• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.713-725
• /
• 2022

Mostly, artificial intelligence does not show any definite change in emotions. For this reason, it is hard to demonstrate empathy in communication with humans. If frequency modification is applied to neutral emotions, or if a different emotional frequency is added to them, it is possible to develop artificial intelligence with emotions. This study proposes the emotion conversion using the Generative Adversarial Network (GAN) based voice frequency synthesis. The proposed method extracts a frequency from speech data of twenty-four actors and actresses. In other words, it extracts voice features of their different emotions, preserves linguistic features, and converts emotions only. After that, it generates a frequency in variational auto-encoding Wasserstein generative adversarial network (VAW-GAN) in order to make prosody and preserve linguistic information. That makes it possible to learn speech features in parallel. Finally, it corrects a frequency by employing Amplitude Scaling. With the use of the spectral conversion of logarithmic scale, it is converted into a frequency in consideration of human hearing features. Accordingly, the proposed technique provides the emotion conversion of speeches in order to express emotions in line with artificially generated voices or speeches.

• Structural Engineering and Mechanics
• /
• v.81 no.6
• /
• pp.769-780
• /
• 2022

This paper studies the dynamic behavior of laminated composite circular cylindrical shells interacting with a fluid. The mathematical formulation of the dynamic problem for an elastic body is developed based on the variational principle of virtual displacements and the relations of linear elasticity theory. The behavior of an ideal compressible fluid is described by the potential theory, the equations of which together with boundary conditions are transformed to a weak form. The hydrodynamic pressure exerted by the fluid on the internal surface of the shell is calculated according to the linearized Bernoulli equation. The numerical implementation of the mathematical formulation has been done using the semi-analytical finite element method. The influence of the ply angle and lay-up configurations of laminated composites on the natural vibration frequencies and the hydroelastic stability boundary have been analyzed for shells with different geometrical dimensions and under different kinematic boundary conditions set at their edges. It has been found that the optimal value of the ply angle depends on the level of filling of the shell with a fluid. The obtained results support the view that by choosing the optimal configuration of the layered composite material it is possible to change upwards or downwards the frequency and mode shape, as well as the critical velocity for stability loss over a wide range.

• Structural Engineering and Mechanics
• /
• v.84 no.5
• /
• pp.651-664
• /
• 2022

A precise prediction of the ultimate bond strength between rebar and surrounding concrete plays a major role in structural design, as it effects the load-carrying capacity and serviceability of a member significantly. In the present study, Gaussian models are employed for modelling bond strength of ribbed steel bars embedded in concrete. Gaussian models offer a non-parametric method based on Bayesian framework which is powerful, versatile, robust and accurate. Five different Gaussian models are explored in this paper-Gaussian Process (GP), Variational Heteroscedastic Gaussian Process (VHGP), Warped Gaussian Process (WGP), Sparse Spectrum Gaussian Process (SSGP), and Twin Gaussian Process (TGP). The effectiveness of the models is also evaluated in comparison to the numerous design formulae provided by the codes. The predictions from the Gaussian models are found to be closer to the experiments than those predicted using the design equations provided in various codes. The sensitivity of the models to various parameters, input feature space and sampling is also presented. It is found that GP, VHGP and SSGP are effective in prediction of the bond strength. For large data set, GP, VHGP, WGP and TGP can be computationally expensive. In such cases, SSGP can be utilized.

• Atmosphere
• /
• v.33 no.1
• /
• pp.33-47
• /
• 2023

In this study, for the application of observation errors to the Korean Integrated Model (KIM) to utilize the Constellation Observing System for Meteorology, Ionosphere & Climate-2 (COSMIC-2) new satellites, the observation errors were diagnosed based on the Desroziers method using the cost function in the process of variational data assimilation. We calculated observation errors for all observational species being utilized for KIM and compared with their relative values. The observation error of the calculated the Global Navigation Satellite System Radio Occultation (GNSS RO) was about six times smaller than that of other satellites. In order to balance with other satellites, we conducted two experiments in which the GNSS RO data expanded by about twice the observation error. The performance of the analysis field was significantly improved in the tropics, where the COSMIC-2 data are more available, and in the Southern Hemisphere, where the influence of GNSS RO data is significantly greater. In particular, the prediction performance of the Southern Hemisphere was improved by doubling the observation error in global region, rather than doubling the COSMIC-2 data only in areas with high density, which seems to have been balanced with other observations.

• Structural Engineering and Mechanics
• /
• v.90 no.1
• /
• pp.1-18
• /
• 2024

The present study conducts a thorough analysis of thermal vibrations in functionally graded porous nanocomposite beams within a thermal setting. Investigating the temperature-dependent material properties of these beams, which continuously vary across their thickness in accordance with a power-law function, a finite element approach is developed. This approach utilizes a nonlocal strain gradient theory and accounts for a linear temperature rise. The analysis employs four different patterns of porosity distribution to characterize the functionally graded porous materials. A novel two-variable shear deformation beam nonlocal strain gradient theory, based on trigonometric functions, is introduced to examine the combined effects of nonlocal stress and strain gradient on these beams. The derived governing equations are solved through a 3-nodes beam element. A comprehensive parametric study delves into the influence of structural parameters, such as thicknessratio, beam length, nonlocal scale parameter, and strain gradient parameter. Furthermore, the study explores the impact of thermal effects, porosity distribution forms, and material distribution profiles on the free vibration of temperature-dependent FG nanobeams. The results reveal the substantial influence of these effects on the vibration behavior of functionally graded nanobeams under thermal conditions. This research presents a finite element approach to examine the thermo-mechanical behavior of nonlocal temperature-dependent FG nanobeams, filling the gap where analytical results are unavailable.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.3
• /
• pp.229-235
• /
• 2013

To investigate the effect of the flexible artery wall on the blood flow, three-dimensional numerical simulations were carried out for analyzing the time-dependent incompressible flows of Newtonian fluids constrained by a flexible wall. The Navier-Stokes equations for fluid flow were solved using the P2P1 Galerkin finite element method, and mesh movement was achieved using an arbitrary Lagrangian-Eulerian formulation. The Newmark method was employed for solving the dynamic equilibrium equations for the deformation of a linear elastic solid. To avoid complexity due to the necessity of additional mechanical constraints, we used a combined formulation that includes both the fluid and structure equations of motion to produce a single coupled variational equation. The results showed that the flexibility of the carotid wall significantly affects flow phenomena during the pulse cycle. The flow field was also found to be strongly influenced by the bifurcation angle.

• Coupled systems mechanics
• /
• v.1 no.4
• /
• pp.361-379
• /
• 2012

This paper presents a fully coupled three-dimensional solver for the analysis of interaction between pulsatile flow and large deformation structure. A partitioned time marching algorithm is employed for the solution of the time dependent coupled discretised problem, enabling the use of highly developed, robust and well-tested solvers for each field. Conservative transfer of information at the fluid-structure interface is combined with an effective multi-predict-correct iterative scheme to enable implicit coupling of the interacting fields at each time increment. The three-dimensional unsteady incompressible fluid is solved using a powerful implicit time stepping technique and an ALE formulation for moving boundaries with second-order time accurate is used. A full spectrum of total variational diminishing (TVD) schemes in unstructured grids is allowed implementation for the advection terms and finite element shape functions are used to evaluate the solution and its variation within mesh elements. A finite element dynamic analysis of the highly deformable structure is carried out with a numerical strategy combining the implicit Newmark time integration algorithm with a Newton-Raphson second-order optimisation method. The proposed model is used to predict the wave flow fields of a particular flow-induced vibrational phenomenon, and comparison of the numerical results with available experimental data validates the methodology and assesses its accuracy. Another test case about three-dimensional biomedical model with pulsatile inflow is presented to benchmark the algorithm and to demonstrate the potential applications of this method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.2
• /
• pp.150-156
• /
• 2008

Many papers have shown that the hierarchical clustering method takes good-performance, but is limited because of its quadratic time complexity. In contrast, with a large number of variables, K-means reduces a time complexity. Think of the factor of simplify, high-quality and high-efficiency, we combine the two approaches providing a new system named CONDOR system with hierarchical structure based on document clustering using K-means algorithm. Evaluated the performance on different hierarchy depth and initial uncertain centroid number based on variational relative document amount correspond to given queries. Comparing with regular method that the initial centroids have been established in advance, our method performance has been improved a lot.

• Journal of the Korean institute of surface engineering
• /
• v.53 no.3
• /
• pp.95-103
• /
• 2020

In this study, the material used in the hot dip galvanizing equipment was poorly corrosion-resistant, so it was performed to solve the cost and time problems caused by equipment replacement. The theoretical calculation was performed using the DV-Xα method(Discrete Variational Local-density approximation method). The alloy (STS4XX series) of the equipment currently used has a martensite phase. Therefore, the theoretical calculation was performed by applying P4 / mmm, which is a tetragonal structure. The new alloy was chosen by designing theoretical values close to existing materials. Considering elements that contribute to corrosion, most have high prices. Therefore, the design was completed by adjusting the content using only the components of the reference material in the theoretical design. The final design alloys were chosen as D6 and D9. Designed D6 and D9 were dissolved and prepared using an induction furnace. After the heat treatment process was completed, the corrosion rate of the alloys was confirmed by using the potentiodynamic polarization test. The surface of the prepared alloys were processed horizontally and then polished to # 1200 using sand paper to perform potentiodynamic polarization test. Domestic products: 4.735 mpy (mils / year), D6: 0.9166 mpy, D9: 0.3372 mpy, alloys designed than domestic products had a lower corrosion rate. Therefore, the designed alloy was expected to have better erosion resistance.