• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.20-26
• /
• 2008

As they have more and more intelligence robots or computers these days, so the interaction between intelligence robot(computer) - human is getting more and more important also the emotion recognition and expression are indispensable for interaction between intelligence robot(computer) - human. In this paper, firstly we extract emotional features at speech signal and facial image. Secondly we apply both BL(Bayesian Learning) and PCA(Principal Component Analysis), lastly we classify five emotions patterns(normal, happy, anger, surprise and sad) also, we experiment with decision fusion and feature fusion to enhance emotion recognition rate. The decision fusion method experiment on emotion recognition that result values of each recognition system apply Fuzzy membership function and the feature fusion method selects superior features through SFS(Sequential Forward Selection) method and superior features are applied to Neural Networks based on MLP(Multi Layer Perceptron) for classifying five emotions patterns. and recognized result apply to 2D facial shape for express emotion.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.371-377
• /
• 2020

Combustion instability occurred in the combustion test of solid rocket motor with large aspect ration Length/Diameter (L/D) and cylinder-slot grain. As a result of spectral analysis of the pressure perturbation, it was confirmed that the central axis longitudinal frequency was dominant, so that the length of the cylinder part was increased to eliminate the coincidence with acoustic node. In addition, acoustic modal analysis and flow analysis were performed to analyze the cause of instability by unsteady flow structure in solid rocket motors. It was confirmed that the combustion instability is reduced by quantitative comparison of the amplitude and frequencies of the pressure inside the combustion chamber using the grain shape before and after the design change. Finally, a combustion test was performed to verify that the combustion instability was resolved as in the flow analysis.

• Journal of the Korean Institute of Gas
• /
• v.21 no.1
• /
• pp.18-26
• /
• 2017

This work proposes an alternative pipe wall-thinning inspection method based on change of eigenfrequencies of shell vibration modes in wall-thinned pipes. It takes much time to detect wall-thinning of pipes using ultrasonic thickness gauge and only a limited number of pipes are under regular inspection. In a pipe with locally decreased thickness, stiffness varies along circumferential direction and natural frequencies of shell vibration modes of the pipe change or frequencies of same modes bifurcate into two different values. Therefore, one can monitor pipe wall-thinning by measuring change of natural frequencies or estimate wall-thinning shape qualitatively. The feasibility of the proposed method was studied by FE vibration analysis for wall-thinned pipes. Modal testing was also carried out for the pipes with artificial wall-thinned section to verify the working performance of the suggested technique.

• Nuclear Engineering and Technology
• /
• v.42 no.1
• /
• pp.97-108
• /
• 2010

Fluid-elastic instability and turbulence-induced vibration of steam generator U-tubes of a nuclear power plant are studied numerically to investigate the effect of design changes of support structures in the upper region of the tubes. Two steam generator models, Model A and Model B, are considered in this study. The main design features of both models are identical except for the conditions of vertical and horizontal support bars. The location and number of vertical and horizontal support bars at the middle of the U-bend region in Model A differs from that of Model B. The stability ratio and the amplitude of turbulence-induced vibration are calculated by a computer program based on the ASME code. The mode shape with a large modal displacement at the upper region of the U-tube is the key parameter related to the fretting wear between the tube and its support structures, such as vertical, horizontal, and diagonal support bars. Therefore, the location and the number of vertical and horizontal support bars have a great influence on the fretting wear mechanism. The variation in the stability ratios for each vibrational mode is compared with respect to Model A and Model B. Even though both models satisfy the design criteria, Model A shows substantial improvements over Model B, particularly in terms of having greater amplitude margins in the turbulence-excited vibration (especially at the inner region of the tube bundle) and better stability ratios for the fluid-elastic instability.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.7 no.4
• /
• pp.81-87
• /
• 2003

In this paper, the feasibility of using Shannon's sampling theorem to reconstruct exact mode shapes of a structural system from a limited number of sensor points and localizing damage in that structure with reconstructed mode shapes is investigated. Shannon's sampling theorem for the time domain is reviewed. The theorem is then extended to the spatial domain. To verify the usefulness of extended theorem, mode shapes of a simple beam are reconstructed from a limited amount of data and the reconstructed mode shapes are compared to the exact mode shapes. On the basis of the results, a simple rule is proposed for the optimal placement of accelerometers in modal parameter extraction experiments. Practicality of the proposed rule and the extended Shannon's theorem is demonstrated by detecting damage in laboratory beam structure with two-span via applying to mode shapes of pre and post damage states.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.1
• /
• pp.50-60
• /
• 2019

Recently, problems with excessive vibration of the radar masts of large bulk carriers and crude oil tankers have frequently been reported. This paper explores a design method to avoid the resonance of a radar mast installed on a large ship using various design of experiment (DOE) methods. A local vibration test was performed during an actual sea trial to determine the excitation sources of the vibration related to the resonant frequency of the radar mast. DOE methods such as the orthogonal array (OA) and Latin hypercube design (LHD) methods were used to analyze the Pareto effects on the radar mast vibration. In these DOE methods, the main vibration performances such as the natural frequency and weight of the radar mast were set as responses, while the shape and thickness of the main structural members of the radar mast were set as design factors. From the DOE-based Pareto effect results, we selected the significant structural members with the greatest influence on the vibration characteristics of the radar mast. Full factorial design (FFD) was applied to verify the Pareto effect results of the OA and LHD methods. The design of the main structural members of the radar mast to avoid resonance was reviewed, and a normal mode analysis was performed for each design using the finite element method. Based on the results of this normal mode analysis, we selected a design case that could avoid the resonance from the major excitation sources. In addition, a modal test was performed on the determined design to verify the normal mode analysis results.

• Structural Engineering and Mechanics
• /
• v.77 no.1
• /
• pp.47-56
• /
• 2021

This paper deals with damage detection using a Gapped Smoothing Method (GSM) combined with deep learning. Convolutional Neural Network (CNN) is a model of deep learning. CNN has an input layer, an output layer, and a number of hidden layers that consist of convolutional layers. The input layer is a tensor with shape (number of images) × (image width) × (image height) × (image depth). An activation function is applied each time to this tensor passing through a hidden layer and the last layer is the fully connected layer. After the fully connected layer, the output layer, which is the final layer, is predicted by CNN. In this paper, a complete machine learning system is introduced. The training data was taken from a Finite Element (FE) model. The input images are the contour plots of curvature gapped smooth damage index. A free-free beam is used as a case study. In the first step, the FE model of the beam was used to generate data. The collected data were then divided into two parts, i.e. 70% for training and 30% for validation. In the second step, the proposed CNN was trained using training data and then validated using available data. Furthermore, a vibration experiment on steel damaged beam in free-free support condition was carried out in the laboratory to test the method. A total number of 15 accelerometers were set up to measure the mode shapes and calculate the curvature gapped smooth of the damaged beam. Two scenarios were introduced with different severities of the damage. The results showed that the trained CNN was successful in detecting the location as well as the severity of the damage in the experimental damaged beam.

• Structural Engineering and Mechanics
• /
• v.78 no.5
• /
• pp.599-610
• /
• 2021

Early detection of small concrete crack or reinforcement corrosion is necessary for Structural Health Monitoring (SHM). Global vibration based methods are advantageous over local methods because of simple equipment installation and cost efficiency. Among vibration based techniques, FRF based methods are preferred over modal based methods. In this study, a new coupled method using frequency response function (FRF) and proper orthogonal modes (POM) is proposed by using the dynamic characteristic of a damaged beam. For the numerical simulation, wave finite element (WFE), coupled with traditional finite element (FE) method is used for effectively incorporating the damage related information and faster computation. As reported in literature, hybrid combination of wave function based wave finite element method and shape function based finite element method can addresses the mid frequency modelling difficulty as it utilises the advantages of both the methods. It also reduces the dynamic matrix dimension. The algorithms are implemented on a three-dimensional reinforced concrete beam. Damage is modelled and studied for two scenarios, i.e., crack in concrete and rebar corrosion. Single and multiple damage locations with different damage length are also considered. The proposed methodology is found to be very sensitive to both single- and multiple- damage while being computationally efficient at the same time. It is observed that the detection of damage due to corrosion is more challenging than that of concrete crack. The similarity index obtained from the damage parameters shows that it can be a very effective indicator for appropriately indicating initiation of damage in concrete structure in the form of spread corrosion or invisible crack.

• Journal of Korean Association for Spatial Structures
• /
• v.22 no.3
• /
• pp.33-40
• /
• 2022

Recently, cultural heritages in South Korea gain many interests of restoration and preservation from the government since many of that have been severely damaged during earthquakes. Many previous studies in both terms of experimental and analytical approaches have been done to examine structural behavior and decide appropriate methods of preservation. Being motivated by such researches, this research aims to investigate a religious stone pagoda dated back to the Goryeo Dynasty in Korea. The structure consists of a granite stone foundation and baked bricks, which resembles the shape of traditional pagodas. In order to examine the structural behavior of the pagoda, an analytical model is implemented using ANSYS, a comprehensive engineering simulation platform. For the time history analysis of the pagoda, several earthquake excitations are chosen and input to simulation modeling. Seismic response of the tower such as time domain, natural frequency, modal shapes and peak acceleration measured at each layer are presented and discussed. In addition, the amplification ratio of the tower is calculated from the accelerations of each layer to determine tower stability in accordance with Korean seismic design guide. The determination and evaluation of status and response of the brick tower by simulation analysis play an important role in the preservation of history as well as valuable architectural heritages in South Korea.

• Smart Structures and Systems
• /
• v.32 no.5
• /
• pp.319-338
• /
• 2023

The study presents a new hybrid data-driven method by combining radial basis functions neural networks (RBF-NN) with the Jaya algorithm (JA) to provide effective structural health monitoring of arch dams. The novelty of this approach lies in that only one user-defined parameter is required and thus can increase its effectiveness and efficiency, as compared to other machine learning techniques that often require processing a large amount of training and testing model parameters and hyper-parameters, with high time-consuming. This approach seeks rapid damage detection in arch dams under dynamic conditions, to prevent potential disasters, by utilizing the RBF-NNN to seamlessly integrate the dynamic elastic modulus (DEM) and modal parameters (such as natural frequency and mode shape) as damage indicators. To determine the dynamic characteristics of the arch dam, the JA sequentially optimizes an objective function rooted in vibration-based data sets. Two case studies of hyperbolic concrete arch dams were carefully designed using finite element simulation to demonstrate the effectiveness of the RBF-NN model, in conjunction with the Jaya algorithm. The testing results demonstrated that the proposed methods could exhibit significant computational time-savings, while effectively detecting damage in arch dam structures with complex nonlinearities. Furthermore, despite training data contaminated with a high level of noise, the RBF-NN and JA fusion remained the robustness, with high accuracy.