• Journal of the Society of Naval Architects of Korea
• /
• v.40 no.6
• /
• pp.37-48
• /
• 2003

A study for the structural strength evaluation of doubler plates subjected to the in-plane combined load and lateral pressure load has been performed through a systematic evaluation process. In order to properly estimate the static strength of doubler plate, elasto-plastic large deflection analysis is introduced including the contact effect between main plate and doubler. The characteristics of stiffness and strength variation are discussed based on the analysis results. Also, in order to compare the doubler structure with the original strength of main plate without doubler, a simple formula for the evaluation of the equivalent flat plate thickness is derived based on the additional series analysis of fiat plate structure. Using this derived equation, the thickness change of a equivalent flat plate is analyzed according to the variation of various design parameters of doubler plate and some design guides are suggested In order to maintain the original strength of main plate without doubler reinforcement. Finally, correlation between derived equivalent plate thickness formula and the developed buckling strength formulas for intact plates by author et al. is discovered and these relations are formulated for the future development of simple strength evaluation formula of doubler plate structure.

• Advances in concrete construction
• /
• v.3 no.2
• /
• pp.91-102
• /
• 2015

In this paper, the load-deflection analysis of the Carbon Fiber Reinforced Polymer (CFRP) strengthened Reinforced Concrete (RC) slab using Recurrent Neural Network (RNN) is investigated. Six reinforced concrete slabs having dimension $1800{\times}400{\times}120mm$ with similar steel bar of 2T10 and strengthened using different length and width of CFRP were tested and compared with similar samples without CFRP. The experimental load-deflection results were normalized and then uploaded in MATLAB software. Loading, CFRP length and width were as neurons in input layer and mid-span deflection was as neuron in output layer. The network was generated using feed-forward network and a internal nonlinear condition space model to memorize the input data while training process. From 122 load-deflection data, 111 data utilized for network generation and 11 data for the network testing. The results of model on the testing stage showed that the generated RNN predicted the load-deflection analysis of the slabs in acceptable technique with a correlation of determination of 0.99. The ratio between predicted deflection by RNN and experimental output was in the range of 0.99 to 1.11.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.21-25
• /
• 2023

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

• Wind and Structures
• /
• v.8 no.3
• /
• pp.163-178
• /
• 2005

Wind-induced mean and dynamic interference effects of tall buildings are studied in detail by a series of wind tunnel tests in this paper. Interference excitations of several types of upwind structures of different sizes in different upwind terrains are considered. Comprehensive interference characteristics are investigated by artificial neural networks and correlation analysis. Mechanism of the wakes vortex-induced resonance is discussed, too. Measured results show significant correlations exist in the distributions of the interference factors of different configurations and upwind terrains and, therefore, a series of relevant regression equations are proposed to simplify the complexity of the multi-parameter wind induced interference effects between two tall buildings.

• Journal of Korean Society for Atmospheric Environment
• /
• v.1 no.1
• /
• pp.83-92
• /
• 1985

In odrder to survey the emission level of air pollutants from diesel vehicles, was measured CO, HC, NOx and smoke of 4 types of domestic-use diesel engines under various conditions. The emission of CO, HC and NOx tested by 6-Mode test method and smoke emission by full load test met the permissible vehicle emission standard. Pollutant emission rates of diesel engines were different according to engine operating conditions, that is, engine load and engine speed. Generally, CO and HC was emitted more at low load and NOx at high load but the trend was quite different by the type of engines. In exhaust gas, $NO_2$ portion of NOx emission was high, specially at low speed and low load. The correlation equation between CLD(NOx) and NDIR(NO) method of nitrogen of nitrogen oxides analysis was y = 1.10x - 3.48 (y: CLD method) as a result of 6-mode test.

• KIEAE Journal
• /
• v.10 no.4
• /
• pp.117-122
• /
• 2010

In these days numerous super tall buildings are under construction or being planned in Middle East and Asian countries. Some of them are planned as an ultra high-rise building that goes over 600m tall, including Burj Khalifa, the tallest building in the world. External environment such as wind speed, temperature and humidity of the super tall building varies due to its vertical height. Therefore, it is necessary to consider these environmental changes to estimate building heating and cooling load. This paper analyzes how vertical microclimate difference affects building heating and cooling load in super tall building by simulation using radiosonde climate data. Besides, the correlation between air-tightness of building envelope and building load was analyzed for a super tall building.

• Computers and Concrete
• /
• v.33 no.6
• /
• 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.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.2
• /
• pp.70-79
• /
• 2020

The offshore installation units may be subjected to various accidental loads such as collision from supply vessels, impact from dropped objects, blast load from gas explosion and thermal load from fire. This paper deals with the design and strength evaluation method of the stiffened plate structures in response to a blast load caused by a gas explosion accident. It is a comprehensive review of various items used in actual project such as the size and type of the explosive loads, general design procedure/concept and analysis method. The structural analyses using simple analysis methods based on SDOF model and nonlinear finite element analysis are applied to the particular FPSO project. Also validation studies on the design guidance given by simple analysis method based on SDOF model have also considered several items such as backpressure effects, material behavior and duration time of the overpressure. A good correlation between the prediction made by simple analysis method based on SDOF model and nonlinear finite element analysis can be generally obtained up to the elastic limit.

• Tunnel and Underground Space
• /
• v.25 no.1
• /
• pp.24-36
• /
• 2015

The Geochang granite widely used in construction works is one of the most popular dimension stones in Korea. In order to evaluate the physical properties of rock, a lot of laboratory tests for the Geochang granite were conducted to find unit weight, absorption ratio, P wave velocity, S wave velocity, uniaxial compressive strength, Young's modulus, Poisson's ratio, tensile strength, cohesion, friction angle and point load strength index. The uniaxial compressive strength of the Geochang granite was 19.5 times tensile strength and also 8.6 times cohesion, besides P wave velocity was 1.5 times S wave velocity. Correlation analyses were also conducted to find the correlation among 11 different physical properties, where the uniaxial compressive strength showed Pearson correlation coefficient of more than 0.8 with Poisson's ratio, point load strength index and Young's modulus, respectively. Regression analyses were finally conducted by means of both linear and multiple analysis and the brief results including coefficient of determination of more than 0.7 were presented.

• Journal of the Optical Society of Korea
• /
• v.18 no.5
• /
• pp.523-530
• /
• 2014

Machine material and structural strain are critical factors for appraising mechanical properties and safety. Particularly in three and four-point bending tests, which appraise the deflection and flexural strain of an object due to external force, measurements are made by the crosshead movement or deflection meter of a universal testing machine. The Digital Image Correlation (DIC) method is one of the non-contact measurement methods. It uses the image analyzing method that compares the reference image with the deformed image for measuring the displacement and strain of the objects caused by external force. Accordingly, the advantage of this method is that the object's surface roughness, shape, and temperature have little influence. However, its disadvantage is that it requires extensive time to compare the reference image with the deformed image for measuring the displacement and strain. In this study, an algorithm is developed for DIC that can improve the speed of image analysis for measuring the deflection and strain of an object caused by a three-point bending load. To implement this algorithm for improving the speed of image analysis, LabVIEW 2010 was used. Furthermore, to evaluate the accuracy of the developed fast correlation algorithm, the deflection of an aluminum specimen under a three-point bending load was measured by using the universal test machine and DIC measurement system.