• Smart Structures and Systems
• /
• v.4 no.5
• /
• pp.583-603
• /
• 2008

In this study, a real-time damage detection method using output-only acceleration signals and artificial neural networks (ANN) is developed to monitor the occurrence of damage and the location of damage in structures. A theoretical approach of an ANN algorithm that uses acceleration signals to detect changes in structural parameters in real-time is newly designed. Cross-covariance functions of two acceleration responses measured before and after damage at two different sensor locations are selected as the features representing the structural conditions. By means of the acceleration features, multiple neural networks are trained for a series of potential loading patterns and damage scenarios of the target structure for which its actual loading history and structural conditions are unknown. The feasibility of the proposed method is evaluated using a numerical beam model under the effect of model uncertainty due to the variability of impulse excitation patterns used for training neural networks. The practicality of the method is also evaluated from laboratory-model tests on free-free beams for which acceleration responses were measured for several damage cases.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.15 no.5
• /
• pp.25-33
• /
• 2011

In the nonlinear response history analysis of building structures, the input ground accelerations have considerable effect on the nonlinear response characteristics of structural systems. As the properties of the ground motion, using time history analysis, are interrelated with many factors such as the fault mechanism, the seismic wave propagation from source to site, and the amplification characteristics of the soil, it is difficult to properly select the input ground motions for seismic response analysis. In this paper, the most unfavourable real seismic design ground motions were selected as input motions. The artificial earthquake waves were generated according to these earthquake events. The artificial waves have identical phase angles to the recorded earthquake waves, and their overall response spectra are compatible with the seismic design spectrum with 5% of critical viscous damping. It is concluded that the artificial earthquake waves simulated in this paper are applicable as input ground motions for a seismic response analysis of building structures.

• Earthquakes and Structures
• /
• v.16 no.5
• /
• pp.563-573
• /
• 2019

When generating spectrum-compatible artificial ground motion in engineering practices, the effect of the variation in fitting parameters on the distribution of the peak ground displacement (PGD) has not yet drawn enough attention. In this study, a method for simulating ground motion matching for multiple targets is developed. In this method, a frequency-dependent amplitude envelope function with statistical parameters is introduced to simulate the nonstationarity of the frequency in earthquake ground motion. Then, several groups of time-history acceleration with different temporal and spectral nonstationarities were generated to analyze the effect of nonstationary parameter variations on the distribution of PGD. The following conclusions are drawn from the results: (1) In the simulation of spectrum-compatible artificial ground motion, if the acceleration time-history is generated with random initial phases, the corresponding PGD distribution is quite discrete and an uncertain number of PGD values lower than the limit value are observed. Nevertheless, the mean values of PGD always meet the requirement in every group. (2) If the nonstationary frequencies of the ground motion are taken into account when fitting the target spectrum, the corresponding PGD values will increase. A correlation analysis shows that the change in the mean and the dispersion values, from before the frequencies are controlled to after, correlates with the modal parameters of the predominant frequencies. (3) Extending the maximum period of the target spectrum will increase the corresponding PGD value and, simultaneously, decrease the PGD dispersion. Finally, in order to control the PGD effectively, the ground motion simulation method suggested in this study was revised to target a specified PGD. This novel method can generate ground motion that satisfies not only the required precision of the target spectrum, peak ground acceleration (PGA), and nonstationarity characteristics of the ground motion but also meets the required limit of the PGD, improving engineering practices.

• Structural Engineering and Mechanics
• /
• v.75 no.3
• /
• pp.295-309
• /
• 2020

The construction of Reinforced Concrete (R/C) buildings with unreinforced masonry infills is part of the traditional building practice in many countries with regions of high seismicity throughout the world. When these buildings are subjected to seismic motions the presence of masonry infills and especially their configuration can highly influence the seismic damage state. The capability to avoid configurations of masonry infills prone to seismic damage at the stage of initial architectural concept would be significantly definitive in the context of Performance-Based Earthquake Engineering. Along these lines, the present paper investigates the potential of instant prediction of the damage response of R/C buildings with various configurations of masonry infills utilizing Artificial Neural Networks (ANNs). To this end, Multilayer Feedforward Perceptron networks are utilized and the problem is formulated as pattern recognition problem. The ANNs' training data-set is created by means of Nonlinear Time History Analyses of 5 R/C buildings with a large number of different masonry infills' distributions, which are subjected to 65 earthquakes. The structural damage is expressed in terms of the Maximum Interstorey Drift Ratio. The most significant conclusion which is extracted is that the ANNs can reliably estimate the influence of masonry infills' configurations on the seismic damage level of R/C buildings incorporating their optimum design.

• Journal of Korean Association for Spatial Structures
• /
• v.14 no.1
• /
• pp.77-84
• /
• 2014

Simple 3, 10, and 30-story buildings with a nonstructural element which is located at roof or near the middle of the building height are selected. Based on 2009 Korean Building Code, the seismic design force applied at the nonstructural element is evaluated. Response spectrum analysis is conducted with the design response acceleration spectrum of 2009 Korean Building Code and the analytical response is compared with the seismic design force from the Code. Furthermore, an artificial earthquake based on Korean design response acceleration spectrum and the 50% intensity of El Centro earthquake, which can be considered as the maximum future earthquake possibly occurring in Korea, are selected to conduct time history analysis. When the period of the nonstructural element is shorter than 0.06 second or longer than that of the 1st period of each building, the Code equations of seismic design force for nonstructural element seems to be appropriate. However, the period of the nonstructural element is close to the one of the building's higher mode periods including the 1st period, seismic force of the nonstructural element might exceed the Code specified seismic design force.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.5
• /
• pp.623-628
• /
• 2007

The accurate peak response estimation of a seismically excited structure with frictional damping system(FDS) is very difficult since the structure with FDS shows nonlinear behavior dependent on the structural period, loading characteristics, and relative magnitude between the frictional force and the excitation load. Previous studies have estimated that by replacing a nonlinear system with an equivalent linear one or by employing the response spectrum obtained based on nonlinear time history and statistical analysis. In the case that an earthquake load is defined with probabilistic characteristics, the corresponding response of the structure with FDS has probabilistic distribution. In this study, nonlinear time history analyses were performed for the structure with FDS subjected to artificial earthquake loads generated using Kanai-Tajimi filter. An equation for the probability density function (PDF) of the displacement response is proposed by adapting the PDF of the normal distribution. Finally, coefficients of the proposed PDF are obtained by regression analysis of the statistical distribution of the time history responses. Finally the correlation between PDFs and statistical response distribution is presented.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.20 no.7_spc
• /
• pp.435-441
• /
• 2016

The Korean peninsula has known as a minor-to-moderate seismic region. However, some recent studies had shown that the maximum possible earthquake magnitude in the region is approximately 6.3-6.5. Therefore, a seismic vulnerability assessment of the existing infrastructures considering ground motions in Korea is necessary. In this study, we developed seismic fragility curves for a continuous steel box girder bridge and two typical transmission towers, in which a set of seven artificial and natural ground motions recorded in South Korea is used. A finite element simulation framework, OpenSees, is utilized to perform nonlinear time history analyses of the bridge and a commercial software, SAP2000, is used to perform time history analyses of the transmission towers. The fragility curves based on Korean ground motions were then compared with the fragility curves generated using worldwide ground motions to evaluate the effect of the two ground motion groups on the seismic fragility curves of the structures. The results show that both non-isolated and base-isolated bridges are less vulnerable to the Korean ground motions than to worldwide earthquakes. Similarly to the bridge case, the transmission towers are safer during Korean motions than that under worldwide earthquakes in terms of fragility functions.

• Journal of the Korean Geotechnical Society
• /
• v.27 no.10
• /
• pp.45-54
• /
• 2011

In this study, the consolidation characteristics are investigated on the artificial soil mixture of kaolinite, fine soils representing dredged soils and reclaimed coal ash from the ash ponds. A large sedimentation chamber was designed and manufactured to produce the artificial soil mixture with uniform stress history. In order to examine the consolidation characteristics in lateral and vertical directions, standard consolidation and Rowe Cell tests were performed. From the results of standard consolidation tests, the artificial soil mixture with coal ash showed lower compressibility and the larger consolidation coefficients enough to aid in early stabilization of the reclaimed sites compared with the kaolinite only. Also, in order to examine the consolidation characteristics when applying vertical drains, the drainage material was installed and tested in the Rowe Cell. The Rowe Cell test results show that the artificial soil mixture yields higher coefficient of consolidation. Thus, the application of artificial soil mixture on the reclaimed sites can shorten the consolidation time.

• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.