• Structural Engineering and Mechanics
• /
• v.26 no.3
• /
• pp.251-262
• /
• 2007

This paper examines the application of artificial neural networks (ANN) to the response prediction of geometrically nonlinear truss structures. Two types of analysis (deterministic and probabilistic analyses) are considered. A three-layer feed-forward backpropagation network with three input nodes, five hidden layer nodes and two output nodes is firstly developed for the deterministic response analysis. Then a back propagation training algorithm with Bayesian regularization is used to train the network. The trained network is then successfully combined with a direct Monte Carlo Simulation (MCS) to perform a probabilistic response analysis of geometrically nonlinear truss structures. Finally, the proposed ANN is applied to predict the response of a geometrically nonlinear truss structure. It is found that the proposed ANN is very efficient and reasonable in predicting the response of geometrically nonlinear truss structures.

• Journal of KSNVE
• /
• v.2 no.4
• /
• pp.273-280
• /
• 1992

The prediction of vibration response of floor is necessary in order to check whether the floor vibration level will satisfy the allowable vibration standard of precise machinery such as electronic microscopes in semiconductor manufacturing plant before the installation of various neighboring equipment facility. In conventional vibration isolation, we were mainly interested in minimization of vibration transmissibility and stabilization of vibration isolation system. But in order to predict vibration response of floor, it is necessary to know exciting force of equipment installed on the floor and the mobility of the floor. We measured the exciting force of the dropped mass assumed as equipment and the mobility of some practical building floor using large impact hammer. And from this we predicted the vibration response of floor on which the mass dropped. This predicted vibration response of floor is compared with measured vibration response. Through upper procedure, we examined the possibility of predicting vibration response of floor from the information of exciting force of equipment and the mobility of floor.

• Transactions of Materials Processing
• /
• v.29 no.5
• /
• pp.241-250
• /
• 2020

In this study, the methodology of the springback prediction of automotive parts applied 3rd generation AHSS was investigated using the response surface model analysis based on a regression model, and the meta model analysis based on a Kriging model. To design the learning data set for constructing the springback prediction models, and the experimental design was conducted at three levels for each processing variable using the definitive screening designs method. The hat-shaped member, which is the basic shape of the member parts, was selected and the springback values were measured for each processing type and processing variable using the finite element analysis. When the nonlinearity of the variables is small during the hat-shaped member forming, the response surface model and the meta model can provide the same processing parameter. However, the accuracy of the springback prediction of the meta model is better than the response surface model. Even in the case of the simple shape parts forming, the springback prediction accuracy of the meta model is better than that of the response surface model, when more variables are considered and the nonlinearity effect of the variables is large. The efficient global optimization algorithm-based Kriging is appropriate in resolving the high computational complexity optimization problems such as developing automotive parts.

• Earthquakes and Structures
• /
• v.8 no.5
• /
• pp.957-976
• /
• 2015

Recently, two energy-based response parameters, i.e., the absolute and the relative elastic input energy equivalent velocity, have been receiving a lot of research attention. Several studies, in fact, have demonstrated the potential of these intensity measures in the prediction of the seismic structural response. Although some ground motion prediction equations have been developed for these parameters, they only provide marginal distributions without information about the joint occurrence of the spectral values at different periods. In order to build new prediction models for the two equivalent velocities, a large set of ground motion records is used to calculate the correlation coefficients between the response spectral values corresponding to different periods and components of the ground motion. Then, functional forms adopted in models from the literature are calibrated to fit the obtained data. A new functional form is proposed to improve the predictions of the considered models from the literature. The components of the ground motion considered in this study are the two horizontal ones only. Potential uses of the proposed equations in addition to the prediction of the correlation coefficients of the equivalent velocity spectral values are shown, such as the prediction of derived intensity measures and the development of conditional mean spectra.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.20 no.1
• /
• pp.45-54
• /
• 2016

This study suggests a prediction model of ground motion spectral shape considering characteristics of earthquake records in Korea. Based on the Graizer and Kalkan's prediction procedure, a spectral shape model is defined as a continuous function of period in order to improve the complex problems of the conventional models. The approximate spectral shape function is then developed with parameters such as moment magnitude, fault distance, and average shear velocity of independent variables. This paper finally determines estimator coefficients of subfunctions which explain the corelation among the independent variables using the nonlinear optimization. As a result of generating the prediction model of ground motion spectral shape, the ground motion spectral shape well estimates the response spectrum of earthquake recordings in Korea.

• ETRI Journal
• /
• v.31 no.2
• /
• pp.162-172
• /
• 2009

A linear-prediction-based blind equalization algorithm for single-input single-output (SISO) finite impulse response/infinite impulse response (FIR/IIR) channels is proposed. The new algorithm is based on second-order statistics, and it does not require channel order estimation. By oversampling the channel output, the SISO channel model is converted to a special single-input multiple-output (SIMO) model. Two forward linear predictors with consecutive prediction delays are applied to the subchannel outputs of the SIMO model. It is demonstrated that the partial parameters of the SIMO model can be estimated from the difference between the prediction errors when the length of the predictors is sufficiently large. The sufficient filter length for achieving the optimal prediction is also derived. Based on the estimated parameters, both batch and adaptive minimum-mean-square-error equalizers are developed. The performance of the proposed equalizers is evaluated by computer simulations and compared with existing algorithms.

• Communications for Statistical Applications and Methods
• /
• v.7 no.3
• /
• pp.741-757
• /
• 2000

In may experimental situations, whenever a block design is used, the block effect is usually considered to be fixed. There are, however, experimental situations in which it should be treated as random. The choice of a blocking arrangement for a response surface design can have a considerable effect on estimating the mean response and on the size of he prediction variance even if the experimental runs re the same. Therefore, care should be exercised in the selection of blocks. In this paper, in the presence of a random block effect, we propose a graphical method or evaluating the effect of blocking in response surface designs using cuboidal regions. This graphical method can be used to investigate how the blocking has influence on the prediction variance throughout all experimental regions of interest when this region is cuboidal, and compare the block effects in the cases of the orthogonal and non-orthogonal block designs, respectively.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.8
• /
• pp.707-716
• /
• 2013

Tire noise is divided into two parts. One is pattern noise the other one is road noise. Pattern noise primarily occurs in over 500 Hz frequency but road noise occurs mainly in low frequency. It is important to develop a technology to predict the pattern noise at the design stage. Prediction technology of pattern noise has been developed by using image processing. Shape of tire pattern is computed by using imaging signal processing. Its results are different with the measured one. Therefore, the prediction of actual measured pattern noise is valuable. In the signal processing theory is applied to calculate the impulse response for the measurement environment. This impulse response used for the prediction of pattern noise by convolving this impulse response by the results of image processing of tire pattern.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.2
• /
• pp.123-129
• /
• 2012

It was previously suggested the design sensitivity analysis based on transmissibility function to identify the most sensitive response location over a small design modification. On the other hand, energy isoclines were used to predict the fatigue damage with acceleration response only. Both of previous studies commonly tackle the engineering problem using the acceleration response alone such that it may be possible to investigate the relationship between sensitivity analysis and accumulated fatigue damage. In this paper, it is suggested the novel method of vibration fatigue prediction using design sensitivity analysis to enhance the accuracy of predicted accumulated fatigue. Uni-axial vibration testing is performed with a simple notched specimen and the prediction of fatigue damage is conducted using accelerations measured at different locations. It can be concluded that the accuracy of predicted fatigue damage is proportional to the sensitivity index of the responsible location.