• Structural Engineering and Mechanics
• /
• v.71 no.2
• /
• pp.175-183
• /
• 2019

This paper deals with damage detection in a girder bridge using transmissibility functions as input data to Artificial Neural Networks (ANNs). The original contribution in this work is that these two novel methods are combined to detect damage in a bridge. The damage was simulated in a real bridge in Vietnam, i.e. Ca-Non Bridge. Finite Element Method (FEM) of this bridge was used to show the reliability of the proposed technique. The vibration responses at some points of the bridge under a moving truck are simulated and used to calculate the transmissibility functions. These functions are then used as input data to train the ANNs, in which the target is the location and the severity of the damage in the bridge. After training successfully, the network can be used to assess the damage. Although simulated responses data are used in this paper, the practical application of the technique to real bridge data is potentially high.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.8
• /
• pp.49-58
• /
• 2016

In designing heterogeneous architecture based application-specific network-on-chips (NoCs), the opportunities of performance improvement would be expanded when applying asynchronous on-chip communication protocol. This is because the wire latency can be configured independently considering the wirelength of each link. In this paper, we develop the delay model of link-wire-length in asynchronous NoC and propose simulated annealing (SA) based floorplan-aware topology generation algorithm to optimize link-wirelengths. Incorporating the generated topology and the associated latency values across all links, we evaluate the performance using the floorplan-annotated sdf (standard delay format) file and RTL-synthesized gate-level netlist. Compared to TopGen, one of general topology generation algorithms, the experimental results show the reduction in latency by 13.7% and in execution time by 11.8% in average with regards to four applications.

• Economic and Environmental Geology
• /
• v.28 no.5
• /
• pp.503-512
• /
• 1995

Groundwater flow in fracture networks is simulated using a discrete fracture (DF) model which assume that groundwater flows only through the fracture network. This assumption is available if the permeability of rock matrix is very low. It is almost impossible to describe fracture networks perfectly, so a stochastic approach is used. The stochastic approach assumes that the characteristic parameters in fracture network have special distribution patterns. The stochastic model generates fracture networks with some characteristic parameters. The finite element method is used to compute fracture flows. One-dimensional line element is the element type of the finite elements. The simulation results are shown by dominant flow paths in the fracture network. The dominant flow path can be found from the simulated groundwater flow field. The model developed in this study provides the tool to estimate the influences of characteristic parameters on groundwater flow in fracture networks. The influences of some characteristic parameters on the frcture flow are estimated by the Monte Carlo simulation based on 30 realizations.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.227-232
• /
• 2005

A network of Packet based switch Mode will be required to carry the traffics(CVR,VBR, UBR, ABR) generated by a wide range of services. Packet based Network services the quality-of-Service (QoS) management of traffic sources and bandwidth. Besides efficiency and throughput services are achieved in the multimedia traffic sent in the network. In this paper. the scheduler transmits the safe packet, drop the unsafe packet and evaluate unsafe packet as the requirement of the delay avoiding the network congestion for improving the QoS of the multimedia network In this paper. we Propose the scheduling algorithm which evaluates and drops the packet . The suggested model performance of the switch is estimated and simulated in terms of the delay by computer.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.3
• /
• pp.329-334
• /
• 2014

Recently, various electronic functions are developed for car drivers as the advent of electrical automobile. Especially, there are functions to examine for preventing drowsy or healthcare through monitoring brainwave(EEG) of drivers in real time. This function can be provided by transmitting driver's EEG, and the network function for transmission among cars or between car and road side infrastructure is a vital issue. Therefore, in this paper, to provide efficient routing protocol for transmitting EEG data at a cross road in an urban area, 5 different wireless communication network applied each routing protocol such as AODV, DSR, GRP, OLSR, and TORA is designed and simulated in the OPNet network simulator, then it is evaluated for the result.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.245-250
• /
• 2005

A network of Packet based switch Mode will be required to carry the traffics(CVR,VBR, UBR, ABR) generated by a wide range of services. Packet based Network services the Qualify-of-Service (QoS) management of traffic sources and bandwidth. Besides efficiency and throughput services are achieved in the multimedia traffic sent in the network. In this paper, the scheduler transmits the safe packet, drop the unsafe packet and evaluate unsafe Packet as the requirement of the delay avoiding the network congestion for improving the QoS of the multimedia network. In this paper, we Propose the scheduling algorithm which evaluates and drops the packet The suggested model Performance of the switch is estimated and simulated in terms of the delay by computer.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• pp.505-510
• /
• 2000

Vehicle performances such as fuel consumption and catalyst-out emissions are affected by a driving pattern, which is defined as a driving cycle with the grade in this study. We developed an algorithm to recognize a current driving pattern by using a neural network. And this algorithm can be used in adapting the driving control strategy to the recognized driving pattern. First, we classified the general driving patterns into 6 representative driving patterns, which are composed of 3 urban driving patterns, 2 suburban driving patterns and 1 expressway driving pattern. A total of 24 parameters such as average cycle velocity, positive acceleration kinetic energy, relative duration spent at stop, average acceleration and average grade are chosen to characterize the driving patterns. Second, we used a neural network (especially the Hamming network) to decide which representative driving pattern is closest to the current driving pattern by comparing the inner products between them. And before calculating inner product, each element of the current and representative driving patterns is transformed into 1 and -1 array as to 4 levels. In the end, we simulated the driving pattern recognition algorithm in a temporary pattern composed of 6 representative driving patterns and, verified the reliable recognition performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.7
• /
• pp.711-719
• /
• 2010

Heliostat, as a concentrator reflecting the incident solar energy to the receiver located at the tower, is the most important system in the tower-type solar thermal power plant, since it determines the efficiency and performance of solar thermal plower plant. Thus, a good sun tracking ability as well as its good optical property are required. In this paper, we propose a method to compensate the heliostat sun tracking error. We first model the sun tracking error, which could be measured using BCS (Beam Characterization System), by multilayered neural network. Then the extended Kalman filter was employed to train the neural network. Finally the model is used to compensate the sun tracking errors. Simulated result shows that the method proposed in this paper improve the heliostat sun tracking performance dramatically. It also shows that the training of neural network by the extended Kalman filter provides faster convergence property, more accurate estimation and higher measurement noise rejection ability compared with the other training methods like gradient descent method.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.51 no.9
• /
• pp.509-514
• /
• 2002

The aim of this research is to find out how the common earth network affects the level of the traction return current in the $2{\times}25 kV$ Power Supply System. The traction return current plays a significant role in the operation of the facilities near the rails. It is shown that the common earth network in the $2{\times}25 kV$ power supply system not only minimizes the level of the traction return current, but also increases the safety of the working crew on the railways. In order to determine the relationship between common earth network and the traction return current, we investigated the earth system of the Gyongbu High Speed Line that is constructed following the SNCF regulations. We carried out the field test in the Osong station. The results of the test show that the common earth network minimizes the effect of the traction return current. We also find that the simulated results are very similar to the test results. We concluded that the results of the test can be applied for the rest of the Gyongbu High Speed Line under construction.