• Journal of Korean Association for Spatial Structures
• /
• v.20 no.2
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• ALGAE
• /
• v.28 no.4
• /
• pp.365-369
• /
• 2013

The objective of this study was to determine the optimal blade size and timing to transplant seed-stock of Ecklonia cava Kjellman onto the reef structure. We used the modified artificial stepped reef structure. A total of 14 units (3.0 m length ${\times}$ 3.5 m width ${\times}$ 1.1 m height) were deployed 7-8 m deep under the water to examine the optimal blade size and timing to transplant seed-stock of E. cava onto the structures. Sporophytes of E. cava <1 cm in length were all died within 1 month of transplantation. The blades of 5-10 cm in length which were transplanted in March 2007 survived and grew well on the artificial reefs. Growth rates of 5-10 cm size class were higher than those of longer blade sporophytes (20-30 cm size class, transplanted in April) while the survival rates showed no difference between the classes of blade size. Both classes of 5-10 and 20-30 cm in length grew until July, and a reduction in size had occurred in September. These results indicate the importance of the blade size of E. cava and timing for successful transplantation of the seaweed on artificial reef structures.

• International Journal of Contents
• /
• v.14 no.3
• /
• pp.53-60
• /
• 2018

Based on the previous studies on sinkholes and ground subsidence conducted until date, the factors affecting the occurrence of sinkholes can be divided into natural environmental factors and human environmental factors in accordance with the purpose of the study. Furthermore, to be more specific, the human environment can be classified into the artificial type and the social type. In this study, the assessment indices for assessing risks of sinkholes and ground subsidence were developed by performing AHP analysis based on the results of the study by Lee et al. (2016), who selected the risk factors for the occurrence of sinkholes by performing Delphi analysis targeting relevant experts. Analysis showed that the artificial environmental factors were of significance in affecting the occurrence of sinkholes. Explicitly, the underground factors were found to be of importance in the natural environment, and among them, the level of underground water turned out to be an imperative influencing factor. In the artificial environment, the underground and subterranean structures exhibited similar importance, and in the underground structures, the excessive use of the underground space was found to be an important influencing factor. In the subterranean ones, the level of water leakage and the erosion of the water supply and sewage piping system were the influential factors, and in the surface, compaction failure was observed as an imperative factor. In the social environment, the regional development, and above all, the groundwater overuse were found to be important factors. In the managemental and institutional environment, the improper construction management proved to be the most important influencing factor.

• Journal of Magnetics
• /
• v.19 no.4
• /
• pp.315-322
• /
• 2014

In this work, Artificial Neural Network (ANN) was used to model the dynamic behavior of ferromagnetic hysteresis derived from performing the mean-field analysis on the Ising model. The effect of field parameters and system structure (via coordination number) on dynamic critical points was elucidated. The Ising magnetization equation was drawn from mean-field picture where the steady hysteresis loops were extracted, and series of the dynamic critical points for constructing dynamic phase-diagram were depicted. From the dynamic critical points, the field parameters and the coordination number were treated as inputs whereas the dynamic critical temperature was considered as the output of the ANN. The input-output datasets were divided into training, validating and testing datasets. The number of neurons in hidden layer was varied in structuring ANN network with highest accuracy. The network was then used to predict dynamic critical points of the untrained input. The predicted and the targeted outputs were found to match well over an extensive range even for systems with different structures and field parameters. This therefore confirms the ANN capabilities and indicates the ANN ability in modeling the ferromagnetic dynamic hysteresis behavior for establishing the dynamic-phase-diagram.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.10 no.3
• /
• pp.39-47
• /
• 1990

The generation of artificial accelerograms considering the characteristic of earthquakes in the Korean peninsula for a time history analysis of structures is accomplised by the stochastic method. The engineering data such as a representative shape of envelope function and an effective duration are investigated from the instrumental records. The maximum ground acceleration value is based on seismic zoning map which are constructed for the Korean peninsula. The acceleration-time histories are generated for two different types of earthquake motions and two types of soil conditions. In the study, the maximum ground acceleration value of 0.2 g and effective durations of 24 seconds are used. The validity of the artificial accelerograms is obtained by the comparison with the required envelope functions and the design response spectrum.

• Earthquakes and Structures
• /
• v.15 no.4
• /
• pp.431-441
• /
• 2018

This study provides fragility-based assessment of seismic performance of reinforced concrete bridges. Seismic fragility curves were created using nonlinear analysis (NA) and artificial neural networks (ANNs). Nonlinear response history analyses were performed, in order to calculate the seismic performances of the bridges. To this end, 306 bridge-earthquake cases were considered. A multi-layered perceptron (MLP) neural network was implemented to predict the seismic performances of the selected bridges. The MLP neural networks considered herein consist of an input layer with four input vectors; two hidden layers and an output vector. In order to train ANNs, 70% of the numerical results were selected, and the remained 30% were employed for testing the reliability and validation of ANNs. Several structures of MLP neural networks were examined in order to obtain suitable neural networks. After achieving the most proper structure of neural network, it was used for generating new data. A total number of 600 new bridge-earthquake cases were generated based on neural simulation. Finally, probabilistic seismic safety analyses were conducted. Herein, fragility curves were developed using numerical results, neural predictions and the combination of numerical and neural data. Results of this study revealed that ANNs are suitable tools for predicting seismic performances of RC bridges. It was also shown that yield stresses of the reinforcements is one of the important sources of uncertainty in fragility analysis of RC bridges.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.1
• /
• pp.27-35
• /
• 2016

Black-box classifiers, such as artificial neural network and support vector machine, are a popular classifier because of its remarkable performance. They are applied in various fields such as inductive inferences, classifications, or regressions. However, by its characteristics, they cannot provide appropriate explanations how the classification results are derived. Therefore, there are plenty of actively discussed researches about interpreting trained black-box classifiers. In this paper, we propose a method to make a fuzzy logic-based classifier using extracted rules from the artificial neural network and support vector machine in order to interpret internal structures. As an object of classification, an anomalous propagation echo is selected which occurs frequently in radar data and becomes the problem in a precipitation estimation process. After applying a clustering method, learning dataset is generated from clusters. Using the learning dataset, artificial neural network and support vector machine are implemented. After that, decision trees for each classifier are generated. And they are used to implement simplified fuzzy logic-based classifiers by rule extraction and input selection. Finally, we can verify and compare performances. With actual occurrence cased of the anomalous propagation echo, we can determine the inner structures of the black-box classifiers.

• Bulletin of the Korean Chemical Society
• /
• v.28 no.9
• /
• pp.1472-1476
• /
• 2007

Artificial neural networks (ANNs) are successfully developed for the modeling and prediction of normalized polarity parameter (ETN) of 216 various solvents with diverse chemical structures using a quantitative-structure property relationship. ANN with architecture 5-9-1 is generated using five molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The most positive charge of a hydrogen atom (q+), total charge in molecule (qt), molecular volume of solvent (Vm), dipole moment (μ) and polarizability term (πI) are input descriptors and its output is ETN. It is found that properly selected and trained neural network with 192 solvents could fairly represent the dependence of normalized polarity parameter on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network is applied for prediction of the ETN values of 24 solvents in the prediction set, which are not used in the optimization procedure. Correlation coefficient (R) and root mean square error (RMSE) of 0.903 and 0.0887 for prediction set by MLR model should be compared with the values of 0.985 and 0.0375 by ANN model. These improvements are due to the fact that the ETN of solvents shows non-linear correlations with the molecular descriptors.

• Journal of Mechanical Science and Technology
• /
• v.20 no.10
• /
• pp.1576-1589
• /
• 2006

Most of surface water ways in Egypt suffer from the infestation of aquatic weeds especially submerged ones which cause lots of problems for the open channels and the water structures such as increasing water losses, obstructing the water flow, and reducing the efficiency of the water structures. Accurate simulation of the water flow behavior in such channels is very essential for water distribution decision makers. Artificial Neural Network (ANN) has been widely utilized in the past ten years in civil engineering applications for the simulation and prediction of the different physical phenomena and has proven its capabilities in the different fields. The present study aims towards introducing the use of ANN technique to model and predict the impact of the existence of submerged aquatic weeds on the hydraulic performance of open channels. Specifically the current paper investigates utilizing the ANN technique in developing a simulation and prediction model for the flow behavior in an open channel experiment that simulates the existence of submerged weeds as branched flexible elements. This experiment was considered as an example for implementing the same methodology and technique in a real open channel system. The results of current manuscript showed that ANN technique was very successful in simulating the flow behavior of the pre-mentioned open channel experiment with the existence of the submerged weeds. In addition, the developed ANN models were capable of predicting the open channel flow behavior in all the submerged weeds' cases that were considered in the ANN development process.

• Smart Structures and Systems
• /
• v.14 no.2
• /
• pp.159-189
• /
• 2014

One of the most important requirements in the evaluation of existing structural systems and ensuring a safe performance during their service life is damage assessment. Damage can be defined as a weakening of the structure that adversely affects its current or future performance which may cause undesirable displacements, stresses or vibrations to the structure. The mass and stiffness of a structure will change due to the damage, which in turn changes the measured dynamic response of the system. Damage detection can increase safety, reduce maintenance costs and increase serviceability of the structures. Artificial Neural Networks (ANNs) are simplified models of the human brain and evolved as one of the most useful mathematical concepts used in almost all branches of science and engineering. ANNs have been applied increasingly due to its powerful computational and excellent pattern recognition ability for detecting damage in structural engineering. This paper presents and reviews the technical literature for past two decades on structural damage detection using ANNs with modal parameters such as natural frequencies and mode shapes as inputs.