• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.335-341
• /
• 2022

In this paper, we adopt a transformer that shows remarkable performance in natural language processing as an acoustic model of hybrid speech recognition. The transformer acoustic model uses attention structures to process sequential data and shows high performance with low computational cost. This paper proposes a method to improve the performance of transformer AM by applying each of the four algorithms of sequence discriminative training, a weighted finite-state transducer (wFST)-based learning used in the existing DNN-HMM model. In addition, compared to the Cross Entropy (CE) learning method, sequence discriminative method shows 5 % of the relative Word Error Rate (WER).

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.513-522
• /
• 2022

Due to the importance of accurate analysis of bearing capacity in civil engineering projects, this paper studies the efficiency of two novel metaheuristic-based models for this objective. To this end, black hole algorithm (BHA) and multi-verse optimizer (MVO) are synthesized with an artificial neural network (ANN) to build the proposed hybrid models. Based on the settlement of a two-layered soil (and a shallow footing) system, the stability values (SV) of 0 and 1 (indicating the stability and failure, respectively) are set as the targets. Each model predicted the SV for 901 stages. The results indicated that the BHA and MVO can increase the accuracy (i.e., the area under the receiving operating characteristic curve) of the ANN from 94.0% to 96.3 and 97.2% in analyzing the SV pattern. Moreover, the prediction accuracy rose from 93.1% to 94.4 and 95.0%. Also, a comparison between the ANN's error decreased by the BHA and MVO (7.92% vs. 18.08% in the training phase and 6.28% vs. 13.62% in the testing phase) showed that the MVO is a more efficient optimizer. Hence, the suggested MVO-ANN can be used as a reliable approach for the practical estimation of bearing capacity.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.167-183
• /
• 2022

In this paper, the free and forced vibration analysis of rotating cantilever nanoscale cylindrical beams and tubes is investigated under the external dynamic load to examine the nonlocal effect. A couple of nonlocal strain gradient theories with different beams and tubes theories, involving the Euler-Bernoulli, Timoshenko, Reddy beam theory along with the higher-order tube theory, are assumed to the mathematic model of governing equations employing the Hamilton principle in order to derive the nonlocal governing equations related to the local and accurate nonlocal boundary conditions. The two-dimensional functional graded material (2D-FGM), made by the axially functionally graded (AFG) in conjunction with the porosity distribution in the radial direction, is considered material modeling. Finally, the derived Partial Differential Equations (PDE) are solved via a couple of the generalized differential quadrature element methods (GDQEM) with the Newmark-beta techniques for the time-dependent results. It is indicated that the boundary conditions equations play a crucial task in responding to nonlocal effects for the cantilever structures.

• Coupled systems mechanics
• /
• v.12 no.3
• /
• pp.241-260
• /
• 2023

The objective of this study is to evaluate the effects of adding fibers to concrete and the distribution rate of the porosity on the interfacial stresses of the beams strengthened with various types of functionally graded porous (FGP) plate. Toward this goal, the beams strengthened with FGP plate were considered and subjected to uniform loading. Three types of beams are considered namely RC beam, RC beam reinforced with metal fibers (RCFM) and RC beam reinforced with Alfa fibers (RCFA). From an analytical development, shear and normal interfacial stresses along the length of the FGP plates were obtained. The accuracy and validity of the proposed theoretical formula are confirmed by the others theoretical results. The results showed clearly that adding fibers to concrete and the distribution rate of the porosity have significant influence on the interfacial stresses of the beams strengthened with FGP plates. Finally, parametric studies are carried out to demonstrate the effect of the mechanical properties and thickness variations of FGP plate, concrete and adhesive on interface debonding, we can conclude that, This research is helpful for the understanding on mechanical behavior of the interface and design of the FRP-RC hybrid structures.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.281-291
• /
• 2022

Surmounting complexities in analyzing the mechanical parameters of concrete entails selecting an appropriate methodology. This study integrates a novel metaheuristic technique, namely satin bowerbird optimizer (SBO) with artificial neural network (ANN) for predicting uniaxial compressive strength (UCS) of concrete. For this purpose, the created hybrid is trained and tested using a relatively large dataset collected from the published literature. Three other new algorithms, namely Henry gas solubility optimization (HGSO), sunflower optimization (SFO), and vortex search algorithm (VSA) are also used as benchmarks. After attaining a proper population size for all algorithms, the Utilizing various accuracy indicators, it was shown that the proposed ANN-SBO not only can excellently analyze the UCS behavior, but also outperforms all three benchmark hybrids (i.e., ANN-HGSO, ANN-SFO, and ANN-VSA). In the prediction phase, the correlation indices of 0.87394, 0.87936, 0.95329, and 0.95663, as well as mean absolute percentage errors of 15.9719, 15.3845, 9.4970, and 8.0629%, calculated for the ANN-HGSO, ANN-SFO, ANN-VSA, and ANN-SBO, respectively, manifested the best prediction performance for the proposed model. Also, the ANN-VSA achieved reliable results as well. In short, the ANN-SBO can be used by engineers as an efficient non-destructive method for predicting the UCS of concrete.

• Steel and Composite Structures
• /
• v.49 no.1
• /
• pp.47-64
• /
• 2023

Due to their efficient use of materials, hybrid reinforced concrete-steel (RCS) systems provide more practical and economic advantages than traditional steel and concrete moment frames. This study evaluated the seismic design factors and response modification factor 'R' of RCS composite moment frames composed of reinforced concrete (RC) columns and steel (S) beams. The current International Building Code (IBC) and ASCE/SEI 7-05 classify RCS systems as special moment frames and provide an R factor of 8 for these systems. In this study, seismic design parameters were initially quantified for this structural system using an R factor of 8 based on the global methodology provided in FEMA P695. For analyses, multi-story (3, 5, 10, and 15) and multi-span (3 and 5) archetypes were used to conduct nonlinear static pushover analysis and incremental dynamic analysis (IDA) under near-field and far-field ground motions. The analyses were performed using the OpenSees software. The procedure was reiterated with a larger R factor of 9. Results of the performance evaluation of the investigated archetypes demonstrated that an R factor of 9 achieved the safety margin against collapse outlined by FEMA P695 and can be used for the design of RCS systems.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.340-351
• /
• 2023

Wearable sensors designed for strain, pressure, and temperature measurements are essential for monitoring human movements, health status, physiological data, and responses to external stimuli. Notably, recent research has led to the development of high-performance wearable sensors using innovative materials and device structures that exhibit ultra-high sensitivity compared with their commercial counterparts. However, the quest for accurate sensing has identified a critical challenge. Specifically, the mechanical flexibility of the substrates in wearable sensors can introduce interference signals, particularly when subjected to varying external stimuli and environmental conditions, potentially resulting in signal crosstalk and compromised data fidelity. Consequently, the pursuit of non-interference sensing technology is pivotal for enabling independent measurements of concurrent input signals related to strain, pressure, and temperature, ensuring precise signal acquisition. In this comprehensive review, we present an overview of the recent advances in noninterference sensing strategies. We explore various fabrication methods for sensing strain, pressure, and temperature, emphasizing the use of hybrid composite materials with distinct mechanical properties. This review contributes to the understanding of critical developments in wearable sensor technology that are vital for their ongoing application and evolution in numerous fields.

• Smart Structures and Systems
• /
• v.32 no.6
• /
• pp.393-402
• /
• 2023

Recently, hybrid and electric vehicles have been actively developed to replace internal combustion engine (ICE) vehicles. However, their vibrations and noise with complex spectra cause discomfort to drivers. To reduce the vibrations transmitted through primary excitation sources such as powertrains, structural changes have been introduced. However, the interference among different parts is a limitation. Thus, active mounting systems based on smart materials have been actively investigated to overcome these limitations. This study focuses on diminishing the source movement when a structure with two active mounting systems is excited to a single sinusoidal and a multi-frequency signal, which were investigated for source movement reduction. The overall structure was modeled based on the lumped parameter method. Active vibration control was implemented based on the modeled structure, and a multi-normalization least mean square (NLMS) algorithm was used to obtain the control input for the active mounting system. Furthermore, the performance of the NLMS algorithm was compared with that of the quantification method to demonstrate the performance of active vibration control. The results demonstrate that the vibration attenuation performance of the source component was improved.

• Wind and Structures
• /
• v.38 no.6
• /
• pp.461-475
• /
• 2024

A reliable wind speed forecasting method is crucial for the applications in wind engineering. In this study, the generalized S-transform (GST) is innovatively applied for wind speed forecasting to uncover the time-frequency characteristics in the non-stationary wind speed data. The improved grey wolf optimizer (IGWO) is employed to optimize the adjustable parameters of GST to obtain the best time-frequency resolution. Then a hybrid method based on IGWO-optimized GST is proposed to validate the effectiveness and superiority for multi-step non-stationary wind speed forecasting. The historical wind speed is chosen as the first input feature, while the dynamic time-frequency characteristics obtained by IGWO-optimized GST are chosen as the second input feature. Comparative experiment with six competitors is conducted to demonstrate the best performance of the proposed method in terms of prediction accuracy and stability. The superiority of the GST compared to other time-frequency analysis methods is also discussed by another experiment. It can be concluded that the introduction of IGWO-optimized GST can deeply exploit the time-frequency characteristics and effectively improving the prediction accuracy.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.3
• /
• pp.575-583
• /
• 2017

Various types of flow patterns around the stepped weir and spillway, such as the skimming flow over such structures and the wave-type flow with a standing undular hydraulic jump and roller downstream of the structures, are developed in open channels. Unsteady three-dimensional numerical simulations are carried out using a hybrid RANS-LES turbulence modeling approach and the volume of fluid method for resolving free surface fluctuations to represent the turbulent flow including the skimming flow and wave-type flow over a stepped weir installed in a rectangular channel. The comparison of numerical results with an existing experimental measurement reveals that the present numerical simulations reasonably well reproduce the turbulent flow passing the stepped weir, in terms of time-averaged velocity profiles at selected locations downstream of the weir, flow topology characterized by the wave-type and skimming flows, the maximum height and length of the standing wave and the length of reattachment of recirculating zone. The numerical result further elucidates the distinct flow behaviors of the wave-type and skimming flow by presenting instantaneous intense variations of free surface and velocity vectors, the distributions of Reynolds shear stress and turbulent kinetic energy and three-dimensional complex features of coherent structures and total pressure distribution.