• Structural Engineering and Mechanics
• /
• v.87 no.3
• /
• pp.231-242
• /
• 2023

A novel combinatorial type-2 adaptive neuro-fuzzy inference system (T2-ANFIS) and robust proportional integral derivative (PID) control framework for intelligent vibration mitigation of uncertain structural system is introduced. The fuzzy logic controllers (FLCs), are designed independently of the mathematical model of the system. The type-1 FLCs, have a limited ability to reduce the effect of uncertainty, due to their fuzzy sets with a crisp degree of membership. In real applications, the consequent part of the fuzzy rules is uncertain. The type-2 FLCs, are robust to the fuzzy rules and the process parameters due to the fuzzy degree of membership functions and footprint of uncertainty (FOU). The adaptivity of the proposed method is provided with the optimum tuning of the parameters using the neural network training algorithms. In our approach, the PID control force is obtained using the generalized type-2 neuro-fuzzy in such a way that the stability and robustness of the controller are guaranteed. The robust performance and stability of the presented framework are demonstrated in a numerical study for an eleven-story seismically-excited building structure combined with an active tuned mass damper (ATMD). The results indicate that the introduced type-2 neuro-fuzzy PID control scheme is effective to attenuate plant states in the presence of the structured and unstructured uncertainties, compared to the conventional, type-1 FLC, type-2 FLC, and type-1 neuro-fuzzy PID controllers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.127-130
• /
• 2022

This paper is a study on singing voice synthesis modeling using a generator loss function, which analyzes various factors that may occur when applying BEGAN among deep learning algorithms optimized for image generation to Audio domain. and we conduct experiments to derive optimal quality. In this paper, we focused the problem that the L1 loss proposed in the BEGAN-based models degrades the meaning of hyperparameter the gamma(𝛾) which was defined to control the diversity and quality of generated audio samples. In experiments we show that our proposed method and finding the optimal values through tuning, it can contribute to the improvement of the quality of the singing synthesis product.

• Journal of Powder Materials
• /
• v.31 no.2
• /
• pp.137-145
• /
• 2024

In order to predict the process window of laser powder bed fusion (LPBF) for printing metallic components, the calculation of volumetric energy density (VED) has been widely calculated for controlling process parameters. However, because it is assumed that the process parameters contribute equally to heat input, the VED still has limitation for predicting the process window of LPBF-processed materials. In this study, an explainable machine learning (xML) approach was adopted to predict and understand the contribution of each process parameter to defect evolution in Ti alloys in the LPBF process. Various ML models were trained, and the Shapley additive explanation method was adopted to quantify the importance of each process parameter. This study can offer effective guidelines for fine-tuning process parameters to fabricate high-quality products using LPBF.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.165-171
• /
• 2024

In this study, we present a novel approach for enhancing chest X-ray image classification (normal, Covid-19, edema, mass nodules, and pneumothorax) by combining contrastive learning and machine learning algorithms. A vast amount of unlabeled data was leveraged to learn representations so that data efficiency is improved as a means of addressing the limited availability of labeled data in X-ray images. Our approach involves training classification algorithms using the extracted features from a linear fine-tuned Momentum Contrast (MoCo) model. The MoCo architecture with a Resnet34, Resnet50, or Resnet101 backbone is trained to learn features from unlabeled data. Instead of only fine-tuning the linear classifier layer on the MoCopretrained model, we propose training nonlinear classifiers as substitutes for softmax in deep networks. The empirical results show that while the linear fine-tuned ImageNet-pretrained models achieved the highest accuracy of only 82.9% and the linear fine-tuned MoCo-pretrained models an increased highest accuracy of 84.8%, our proposed method offered a significant improvement and achieved the highest accuracy of 87.9%.

• Journal of Korean Society of Steel Construction
• /
• v.26 no.3
• /
• pp.177-189
• /
• 2014

When floor vibration problems occur in existing buildings, TMD (tuned mass damper) can be a viable alternative to resolving the problem. Only when TMD has been exactly tuned to the natural frequency of the floor, it can control the vibration as intended in design. However, TMD gets inefficient in the situation where the natural frequency changes as a result of the uncontrollable variation of the floor mass weight. This physical phenomenon is often called as TMD-off-tuning. This study proposes asymmetric TMD for enhancing the robustness of floor vibration control against uncertain natural frequencies. The proposed TMD features two asymmetric linear springs such that the floor vibrational energy can be dissipated through both the translational and rotational motion. An easy-to-use graphical optimization method was developed in this study. The asymmetric TMD proposed outperformed in vibration control by 28% compared to that of conventional TMD. The robustness of asymmetric TMD of this study was two times higher than that of conventional TMD.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.7
• /
• pp.3140-3145
• /
• 2012

In this paper, a design method for a compact slot antenna fed by a coplanar waveguide (CPW) is studied. A T-shaped tuning stub is inserted inside a narrow rectangular slot and the slot is impedance matched to the CPW feedline by adjusting the width, length, and position of the stub. The resonance frequency is adjustable by the slot length and the antenna size can be reduced by bending the slot. The resonance frequency and impedance matching property of the compact slot antenna are similar to those of the half-wavelength slot antenna, which enables one to design compact antenna of this type with ease. A compact slot antenna for 2.45-GHz ISM band is designed, fabricated on an FR4 substrate (dielectric constant of 4.4 and thickness of 0.8 mm), and experimentally tested. The measured results agree well with the simulations, which confirms the validity of this study. The fabricated compact slot antenna shows an impedance bandwidth of 200 MHz(2.32-2.52 GHz) for a VSWR < 2, which is suitable for 2.45-GHz ISM band (2.4-2.48 GHz). The measured radiation patterns show ${\infty}$-shaped directional pattern in the E-plane and nearly omni-directional pattern in the H-plane with a peak gain of 2.0 dBi, which are similar to those of a monopole antenna. The proposed antenna is expected to be suitable for the applications as antennas for WLAN, RFID, and mobile handset.

• Korean Journal of Optics and Photonics
• /
• v.29 no.6
• /
• pp.241-246
• /
• 2018

In this paper, a low-cost optical temperature sensor is implemented, using a fiber Bragg grating (FBG) as the temperature probe and a low-cost VCSEL with temperature-dependent output wavelength as the light source. To analyze the wavelength of the reflected light from the FBG, an interrogation was applied using a method of referring to the internal temperature according to the output wavelength of the VCSEL. When the temperature of the VCSEL was adjusted from 14 to $52.2^{\circ}C$, the output wavelength varied from 1519.90 to 1524.25 nm. The degree of wavelength tuning according to temperature was $0.114nm/^{\circ}C$. The variable wavelength repeatability error according to temperature was ${\pm}0.003nm$, and the temperature measurement error was ${\pm}0.18^{\circ}C$. As a result of measuring the temperatures from 22.3 to $194.2^{\circ}C$, the value of the internal temperature change of the light source according to the applied temperature ${\Delta}T$ was $0.146^{\circ}C/{\Delta}T$, the change in reflected wavelength of the temperature probe according to applied temperature ${\Delta}T$ was measured at $16.64pm/^{\circ}C$. and the temperature measurement error of the sensor was ${\pm}1^{\circ}C$.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.117-125
• /
• 2023

In the development of clothing design through virtual simulation, it is essential to minimize the differences between the virtual and the real world as much as possible. The most critical task to enhance the similarity between virtual and real garments is to find simulation parameters that can closely emulate the physical properties of the actual fabric in use. The simulation parameter optimization process requires manual tuning by experts, demanding high expertise and a significant amount of time. Especially, considerable time is consumed in repeatedly running simulations to check the results of applying the tuned simulation parameters. Recently, to tackle this issue, artificial neural network learning models have been proposed that swiftly estimate the results of drape test simulations, which are predominantly used for parameter tuning. In these earlier studies, relatively simple linear stiffness models were used, and instead of estimating the entirety of the drape mesh, they estimated only a portion of the mesh and interpolated the rest. However, there is still a scarcity of research on non-linear stiffness models, which are commonly used in actual garment design. In this paper, we propose a learning model for estimating the results of drape simulations for non-linear stiffness models. Our learning model estimates the full high-resolution mesh model of drape. To validate the performance of the proposed method, experiments were conducted using three different drape test methods, demonstrating high accuracy in estimation.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.4
• /
• pp.333-343
• /
• 2009

The BPF designed by the formula based on strip line shows the center frequency shift and distortion in filter response and this becomes more significant with higher frequency. In this paper, the novel design based on EM simulation is proposed. In the design, the filter is decomposed into individual resonators and, for each resonator, the reactance slope and the inverter values are measured and tuned to desired design values for a inverter BPF prototype. The filter composed with such resonators shows the desired filter response without further tuning. This is because possible effects of discontinuities and dispersion are included in the filter parameter extraction. The method can generally apply to all filters that can be transformed into inverter BPF prototype. The procedure is verified by designing a 5th-order SIR filter and quite general to adapt into the design of a parallel coupled line filter, and hair-pin filter.

• Journal of Power Electronics
• /
• v.15 no.3
• /
• pp.753-762
• /
• 2015

This paper presents a nonlinear sliding mode control (SMC) scheme with a variable damping ratio for interior permanent magnet synchronous motors (IPMSMs). First, a nonlinear sliding surface whose parameters change continuously with time is designed. Actually, the proposed SMC has the ability to reduce the settling time without an overshoot by giving a low damping ratio at the initial time and a high damping ratio as the output reaches the desired setpoint. At the same time, it enables a fast convergence in finite time and eliminates the singularity problem with the upper bound of an uncertain term, which cannot be measured in practice, by using a simple adaptation law. To improve the efficiency of a system in the constant torque region, the control system incorporates the maximum torque per ampere (MTPA) algorithm. The stability of the nonlinear sliding surface is guaranteed by Lyapunov stability theory. Moreover, a simple sliding mode observer is used to estimate the load torque and system uncertainties. The effectiveness of the proposed nonlinear SMC scheme is verified using comparative experimental results of the linear SMC scheme when the speed reference and load torque change under system uncertainties. From these experimental results, the proposed nonlinear SMC method reveals a faster transient response, smaller steady-state speed error, and less sensitivity to system uncertainties than the linear SMC method.