• Structural Engineering and Mechanics
• /
• 제85권3호
• /
• pp.315-335
• /
• 2023

Limited studies are available on the mathematical estimates of the compressive strength (CS) of glass fiber-embedded polymer (glass-FRP) compressive elements. The present study has endeavored to estimate the CS of glass-FRP normal strength concrete (NSTC) compression elements (glass-FRP-NSTC) employing two various methodologies; mathematical modeling and artificial neural networks (ANNs). The dataset of 288 glass-FRP-NSTC compression elements was constructed from the various testing investigations available in the literature. Diverse equations for CS of glass-FRP-NSTC compression elements suggested in the previous research studies were evaluated employing the constructed dataset to examine their correctness. A new mathematical equation for the CS of glass-FRP-NSTC compression elements was put forwarded employing the procedures of curve-fitting and general regression in MATLAB. The newly suggested ANN equation was calibrated for various hidden layers and neurons to secure the optimized estimates. The suggested equations reported a good correlation among themselves and presented precise estimates compared with the estimates of the equations available in the literature with R²= 0.769, and R² =0.9702 for the mathematical and ANN equations, respectively. The statistical comparison of diverse factors for the estimates of the projected equations also authenticated their high correctness for apprehending the CS of glass-FRP-NSTC compression elements. A broad parametric examination employing the projected ANN equation was also performed to examine the effect of diverse factors of the glass-FRP-NSTC compression elements.

• 한국수자원학회논문집
• /
• 제51권4호
• /
• pp.335-346
• /
• 2018

최근 ADCP (Acoustic Doppler Current Profiler) 등 첨단장비를 활용한 유량 및 하상측정, 각종 하천기본계획 수립 시 확보되는 횡단측정 자료, 식생 및 서식처 등 하천환경과 생태자료, 드론 등을 활용한 영상자료 등 방대한 하천 정보가 확보되고 있으며, 다기능보 등 다양한 하천구조물 및 친수구역이 증가하는 등 이전과 비교하여 괄목할만한 수준으로 정보의 양이 증가하고 있다. 이에 따라 다양한 하천정보를 체계적으로 저장, 관리, 공유하기 위하여 표준화된 데이터 모델의 수립이 필요하다. 하천 정보의 경우 하천 시설물, 하천 단면측량 자료, 하천 시계열 측정 자료 등이 특정 하천을 중심으로 관리되는 반면, 기존 데이터 모델 연구에서는 특정 주제도에 기반하여 하천 정보가 레이어 형식으로 제공되어 상호 연계되지 않아 하천 정보의 효율적 관리측면에서 적합하지 않았다. 또한 신규 정보를 추가 시 기존 데이터 모델의 과다한 수정이 필요하고, 기존의 데이터 모델의 경우 표준화되지 않아 활용성이 매우 낮고, 유역중심으로 구성되어 특정 조건에 해당되는 하천 정보 검색이 어려운 단점이 존재하였다. 본 연구에서는 기존의 주제도 및 레이어 형식으로 구성되어 있던 데이터 모델 형식에서 벗어나 하천흐름선을 기준으로 데이터모델을 구축하는 방안을 제시하였으며, 하천흐름선과 하천 시설물, 단면 측량 자료, 계측 자료를 순차적으로 수용하고, 최근 신규로 생성되고 있는 다차원 하천 정보의 추가 시 기존 데이터 모델의 형식을 수정하지 않고 유연하게 대응할 수 있는 관계형 데이터 모델을 구상하였다. 또한, 하천과 유역의 논리적 저장방안 고려하여 한 개의 하천을 다수의 세그먼트로 구분하여 코드(Reach Code)를 부여하는 방안을 제시하였으며, 구상한 데이터모델을 통하여 국가하천과 지방하천 등 유역의 다양성을 포함하는 한강권역의 섬강유역을 시범하천으로 구축하였다.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.17-30
• /
• 2021

This paper develops a convenient approach for deterministic and probabilistic evaluations of tunnel face stability using support vector machine classifiers. The proposed method is comprised of two major steps, i.e., construction of the training dataset and determination of instance-based classifiers. In step one, the orthogonal design is utilized to produce representative samples after the ranges and levels of the factors that influence tunnel face stability are specified. The training dataset is then labeled by two-dimensional strength reduction analyses embedded within OptumG2. For any unknown instance, the second step applies the training dataset for classification, which is achieved by an ad hoc Python program. The classification of unknown samples starts with selection of instance-based training samples using the k-nearest neighbors algorithm, followed by the construction of an instance-based SVM-KNN classifier. It eventually provides labels of the unknown instances, avoiding calculate its corresponding performance function. Probabilistic evaluations are performed by Monte Carlo simulation based on the SVM-KNN classifier. The ratio of the number of unstable samples to the total number of simulated samples is computed and is taken as the failure probability, which is validated and compared with the response surface method.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.613-626
• /
• 2022

Guaranteeing the quality and integrity of structural health monitoring (SHM) data is very important for an effective assessment of structural condition. However, sensory system may malfunction due to sensor fault or harsh operational environment, resulting in multiple types of data anomaly existing in the measured data. Efficiently and automatically identifying anomalies from the vast amounts of measured data is significant for assessing the structural conditions and early warning for structural failure in SHM. The major challenges of current automated data anomaly detection methods are the imbalance of dataset categories. In terms of the feature of actual anomalous data, this paper proposes a data anomaly detection method based on data-level and deep learning technique for SHM of civil engineering structures. The proposed method consists of a data balancing phase to prepare a comprehensive training dataset based on data-level technique, and an anomaly detection phase based on a sophisticatedly designed network. The advanced densely connected convolutional network (DenseNet) and Transformer encoder are embedded in the specific network to facilitate extraction of both detail and global features of response data, and to establish the mapping between the highest level of abstractive features and data anomaly class. Numerical studies on a steel frame model are conducted to evaluate the performance and noise immunity of using the proposed network for data anomaly detection. The applicability of the proposed method for data anomaly classification is validated with the measured data of a practical supertall structure. The proposed method presents a remarkable performance on data anomaly detection, which reaches a 95.7% overall accuracy with practical engineering structural monitoring data, which demonstrates the effectiveness of data balancing and the robust classification capability of the proposed network.

• 신재생에너지
• /
• 제20권1호
• /
• pp.102-109
• /
• 2024

The Typical Meteorological Year (TMY) dataset compiles 12 months of data that best represent long-term climate patterns, focusing on global horizontal irradiance and other weather-related variables. However, the irradiance measured on the plane of the array (POA) shows certain distinct distribution characteristics compared with the irradiance in the TMY dataset, and this may introduce some biases. Our research recalculated POA irradiance using both the Isotropic and DIRINT models, generating an updated dataset that was tailored to POA characteristics. Our analysis showed a 28% change in the selection of typical meteorological months, an 8% increase in average irradiance, and a 40% reduction in the range of irradiance values, thus indicating a significant shift in irradiance distribution patterns. This research aims to inform stakeholders about accurate use of TMY datasets in potential decision-making. These findings underscore the necessity of creating a typical dataset by using the time series of POA irradiance, which represents the orientation in which PV panels will be deployed.

• 대한공간정보학회지
• /
• 제22권4호
• /
• pp.175-181
• /
• 2014

정부 3.0이라는 새로운 정부운영 계획과 함께 다양한 공공정보를 민간이 활용할 수 있게 되었으며, 특히 서울은 이러한 행정정보 공개 및 활용을 선도하고 있다. 공개된 행정정보를 통해 각 지역을 특징짓는 행정요소를 발견할 경우, 각종 행정정책을 위한 의사결정 수단에 반영할 수 있을 뿐만 아니라 특정 지역의 고객 특성을 파악하여 특화된 서비스나 상품을 판매하는 마케팅 수단으로도 사용할 수 있을 것으로 사료된다. 하지만, 방대한 양의 행정자료로부터 각 군집의 특성을 명확히 구분할 수 있는 최적의 조합을 찾는 과정은 조합최적화 문제로서 상당한 연산량을 요구한다. 본 연구에서는 서울시에서 제공하는 다차원 행정자료로부터 서울시를 대표하는 문화 산업의 중심인 서초구, 강남구, 송파구 등의 강남 3구를 다른 지역과 효과적으로 구분하는 행정요인를 찾고자 하였다. 방대한 양의 행정정보로부터 두 군집간의 차이점을 극대화하는 요인을 선별하기 위한 최적화 방법으로 유전자 알고리즘을 이용하였으며, 군집간 차이를 계산하는 척도로는 Dunn 지수를 이용하였다. 또한 유전자 알고리즘의 연산속도의 향상을 위해 Microsoft Azure에서 제공하는 cloud computing을 이용한 분산처리를 수행하였다. 자료로는 통계청으로 부터 취득한 총 718개의 행정자료를 이용하였으며, 그 중 28개가 최적 변수로 선정되었다. 검증을 위해 선정된 28개의 변수를 입력값으로 Ward의 최소분산법 및 K-means 알고리즘을 통한 군집화를 수행한 결과 두 경우 모두 강남 3구가 다른 지역으로부터 효과적으로 분류됨을 확인하였다.

• 대한원격탐사학회지
• /
• 제38권6_4호
• /
• pp.1925-1934
• /
• 2022

원격탐사 기술을 활용한 접근불능 지역에 대한 핵활동 모니터링은 핵 비확산을 위해 필수적이다. 최근에는 딥러닝을 이용하여 핵활동 관련 객체를 탐지하는 연구가 활발하게 수행되고 있으나, 고해상도 위성영상 내 소형객체는 클래스 불균형 발생 빈도가 높다. 이로 인해 소형객체 탐지 성능이 저하되는 문제점이 존재한다. 이에 본 연구에서는 입력 데이터 내 핵활동 관련 소형객체의 비율이 딥러닝 모델 성능에 미치는 영향을 분석하여 탐지 정확도를 개선하기 위한 방안을 도출하고자 한다. 이를 위해 소형객체 비율이 상이한 6가지 학습자료를 구축하여 학습자료별로 U-Net 모델 학습을 진행하고, 다양한 종류의 소형객체가 포함된 test dataset을 이용하여 학습된 U-Net 모델 간 정량적·정성적 비교평가를 수행하였다. 그 결과, 입력영상 내 객체 픽셀 비율을 조절하였을 때 핵활동 관련 소형객체를 효과적으로 탐지할 수 있는 것이 확인되었으며, 이를 통해 훈련 자료 내 객체 비율을 조정하여 딥러닝 모델 성능을 향상시킬 수 있을 것으로 판단된다.

• Steel and Composite Structures
• /
• 제49권4호
• /
• pp.419-430
• /
• 2023

This paper is aimed at investigating the effect of multiple longitudinal stiffeners on the patch loading resistance of slender steel plate girders. Firstly, a numerical study is conducted through geometrically and materially nonlinear analysis with imperfections included (GMNIA), the model is validated with experimental results taken from the literature. The structural responses of girders with multiple longitudinal stiffeners are compared to the one of girders with a single longitudinal stiffener. Thereafter, a patch loading resistance model is developed through machine learning (ML) using symbolic regression (SR). An extensive numerical dataset covering a wide range of bridge girder geometries is employed to fit the resistance model using SR. Finally, the performance of the SR prediction model is evaluated by comparison of the resistances predicted using available formulae from the literature.

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• Computers and Concrete
• /
• 제33권6호
• /
• pp.739-754
• /
• 2024

This study presents an innovative AI-driven approach to assess the ultimate axial load in Double-Skinned Profiled Steel sheet Composite Walls (DPSCWs). Utilizing a dataset of 80 entries, seven input parameters were employed, and various AI techniques, including Linear Regression, Polynomial Regression, Support Vector Regression, Decision Tree Regression, Decision Tree with AdaBoost Regression, Random Forest Regression, Gradient Boost Regression Tree, Elastic Net Regression, Ridge Regression, and LASSO Regression, were evaluated. Decision Tree Regression and Random Forest Regression emerged as the most accurate models. The top three performing models were integrated into a hybrid approach, excelling in accurately estimating DPSCWs' ultimate axial load. This adaptable hybrid model outperforms traditional methods, reducing errors in complex scenarios. The validated Artificial Neural Network (ANN) model showcases less than 1% error, enhancing reliability. Correlation analysis highlights robust predictions, emphasizing the importance of steel sheet thickness. The study contributes insights for predicting DPSCW strength in civil engineering, suggesting optimization and database expansion. The research advances precise load capacity estimation, empowering engineers to enhance construction safety and explore further machine learning applications in structural engineering.