• Steel and Composite Structures
• /
• v.37 no.2
• /
• pp.193-209
• /
• 2020

In this paper, the efficiency of five Machine Learning (ML) methods consisting of Deep Learning (DL), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Gradient Tree Booting (GTB) for regression and classification of the Ultimate Load Factor (ULF) of nonlinear inelastic steel frames is compared. For this purpose, a two-story, a six-story, and a twenty-story space frame are considered. An advanced nonlinear inelastic analysis is carried out for the steel frames to generate datasets for the training of the considered ML methods. In each dataset, the input variables are the geometric features of W-sections and the output variable is the ULF of the frame. The comparison between the five ML methods is made in terms of the mean-squared-error (MSE) for the regression models and the accuracy for the classification models, respectively. Moreover, the ULF distribution curve is calculated for each frame and the strength failure probability is estimated. It is found that the GTB method has the best efficiency in both regression and classification of ULF regardless of the number of training samples and the space frames considered.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.4 no.3
• /
• pp.199-210
• /
• 2012

The recent researches on the automatic berthing control problems have used various kinds of tools as a control method such as expert system, fuzzy logic controllers and artificial neural network (ANN). Among them, ANN has proved to be one of the most effective and attractive options. In a marine context, the berthing maneuver is a complicated procedure in which both human experience and intensive control operations are involved. Nowadays, in most cases of berthing operation, auxiliary devices are used to make the schedule safer and faster but none of above researches has taken into account. In this study, ANN is applied to design the controllers for automatic ship berthing using assistant devices such as bow thruster and tug. Using back-propagation algorithm, we trained ANN with set of teaching data to get a minimal error between output values and desired values of four control outputs including rudder, propeller revolution, bow thruster and tug. Then, computer simulations of automatic berthing were carried out to verify the effectiveness of the system. The results of the simulations showed good performance for the proposed berthing control system.

• Journal of Communications and Networks
• /
• v.18 no.1
• /
• pp.27-39
• /
• 2016

This paper derives and analyzes a novel block fast Fourier transform (FFT) based joint detection algorithm. The paper compares the performance and complexity of the novel block-FFT based joint detector to that of the Cholesky based joint detector and single user detection algorithms. The novel algorithm can operate at chip rate sampling, as well as higher sampling rates. For the performance/complexity analysis, the time division duplex (TDD) mode of a wideband code division multiplex access (WCDMA) is considered. The results indicate that the performance of the fast FFT based joint detector is comparable to that of the Cholesky based joint detector, and much superior to that of single user detection algorithms. On the other hand, the complexity of the fast FFT based joint detector is significantly lower than that of the Cholesky based joint detector and less than that of the single user detection algorithms. For the Cholesky based joint detector, the approximate Cholesky decomposition is applied. Moreover, the novel method can also be applied to any generic multiple-input-multiple-output (MIMO) system.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.4
• /
• pp.395-401
• /
• 1999

In this paper, a temperature controller for a semiconductor test handler is proposed. First, a handware system for identification and control is established using RTD sensors, an A/D converter, solid state relays, a heater, and a computer system. Second, using ARMAX model and least square method, a chamber model for the design of a controller is identified through experiments. The identified model is verified to describe the real plant very well in the sense that it shows very similar input-output responses to those of the real system. With the identified model an LQG controller is designed. Frequency response of the designed controller shows that it has 15 dB of gainmargin and (-50˚, +50˚) of phase margin. Experiment with a real test handler demonstrates a good performance in the sense that its overshoot and steady state error are smaller and response time is faster, compared with those of a conventional PID controller.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.49 no.1
• /
• pp.54-61
• /
• 2000

Conventionally, ZVS FB DC/DC converter was controlled by monolithic IC UC3879, which includes the functions of oscillator, error amplifier and phase-shift circuit. Also, microprocessor and DSP have been widely used for the remote control and for the immediate waveform control in ZVS FB DC/DC converter. However the conventional microprocessor controller is complex and difficult to control because the controller consists of analog and digital parts. In the case of the control of FB DC/DC converter, the output is required of driving a direct signal to the switch drive circuits by the digital controller. So, this paper presents the method and realization of designing the digital-to-phase shift PWM circuit controlled by DSP (TMX320C32) in a 2,500A, 40㎾ ZVS FB DC/DC converter.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.2
• /
• pp.167-176
• /
• 2008

Vulnerability assessment of power systems is important so as to determine their ability to continue to provide service in case of any unforeseen catastrophic contingency such as power system component failures, communication system failures, human operator error, and natural calamity. An approach towards the development of on-line power system vulnerability assessment is by means of using an artificial neural network(ANN), which is being used successfully in many areas of power systems because of its ability to handle the fusion of multiple sources of data and information. An important consideration when applying ANN in power system vulnerability assessment is the proper selection and dimension reduction of training features. This paper aims to investigate the effect of using various feature extraction methods on the performance of ANN as well as to evaluate and compare the efficiency of the proposed feature extraction method named as neural network weight extraction. For assessing vulnerability of power systems, a vulnerability index based on power system loss is used and considered as the ANN output. To illustrate the effectiveness of ANN considering various feature extraction methods for vulnerability assessment on a large sized power system, it is verified on the IEEE 300-bus test system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.4
• /
• pp.519-529
• /
• 1993

A spectral and power efficient modulation technique, named Compact Superposed Quadrature Amplitude Modulation (Compact-SQAM), is introduced. The performance of Compact-SQAM system, in a Linearly and nonlinearly amplified single and multicarrier environment, in the presence of additive white Gaussian noise(AWGN), intersymbol interference(ISI), timing jitter and adjacent channel interference (ACI), is experimentally analyzed via computer simulation. Various channel conditions, such as channel spacing, between the main and adjacent channels and fade depth on the desired main channel, are examined. Our result shows that Compact-SQAM, and better P(e) performance that other modems using simple Butteroworth type postdetection receive filters. Especially, Compact-SQAM modem achieves higher efficiency of frequency utilization and better P(e) performance than other modems in the severly bandlimited nonlinear multicarrier channels.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.25 no.1
• /
• pp.1-5
• /
• 2020

Solar power generation systems require maximum power point tracking (MPPT) control to operate PV panels at their maximum power point (MPP). Most conventional MPPT algorithms are based on the slope-tracking concept. A typical slope-tracking method is the perturb and observe (P&O) algorithm. The P&O algorithm measures the current and voltage of a PV panel to find the operating point of the voltage at which the calculated power is maximized. However, the measurement error of the sensor causes irregularity in the calculation of the generated power and voltage control. This irregularity leads to the problem of not finding the correct MPP operating point. In this work, the power output of a PV panel based on the P&O algorithm is simulated by considering the insolation profiles from typical clear and cloudy weather conditions and the errors of current and voltage sensors. Simulation analysis suggests the optimal control period and perturbation voltage of MPPT to maximize its target efficiency under real weather conditions with sensor tolerance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12C
• /
• pp.181-189
• /
• 2001

In this thesis, a policing algorithm is proposed, which is one of the traffic management function in ATM networks. The proposed algorithm minimizes CLR(Cell Loss patio) of high priority cells and solves burstiness problem of the traffic caused by multiplexing and demultiplexing process. The proposed algorithm has been implemented with VHDL and is divided into three parts, which are an input module, an UPC module, and an output module. In implementation of the UPC module\`s memory access, memory address is assigned according to VCI\`s LSB(Lowest Significant Byte) of ATM header for convenience. And the error of VSA operation from counter\`s wrap-around can be recovered by the proposed method. ANAM library 0.25 $\mu\textrm{m}$ and design compiler of Synopsys are used for synthesis of the algorithm and Synopsys VSS tool is used for VHDL simulation of it

• Journal of Electrical Engineering and Technology
• /
• v.8 no.4
• /
• pp.752-759
• /
• 2013

This paper proposes a method for fault diagnosis and fault-tolerant control of DC-link voltage sensor for two-stage three-phase grid-connected PV inverters. Generally, the front-end DC-DC boost converter tracks the maximum power point (MPP) of PV array and the rear-end DC-AC inverter is used to generate a sinusoidal output current and keep the DC-link voltage constant. In this system, a sensor is essential for power conversion. A sensor fault is detected when there is an error between the sensed and estimated values, which are obtained from a DC-link voltage sensorless algorithm. Fault-tolerant control is achieved by using the estimated values. A deadbeat current controller is used to meet the dynamic characteristic of the proposed algorithm. The proposed algorithm is validated by simulation and experiment results.