• Computational Structural Engineering
• /
• v.9 no.2
• /
• pp.93-101
• /
• 1996

An artificial neural network is a computational model that mimics the biological system of the brain and it consists of a number of interconnected processing units where it can reasonably infer by them. Because the neural network is particularly useful for evaluating systems with a multitude of nonlinear variables, it can be used in experimental results predictions, in structural planning and in optimum design of structures. This paper describes the basic theory related to the neural networks and discusses the applicability of neural networks to predict the ultimate shear capacity of the precast concrete vertical joints by comparing the neural networks with a conventional method such as regression.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.5
• /
• pp.425-432
• /
• 2009

In this study, the ability of neural network in modeling and predicting of the unsteady aerodynamic force coefficients of 2D airfoil with the data obtained from Euler CFD code has been confirmed. Neural network models are constructed based on supervised training process using Levenberg-Marquardt algorithm, combining this into genetic algorithm, hybrid genetic algorithm and the efficiency of the two cases are analyzed and compared. It is shown that hybrid-genetic algorithm is more efficient for neural network of complex system and the predicted properties of the unsteady aerodynamic force coefficients of 2D airfoil by the neural network models are confirmed to be similar to that of the numerical results and verified as suitable representing reduced models.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.1
• /
• pp.24-31
• /
• 2020

In this paper, the deep convolutional neural network for sound event detection is studied. Especially, the end-to-end neural network, which generates the detection results from the input audio waveform, is studied for weakly supervised problem that includes weakly-labeled and unlabeled dataset. The proposed system is based on the network structure that consists of deeply-stacked 1-dimensional convolutional neural networks, and enhanced by the skip connection and gating mechanism. Additionally, the proposed system is enhanced by the sound event detection and post processings, and the training step using the mean-teacher model is added to deal with the weakly supervised data. The proposed system was evaluated by the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 Task 4 dataset, and the result shows that the proposed system has F₁-scores of 54 % (segment-based) and 32 % (event-based).

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.6
• /
• pp.1-10
• /
• 2007

This paper presents a direct nonlinear multivariable self-tuning PID controller using neural network which adapts to the changing parameters of the nonlinear multivariable system with noises and time delays. The nonlinear multivariable system is divided linear part and nonlinear part. The linear controller are used the self-tuning PID controller that can combine the simple structure of a PID controllers with the characteristics of a self-tuning controller, which can adapt to changes in the environment. The linear controller parameters are obtained by the recursive least square. And the nonlinear controller parameters are achieved the through the Back-propagation neural network. In order to demonstrate the effectiveness of the proposed algorithm, the computer simulation results are presented to adapt the nonlinear multivariable system with noises and time delays and with changed system parameter after a constant time. The proposed PID type nonlinear multivariable self-tuning method using neural network is effective compared with the conventional direct multivariable adaptive controller using neural network.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.1
• /
• pp.68-76
• /
• 2018

Target prioritization is necessary for a multifunction radar(MFR) to track an important target and manage the resources of the radar platform efficiently. In this paper, we consider an artificial neural network(ANN) model that calculates the priority of the target. Furthermore, we propose a neural network learning algorithm based on the steepest descent method, which is more suitable for target prioritization by combining the conventional gradient descent method. Several simulation results show that the proposed scheme is much more superior to the traditional neural network model from analyzing the training data accuracy and the output priority relevance of the test scenarios.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.35-48
• /
• 1999

Many organizational contexts should be considered in designing EDI controls to make control systems effective and efficient. This paper gives a description of the neural network model for suggesting the extent of effective EDI controls for a company that has specific organizational environment. Feedforward backpropagation neural network models are designed to predict the state of 12 modes of EDI controls from the sate of environment. The predictive power of the system is compared with that of multivariate regression analysis to evaluate the effectiveness of using neural network model in predicting the level of EDI controls. The results show that the neural network model outperforms regression analysis in predictive accuracy. The controls that have high estimated value in the model are likely to be critical controls and EDI auditor or management can enhance investment of IS resources to enhance these controls.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.39 no.2
• /
• pp.199-206
• /
• 2015

In this study, a new diagnosis method which can predict the working states of a pipe or its element in realtime is proposed by using an artificial neural network. The displacement data of an inspection element of a piping system are obtained by the use of PIV (particle image velocimetry), and are used for teaching a neural network. The measurement system consists of a camera, a light source and a host computer in which the artificial neural network is installed. In order to validate the constructed monitoring system, performance test was attempted for two kinds of mobile phone of which vibration modes are known. Three values of acceleration (minimum, maximum, mean) were tested for teaching the neural network. It was verified that mean values were appropriate to be used for monitoring data. The constructed diagnosis system could monitor the operation condition of a gas pipe.

• Journal of the Korean Society of Industry Convergence
• /
• v.19 no.1
• /
• pp.1-9
• /
• 2016

In this paper, we propose a new learning control scheme for various walk motion control of biped robot with same learning-base by neural network. We show that learning control algorithm based on the neural network is significantly more attractive intelligent controller design than previous traditional forms of control systems. A multi layer back propagation neural network identification is simulated to obtain a dynamic model of biped robot. Once the neural network has learned, the other neural network control is designed for various trajectory tracking control with same learning-base. The biped robots have been received increased attention due to several properties such as its human like mobility and the high-order dynamic equation. These properties enable the biped robots to perform the dangerous works instead of human beings. Thus, the stable walking control of the biped robots is a fundamentally hot issue and has been studied by many researchers. However, legged locomotion, it is difficult to control the biped robots. Besides, unlike the robot manipulator, the biped robot has an uncontrollable degree of freedom playing a dominant role for the stability of their locomotion in the biped robot dynamics. From the simulation and experiments the reliability of iterative learning control was illustrated.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.214-221
• /
• 1998

A new control approach using neural network for the robust position control of a BRUSHLESS direct drive(BLDD) motor is presented. The linear quadratic controller plus feedforward neural network is employed to obtain the robust BLDD motor system approximately linearized using field-orientation method for an AC servo. The neural network is trained in on-line phases and this neural network is composed by a feedforward recall and error back-propagation training. Since the total number of nodes are only eight, this system will be easily realized by the general microprocessor. During the normal operation, the input-output response is sampled and the weighting value is trained by error back-propagation at each sample period to accommodate the possible variations in the parameters or load torque. And the state space analysis is performed to obtain the state feedback gains systematically. In addition, the robustness is also obtained without affecting overall system response.

• Journal of Ocean Engineering and Technology
• /
• v.26 no.1
• /
• pp.60-63
• /
• 2012

The accident risks in the marine environment are increasing because of the tendency to build faster and larger ships. To secure ship safety, risk-based ship design (RBSD) was recently suggested based on a formal safety assessment (FSA). In the process of RBSD, a ship designer decides which risk reduction option is most cost-effective in the design stage using a cost-benefit analysis (CBA). There are three dimensions of risk in this CBA: fatality, environment, and asset. In this paper, we present an approach to estimate the environmental costs based on the size of an oil tanker involved in an accident using a neural network. An appropriate neural network model is suggested for the estimation,and the neural network is trained using IOPCF data. Finally,the learned neural network is compared with the cost regression equation by IMO MEPC 62/WP.13 (2011).