• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.9-17
• /
• 2023

In this paper, we propose a one-class vibration anomaly detection system for bearing defect diagnosis. In order to reduce the economic and time loss caused by bearing failure, an accurate defect diagnosis system is essential, and deep learning-based defect diagnosis systems are widely studied to solve the problem. However, it is difficult to obtain abnormal data in the actual data collection environment for deep learning learning, which causes data bias. Therefore, a one-class classification method using only normal data is used. As a general method, the characteristics of vibration data are extracted by learning the compression and restoration process through AutoEncoder. Anomaly detection is performed by learning a one-class classifier with the extracted features. However, this method cannot efficiently extract the characteristics of the vibration data because it does not consider the frequency characteristics of the vibration data. To solve this problem, we propose an AutoEncoder model that considers the frequency characteristics of vibration data. As for classification performance, accuracy 0.910, precision 1.0, recall 0.820, and f1-score 0.901 were obtained. The network design considering the vibration characteristics confirmed better performance than existing methods.

• Composites Research
• /
• v.35 no.2
• /
• pp.106-114
• /
• 2022

Carbon fiber-reinforced plastic, well known high specific strength and high specific stiffness, have been widely used in the aircraft industry. Mostly the CFRP structure is fabricated by lamination of carbon fiber or carbon prepreg, which has major disadvantage called delamination. Delamination is usually produced due to absence of the through-thickness direction fiber. In this study, three-dimensional carbon preform woven in three directions is used for fabrication of aircraft wing unit structure, a part of repeated structure in aircraft wing. The unit structure include skin, stringer and rib were prepared by resin transfer molding method. After, the 3D structure was compared with laminate structure through compression test. The results show that 3D structure is not only effective to prevent delamination but improved the mechanical strength. Therefore, the 3d preform structure is expected to be used in various fields requiring delamination prevention, especially in the aircraft industry.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.

• Journal of the Korean Society for Heat Treatment
• /
• v.36 no.5
• /
• pp.303-310
• /
• 2023

β titanium alloys are widely used in aerospace industry due to their excellent specific strength and corrosion resistance. In particular, mechanical properties of metastable β titanium can efficiently be controlled by various deformation mechanisms such as slip, twinning, and SIM (Stress-Induced Martensite Transformation), making it an ideal material for many industrial applications. In this study, Ti-5Mo-xFe (x=1, 2, 4 wt%) alloy was designed by adding a relatively inexpensive β element to ensure price competitiveness. Additionally, microstructural analysis was conducted using OM, SEM, and XRD, while mechanical properties were evaluated through hardness and compression tests to consider the deformation mechanisms based on the Fe content. SIMT occurred in all three alloys and was influenced by the presence of β_m (metastable beta) and beta stability. As the Fe content decreased, the α'' phase increased due to SIMT occurring within the β_m phase, resulting in softening. Conversely, as the Fe content increased, the strength of the alloy increased due to a reduction in α'' formation and the contributions of solid solution strengthening and grain strengthening. Moreover, unlike the other alloys, shear bands were observed only in the fracture of the Ti-5Mo-4Fe alloy, which was attributed to differences in texture and microstructure.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.3
• /
• pp.41-50
• /
• 2007

The results from normally consolidated isotropic drained and undrained triaxial compression tests (NCIU and NCID) on sand with high silt content were presented in this paper. The experiments were performed on specimens of Nak-dong River sand with 63% silt content under effective confined pressures, 100 kPa to 400 kPa. From test results, Sandy silt became initially compressive but eventually appeared to provide dilatancy response throughout the entire stress-strain curve The behavior of sandy silt was more difficult to characterize than that of clay and sand due to lower plastic characteristic. Especially, the samples exhibited dilatancy development during shear after failure. The shear behavior and shear strength parameters of sandy silt can be determined as stress-strain behaviors are described by the Mohr-Coulomb failure criterion. The shear behaviors were observed increasing dilatancy volume change tendency with strain-softening tendency after failure. In this paper, the behavior of dilatancy depends on not only sand content but also fine content with low-cohesion during shear in the samples of sandy silt.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.107-112
• /
• 2022

In an embedded system such as a drone, it is difficult to store, transfer and analyze the entire hyper-spectral image to a server in real time because it takes a lot of power and time. Therefore, the hyper-spectral image data is transmitted to the server through dimension reduction or compression pre-processing. Feature selection method are used to send only the bands for analysis purpose, and these algorithms usually take a lot of processing time depending on the size of the image, even though the efficiency is high. In this paper, by improving the temporal disadvantage of the band selection algorithm, the time taken 24 hours was reduced to around 60-180 seconds based on the 40000*682 image resolution of 8GB data, and the use of 7.6GB RAM was significantly reduced to 2.3GB using 45 out of 150 bands. However, in terms of pixel classification performance, more than 98% of analysis results were derived similarly to the previous one.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.11
• /
• pp.33-40
• /
• 2023

This study explores the performance of pile foundations in highly expansive soil, incorporating magnesium oxide-based refractory materials. A controlled model chamber, housing a fixed pile, was utilized to induce ground expansion through fused magnesia (FM). The investigation focused on measuring the vertical displacement of FM-sand mixtures and the axial load on the pile in relation to depth and time. The study varied the amount of FM content (FM_c) at 30%, 50%, and 70%. The upward movement exhibited an augmentation with increasing FM_c, tapering off with depth as accumulation progressed toward the mixture surface. Compression and tensile forces were both evident along the pile for FM_c at 30% and 50%, while only a tensile force was observed at an FM_c of 70%. These results offer valuable insights for the analysis of pile behavior within FM-sand mixtures.

• Steel and Composite Structures
• /
• v.49 no.5
• /
• pp.533-546
• /
• 2023

Cost-effective solutions provided by composite construction are gaining popularity which, in turn, promotes the appearance on the market of new types of composite sections that allow not only to take advantage of the synergy of steel and concrete working together at room temperature, but also to improve their behaviour at high temperatures. When combined with high performance materials, significant load-bearing capacities can be achieved even with reduced cross-sectional dimensions. Steel-reinforced concrete-filled steel tubular (SR-CFST) columns are one of these innovative composite sections, where an open steel profile is embedded into a CFST section. Besides the renowned benefits of these typologies at room temperature, the fire protection offered by the surrounding concrete to the inner steel profile, gives them an enhanced fire performance which delays its loss of mechanical capacity in a fire scenario. The experimental evidence on the fire behaviour of SR-CFST columns is still scarce, particularly when combined with high performance materials. However, it is being much needed for the development of specific design provisions that consider the use of the inner steel profile in CFST columns. In this work, a new experimental program on the thermo-mechanical behaviour of SR-CFST columns is presented to extend the available experimental database. Ten SR-CFST stub columns, with circular and square geometries, combining high strength steel and concrete were tested. It was seen that the circular specimens reached higher failure times than the square columns, with the failure time increasing both when high strength steel was used at the embedded steel profile and high strength concrete was used as infill. Finally, different proposals for the reduction coefficients of high performance materials were assessed in the prediction of the cross-sectional fire resistance of the SR-CFST columns.

• Steel and Composite Structures
• /
• v.51 no.5
• /
• pp.543-562
• /
• 2024

While the external axial compressive load is applied to only the shell edge of stringer-stiffened shell in the most of numerical and analytical previous studies (entitled as conventional approach), a part of external load is applied to the stringers in real conditions. It leads to decrease the accuracy of the axial buckling load calculated by the conventional eigenvalue analysis approach performed in the most of previous studies. In this study, the distribution of stress in the pre-buckling analysis was enhanced by applying the axial external compressive load to both shell and stringers to perform an accurate eigenvalue analysis of the stringer-stiffened composite shell. In this regard, a model was developed in FORTRAN environment to simulate the laminated stringer-stiffened shell under axial compressive load using finite strip method. The axial buckling load of the shell was obtained through eigenvalue analysis. A comparison was made between the results obtained from the model and those available in the previous studies to evaluate the validity of the results obtained from the model. Through a parametric study, the effects of different parameters such as stringer properties and composite layup on the buckling load of the shell under different loading patterns were investigated. The results indicated that in some cases, the axial buckling load obtained for the conventional approach used in the most of previous studies is significantly overestimated or underestimated due to neglecting the stringer in distribution of external load applied to the stringer-stiffened shell. According to the results obtained from the parametric study, some graphs were derived to show the accuracy of the axial buckling load obtained from the conventional approach utilized in the literature.

• Journal of the Korean Wood Science and Technology
• /
• v.52 no.2
• /
• pp.157-174
• /
• 2024

This study investigates the influence of varying concentrations of boric acid (BA) preservative on the physical and mechanical properties of light red meranti (LRM) found in Sarawak. LRM or Shorea leprosula samples were treated with various concentrations of BA via the dip diffusion method using American Society for Testing and Materials (ASTM) standards. The physical property, particularly the retention rate and mechanical properties, bending strength, modulus of elasticity (MOE), tensile and compression strength parallel to grain of impregnated and control samples were tested to determine the effects of BA preservative. The retention rate was found to increase with increasing BA concentration and higher surface area to volume ratio. The mechanical properties in terms of the MOE and tensile strength parallel to grain were found to be greater than those of the control samples, whereas the bending strength and tensile strength parallel to grain were lower. Amongst the results, only the retention rate and MOE showed significant interaction effects at 5% level of significance between all factors tested (samples size and BA concentration for retention rate and BA concentration for MOE).