습을 추가적으로 적용해 데이터 개수가 적은 경우에도 코팅 결함에 대해 정확한 분류를 하고자 한다. 전이학습을 적용할 때 학습 데이터 수와 사전 학습 데이터 ImageNet 간의 유사성을 고려해 분류층만 학습했다. 데이터 학습에는 전역 평균 풀링, 선형 서포트 벡터 머신 및 완전 연결 계층과 같은 분류층을 적용했으며, 고려한 모델 중 완전 연결 계층 방법의 분류층이 가장 높은 95% 정확도를 가진다. 추가적으로 마지막 합성곱층과 분류층을 미세 조정하면 정확도는 97%까지 향상된다. 전이학습 및 미세 조정을 이용하면 선별 정확도를 향상시킴은 물론 이전보다 학습 소요시간을 절반으로 줄일 수 있음을 보였다.

• 한국광학회지
• /
• 제21권4호
• /
• pp.161-167
• /
• 2010

단축 이방성 매질에서 다른 단축 이방성 매질로 진행하는 빛의 유효투과계수 표현을 유도하였다. 두 이방성 매질 사이에 가상의 등방성 매질을 도입한 후, 가상의 등방성 매질 내의 다중반사 효과를 반영함으로써 두 단축 이방성 매질간의 경계면에서 유효 투과계수 표현을 제시하였다. 균일하지 않은 단축 이방성 매질을 얇고 균일한 단축 이방성 층들의 합으로 대치하여 각각의 두 경우에 대하여 투과하는 빛의 편광상태 변화를 계산한 후 비교함으로써 이 방법의 타당성을 확인하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제18권3호
• /
• pp.474-484
• /
• 2017

This paper studies the applicability of an efficient numerical model based on artificial neural networks (ANNs) to predict the dynamic responses of the wing structure of an airplane due to atmospheric turbulence in the time domain. The turbulence velocity is given in the form of a stationary Gaussian random process with the von Karman power spectral density. The wing structure is modeled by a classical beam considering bending and torsional deformations. An unsteady vortex-lattice method is applied to estimate the aerodynamic pressure distribution on the wing surface. Initially, the trim condition is obtained, then structural dynamic responses are computed. The numerical solution of the wing structure's responses to a random turbulence profile is used as a training data for the ANN. The current ANN is a three-layer network with the output fed back to the input layer through delays. The results from this study have validated the proposed low-cost ANN model for the predictions of dynamic responses of wing structures due to atmospheric turbulence. The accuracy of the predicted results by the ANN was discussed. The paper indicated that predictions for the bending moments are more accurate than those for the torsional moments of the wing structure.

• International journal of advanced smart convergence
• /
• 제10권1호
• /
• pp.105-116
• /
• 2021

In order to preserve the seeds of excellent Hanwoo(Korean traditional cattle) and secure quality competitiveness in the infinite competition with foreign imported beef, production of high-quality Hanwoo beef is absolutely necessary. %IMF (Intramuscular Fat Percentage) is one of the most important factors in evaluating the value of high-quality meat, although standards vary according to food culture and industrial conditions by country. Therefore, it is required to develop a %IMF estimation algorithm suitable for Hanwoo. In this study, we proposed a method of estimating %IMF of Hanwoo using CNN in ultrasound images. First, the proposed method classified the chemically measured %IMF into 10 classes using k-means clustering method to apply CNN. Next, ROI images were obtained at regular intervals from each ultrasound image and used for CNN training and estimation. The proposed CNN model is composed of three stages of convolution layer and fully connected layer. As a result of the experiment, it was confirmed that the %IMF of Hanwoo was estimated with an accuracy of 98.2%. The correlation coefficient between the estimated %IMF and the real %IMF by the proposed method is 0.97, which is about 10% better than the 0.88 of the previous method.

• 자동차안전학회지
• /
• 제14권3호
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.170-170
• /
• 2020

Due to the development of technologies, complex computation of huge data set is possible with a prevalent personal computer. Therefore, machine learning methods have been widely applied in the hydrologic field such as regression-based regional frequency analysis (RFA). The main purpose of this study is to compare two frameworks of RFA based on the artificial neural network (ANN) models: quantile regression technique (QRT-ANN) and parameter regression technique (PRT-ANN). As an output layer of the ANN model, the QRT-ANN predicts quantiles for various return periods whereas the PRT-ANN provides prediction of three parameters for the generalized extreme value distribution. Rainfall gauging sites where record length is more than 20 years were selected and their annual maximum rainfalls and various hydro-meteorological variables were used as an input layer of the ANN model. While employing the ANN model, 70% and 30% of gauging sites were used as training set and testing set, respectively. For each technique, ANN model structure such as number of hidden layers and nodes was determined by a leave-one-out validation with calculating root mean square error (RMSE). To assess the performances of two frameworks, RMSEs of quantile predicted by the QRT-ANN are compared to those of the PRT-ANN.

• Steel and Composite Structures
• /
• 제44권6호
• /
• pp.867-882
• /
• 2022

Predicting the compressive strength of concrete (CSoC) is of high significance in civil engineering. The CSoC is a highly dependent and non-linear parameter that requires powerful models for its simulation. In this work, two novel optimization techniques, namely evaporation rate-based water cycle algorithm (ER-WCA) and equilibrium optimizer (EO) are employed for optimally finding the parameters of a multi-layer perceptron (MLP) neural processor. The efficiency of these techniques is examined by comparing the results of the ensembles to a conventionally trained MLP. It was observed that the ER-WCA and EO optimizers can enhance the training accuracy of the MLP by 11.18 and 3.12% (in terms of reducing the root mean square error), respectively. Also, the correlation of the testing results climbed from 78.80% to 82.59 and 80.71%. From there, it can be deduced that both ER-WCA-MLP and EO-MLP can be promising alternatives to the traditional approaches. Moreover, although the ER-WCA enjoys a larger accuracy, the EO was more efficient in terms of complexity, and consequently, time-effectiveness.

• Computers and Concrete
• /
• 제15권6호
• /
• pp.951-972
• /
• 2015

The focus of the present study is to investigate both local and global behaviour of a precast concrete sandwich panel. The selected prototype consists of two reinforced concrete layers coupled by a system of cold-drawn steel profiles and one intermediate layer of insulating material. High-definition nonlinear finite element (FE) models, based on 3D brick and 2D interface elements, are used to assess the capacity of this technology under shear, tension and compression. Geometrical nonlinearities are accounted via large displacement-large strain formulation, whilst material nonlinearities are included, in the series of simulations, by means of Von Mises yielding criterion for steel elements and a classical total strain crack model for concrete; a bond-slip constitutive law is additionally adopted to reproduce steel profile-concrete layer interaction. First, constitutive models are calibrated on the basis of preliminary pull and pull-out tests for steel and concrete, respectively. Geometrically and materially nonlinear FE simulations are performed, in compliance with experimental tests, to validate the proposed modeling approach and characterize shear, compressive and tensile response of this system, in terms of global capacity curves and local stress/strain distributions. Based on these experimental and numerical data, the structural performance is then quantified under various loading conditions, aimed to reproduce the behaviour of this solution during production, transport, construction and service conditions.

• 한국지능시스템학회논문지
• /
• 제25권1호
• /
• pp.97-104
• /
• 2015

An 'associative cube', a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.