• Steel and Composite Structures
• /
• 제31권5호
• /
• pp.529-539
• /
• 2019

Current paper deals with thermoelastic static and free vibrational behaviors of axisymmetric thick cylinders reinforced with functionally graded (FG) randomly oriented graphene subjected to internal pressure and thermal gradient loads. The heat transfer and mechanical analyses of randomly oriented graphene-reinforced nanocomposite (GRNC) cylinders are facilitated by developing a weak form mesh-free method based on moving least squares (MLS) shape functions. Furthermore, in order to estimate the material properties of GRNC with temperature dependent components, a modified Halpin-Tsai model incorporated with two efficiency parameters is utilized. It is assumed that the distributions of graphene nano-sheets are uniform and FG along the radial direction of nanocomposite cylinders. By comparing with the exact result, the accuracy of the developed method is verified. Also, the convergence of the method is successfully confirmed. Then we investigated the effects of graphene distribution and volume fraction as well as thermo-mechanical boundary conditions on the temperature distribution, static response and natural frequency of the considered FG-GRNC thick cylinders. The results disclosed that graphene distribution has significant effects on the temperature and hoop stress distributions of FG-GRNC cylinders. However, the volume fraction of graphene has stronger effect on the natural frequencies of the considered thick cylinders than its distribution.

• Steel and Composite Structures
• /
• 제44권1호
• /
• pp.49-63
• /
• 2022

This study aims to develop ensemble machine learning (ML) models for estimating the peak floor acceleration and maximum top drift of steel moment frames. For this purpose, random forest, adaptive boosting, gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) models were considered. A total of 621 steel moment frames were analyzed under 240 ground motions using OpenSees software to generate the dataset for ML models. From the results, the GBRT and XGBoost models exhibited the highest performance for predicting peak floor acceleration and maximum top drift, respectively. The significance of each input variable on the prediction was examined using the best-performing models and Shapley additive explanations approach (SHAP). It turned out that the peak ground acceleration had the most significant impact on the peak floor acceleration prediction. Meanwhile, the spectral accelerations at 1 and 2 s had the most considerable influence on the maximum top drift prediction. Finally, a graphical user interface module was created that places a pioneering step for the application of ML to estimate the seismic demands of building structures in practical design.

• 한국공간구조학회논문집
• /
• 제23권3호
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Geomechanics and Engineering
• /
• 제37권4호
• /
• pp.395-418
• /
• 2024

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

• 천문학회보
• /
• 제40권1호
• /
• pp.47.1-47.1
• /
• 2015

We present an optical spectroscopic study of 28 supernova remnant (SNR) candidates in M81 and two SNR candidates in M82. The optical spectra of these SNR candidates were obtained using the MMT/Hectospec as a part of the K-GMT Science Program. Based on the [S II]/$H{\alpha}$ ratio and the radial velocity, we find that twenty six out of the M81 candidates are genuine SNRs. Two SNR candidates in M82 are thought to be shocked condensations in the galactic outflow or SNRs. In the spectral line ratio diagrams, M81 SNRs are divided into two groups: an [O III]-strong group and an [O III]-weak group. The [O III]-weak SNRs have larger sizes, and may have faster shock velocity. We estimate the nitrogen and oxygen abundance of the SNRs from the comparison with shock-ionization models. We find a radial gradient in nitrogen abundance, $dLog(N/H)/dlogR=-0.023{\pm}0.009\;dex\;kpc^{-1}$ little evidence for the gradient in oxygen abundance. The nitrogen abundance shows shallower gradient than those of the planetary nebulae and H II regions of M81. We find five X-ray emitting SNRs. Their X-ray hardness colors are consistent with thermal SNRs.

• 한국멀티미디어학회논문지
• /
• 제4권3호
• /
• pp.230-237
• /
• 2001

음향 반향 제거기, 적응 등화기 그리고 적웅 잡음 제거기 등에 적응 필터가 널리 활용되고 있다. 적응 필터의 계수는 주로 NLMS 알고리즘을 이용하고 있지만 NLMS 알고리즘은 주변 잡음에 의해서 적응 필터의 계수가 오조정된다. 본 논문에서 최적 필터의 직교원리를 이용하여 LMS 알고리즘의 순시 기울기 벡터를 저역 통과 시켜 적응 알고리즘의 적응 상수로 결정하는 방법을 제안한다. 순시 기울기 벡터는 입력 신호와 추정 오차 신호의 상호 상관도로써 수렴 초기에는 추정 오차 신호 속에 입력 신호가 대부분 포함되어 있기 때문에 상관도가 크고 적응 필터가 수렴한 후에는 0 에 가까운 값을 갖게 된다. 그리고 입력 신호와 주변 잡음 신호는 상관이 없기 때문에 주변 잡음에 의해서 상호 상관도는 큰 변화가 없다. 따라서 상호 상관도를 적응 상수로 결정하면 수렴 속도가 느려지지 않으면서 주변 잡음에 강건한 특성을 가진다. 본 논문에서는 컴퓨터 시뮬레이션을 통해서 제안하는 적응 알고리즘의 성능이 기존 알고리즘에 비해서 우수함을 보인다.

• 한국통신학회논문지
• /
• 제32권3C호
• /
• pp.278-286
• /
• 2007

본 논문에서는 비월 주사 영상을 순차 주사 영상으로 보간 하는데 사용되는 효율적인 디인터레이싱 알고리즘을 제안한다. 먼저 보간할 화소의 주변 화소들이 갖는 공간적 방향성의 경향을 구하고 구해진 경향에 맞게 소벨 연산을 적응적으로 적용하여 기울기 벡터를 구함으로써 정교한 에지의 방향을 구한다. 이렇게 구해진 정교한 에지 방향에 맞게 보간을 수행하므로 좀 더 선명하고 정확한 영상을 얻을 수 있다. 제안하는 알고리즘은 기존의 알고리즘에 비해 복잡도를 줄이는 동시에 정확한 에지 방향을 추출할 수 있다. 여러 가지 정지 영상에 대한 실험 결과는 제안하는 알고리즘의 객관적, 주관적 우수함을 증명한다.

• Steel and Composite Structures
• /
• 제26권6호
• /
• pp.673-691
• /
• 2018

The main goal of this research is to examine the in-plane and out-of-plane forced vibration of a curved nanocomposite microbeam. The in-plane and out-of-plane displacements of the structure are considered based on the first order shear deformation theory (FSDT). The curved microbeam is reinforced by functionally graded carbon nanotubes (FG-CNTs) and thus the extended rule of mixture is employed to estimate the effective material properties of the structure. Also, the small scale effect is captured using the strain gradient theory. The structure is rested on a nonlinear orthotropic viscoelastic foundation and is subjected to concentrated transverse harmonic external force, thermal and magnetic loads. The derivation of the governing equations is performed using energy method and Hamilton's principle. Differential quadrature (DQ) method along with integral quadrature (IQ) and Newmark methods are employed to solve the problem. The effect of various parameters such as volume fraction and distribution type of CNTs, boundary conditions, elastic foundation, temperature changes, material length scale parameters, magnetic field, central angle and width to thickness ratio are studied on the frequency and force responses of the structure. The results indicate that the highest frequency and lowest vibration amplitude belongs to FGX distribution type while the inverse condition is observed for FGO distribution type. In addition, the hardening-type response of the structure with FGX distribution type is more intense with respect to the other distribution types.

• 한국음향학회지
• /
• 제38권6호
• /
• pp.670-677
• /
• 2019

음성 또는 음향 이벤트 신호에서 발생하는 배경 잡음은 인식기의 성능을 저하시키는 원인이 되며, 잡음에 강인한 특징을 찾는데 많은 노력을 필요로 한다. 본 논문에서는 딥러닝을 기반으로 다중작업 오토인코더(Multi-Task AutoEncoder, MTAE) 와 와설스타인식 생성적 적대 신경망(Wasserstein GAN, WGAN)의 장점을 결합하여, 잡음이 섞인 음향신호에서 잡음과 음성신호를 추정하는 네트워크를 제안한다. 본 논문에서 제안하는 MTAE-WGAN는 구조는 구배 페널티(Gradient Penalty) 및 누설 Leaky Rectified Linear Unit (LReLU) 모수 Parametric ReLU (PReLU)를 활용한 변수 초기화 작업을 통해 음성과 잡음 성분을 추정한다. 직교 구배 페널티와 파라미터 초기화 방법이 적용된 MTAE-WGAN 구조를 통해 잡음에 강인한 음성특징 생성 및 기존 방법 대비 음소 오인식률(Phoneme Error Rate, PER)이 크게 감소하는 성능을 보여준다.

• 지구물리와물리탐사
• /
• 제10권4호
• /
• pp.314-321
• /
• 2007

최근에 들어서 물성이 서로 다른 두 종류의 탐사자료의 복합역산에 대한 연구가 활발하게 이루어지고 있다. 이는 복합역산에 의하여 훨씬 더 정확한 지하구조 영상을 계산할 수 있을 뿐만 아니라 물리탐사 변수가 아닌 다른 물성 분포의 유도가 물리탐사로서 가능해지기 때문이다. 이 연구에서는 (1) cross-gradient로 정의되는 두 지하구조의 유사성의 최대화, (2) 두 물성간의 상관관계의 최대화, (3) 지하 물성 분포에 대한 선험적 정보의 3 종류 제한을 채택한 탄성파 굴절법 주시 토모그래피와 전기비저항 탐사 자료의 복합역산법을 개발하였다. 지표 전기비저항과 탄성파 굴절법 탐사의 수치실험을 통하여, 제안한 복합역산법의 효용성과 각종 제한조건의 효과를 분석하였다. 특히 제한조건을 적절히 이용할 경우, 탄성파 탐사의 저속도층에 의한 숨은 층 문제를 복합탐사 및 역산으로 해결할 수 있음을 알 수 있었다.