• Journal of The Korean Society of Agricultural Engineers
• /
• v.53 no.1
• /
• pp.1-7
• /
• 2011

The nature of a network implies movement among vertices, and can be regarded as flows. Based on the flow concept which network follows the hydraulic fluid principle, we develop a spatial network model using Bernoulli equation. Then we explore the organization of spatial network and growth by the velocity of network flows. Results show that flow velocity determines network connections or influence of a vertex up to a point, and that the overall network structure is the result of pull force (pressure) and flow velocity. We demonstrate how one vertex can monopolize connections within a network.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.18-25
• /
• 2023

In these days, high dimensional data prediction technology based on neural network shows compelling results in many different kind of field including engineering. Especially, a lot of variants of convolution neural network are widely utilized to develop pixel level prediction model for high dimensional data such as picture, or physical field value from the sensors. In this study, velocity vector field of ideal flow on ship surface is estimated on pixel level by Unet. First, potential flow analysis was conducted for the set of hull form data which are generated by hull form transformation method. Thereafter, four different neural network with a U-shape structure were conFig.d to train velocity vectors at the node position of pre-processed hull form data. As a result, for the test hull forms, it was confirmed that the network with short skip-connection gives the most accurate prediction results of streamlines and velocity magnitude. And the results also have a good agreement with potential flow analysis results. However, in some cases which don't have nothing in common with training data in terms of speed or shape, the network has relatively high error at the region of large curvature.

• Computers and Concrete
• /
• v.12 no.6
• /
• pp.785-802
• /
• 2013

Ready-mixed soil material, known as a kind of controlled low-strength material, is a new way of soil cement combination. It can be used as backfill materials. In this paper, artificial neural network and nonlinear regression approach were applied to predict the compressive strength of ready-mixed soil material containing Portland cement, slag, sand, and soil in mixture. The data used for analyzing were obtained from our testing program. In the experiment, we carried out a mix design with three proportions of sand to soil (e.g., 6:4, 5:5, and 4:6). In addition, blast furnace slag partially replaced cement to improve workability, whereas the water-to-binder ratio was fixed. Testing was conducted on samples to estimate its engineering properties as per ASTM such as flowability, strength, and pulse velocity. Based on testing data, the empirical pulse velocity-strength correlation was established by regression method. Next, three topologies of neural network were developed to predict the strength, namely ANN-I, ANN-II, and ANN-III. The first two models are back-propagation feed-forward networks, and the other one is radial basis neural network. The results show that the compressive strength of ready-mixed soil material can be well-predicted from neural networks. Among all currently proposed neural network models, the ANN-I gives the best prediction because it is closest to the actual strength. Moreover, considering combination of pulse velocity and other factors, viz. curing time, and material contents in mixture, the proposed neural networks offer better evaluation than interpolated from pulse velocity only.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2473-2475
• /
• 2001

In trajectory tracking methods, the error values of current position and velocity are compensated to follow the given reference path and velocity. The path tracking for a wheeled mobile robot is treated in this paper. It is very difficult to implement stable trajectory tracking algorithms because mobile robots have kinematically non-holonomic constraints. For solving this problem, a velocity controller is presented in this paper. This velocity controller is designed by a PID controller which could be easily employed. In this case, velocity errors caused by system uncertainties or internal and external disturbances could exist. A neural network is used for compensating the velocity errors. Input variables of this neural network compensator are defined by differences between the velocities of the posture controller and the real velocities of the mobile robot. Simulation results show the effectiveness of the proposed controller.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.2
• /
• pp.111-116
• /
• 2001

A neural network compensator for stick-slip friction phenomena in meashartonics servo systems is practically proposed to supplement the traditionally available position and velocity control loops for precise motion control. The neural network compensa-tor plays the role of canceling the effect of nonlinear slipping friction force. It works robustly and effectively in a real control system. This enables the mechatronics servo systems to provide more precise control in the digital computer. It was confirmed that the con-trol accuracy is improved near zero velocity and points of changing the moving direction through numerical simulation. However, asymptotic property on the steady state error of the normal operation points is guaranteed by the integral term of traditional velocity loop controller.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.12
• /
• pp.1306-1316
• /
• 1990

A controller using a multilayer neural network is proposed to the dynamic control of a PUMA 560 robot arm. This controller is developed based on an error back-propagation (BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it is used as a commanded feedforward torque generator. A Proportional Derivative (PD) feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the manipulator as well as the PD feedback error torque. No a priori knowledge on system dynamics is needed and this information is rather implicitly stored in the interconnection weights of the neural network. In another experiment, the neural network was trained with the current, past and future positions only without any use of velocity sensors. Form this thim window of position values, BP network implicitly filters out the velocity and acceleration components for each joint. Computer simulation demonstrates such powerful characteristics of the neurocontroller as adaptation to changing environments, robustness to sensor noise, and continuous performance improvement with self-learning.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.338-343
• /
• 1999

In this paper, the fuzzy neural network for the obstacle avoidance, which consists of the straight-line navigation and the barrier elusion navigation, is proposed and examined. For the straight-line navigation, the fuzzy neural network gets two inputs, angle and distance between the line and the mobile robot, and produces one output, steering velocity of the mobile robot. For the barrier elusion navigation, four ultrasonic sensors measure the distance between the barrier and the mobile robot and provide the distance information to the network. Then the network outputs the steering velocity to navigate along the obstacle boundary. Training of the proposed fuzzy neural network is executed in a given environment in real-time. The weights adjusting uses the back-propagation of the gradient of error to be minimized. Computer simulations are carried out to examine the efficiency of the real time learning and the guiding ability of the proposed fuzzy neural network. It has been shown that the mobile robot that employs the proposed fuzzy neural network navigates more safely with and less trembling locus compared with the previous reported efforts.

• Atmosphere
• /
• v.20 no.3
• /
• pp.343-353
• /
• 2010

A regional wind network with complex surface conditions must be designed with sufficient space and time resolution to resolve the local circulations. In this study, the spatial variations of the wind field observed in the Seoul and Jeju regional networks were evaluated in terms of annual, seasons, and months to assess the spatial homogeneity of wind fields within the regional networks. The coherency of the wind field as a function of separation distance between stations indicated that significant coherency was sometimes not captured by the network, as inferred by low correlations between adjacent stations. A meso-velocity scale was defined in terms of the spatial variability of the wind within the network. This problem is predictably most significant with weak winds, dull prevailing wind, clear skies and significant topography. The relatively small correlations between stations imply that the wind at a given point cannot be estimated by interpolating winds from the nearest stations. For the Seoul and Jeju regional network, the meso-velocity scale has typically a same order of magnitude as the speed of the network averaged wind, revealing the large spatial variability of the Jeju network station imply topography and weather. Significant scatter in the relationship between spatial variability of the wind field and the wind speed is thought to be related to thermally-generated flows. The magnitude of the mesovelocity scale was significantly different along separation distance between stations, wind speed, intensity of prevailing wind, clear and cloudy conditions, topography. Resultant wind vectors indicate much different flow patterns along condition of contributing factors. As a result, the careful considerations on contributing factors such as prevailing wind in season, weather, and complex surface conditions with topography and land/sea contrast are required to assess the spatial variations of wind field on a regional network. The results in the spatial variation from the mesovelocity scale are useful to represent the characteristics of regional wind speed including lower surface conditions over the grid scale of large scale atmospheric model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.179-179
• /
• 2000

An adaptive neural network compensator for stick-slip friction phenomena in servo systems is proposed to supplement the traditionally available position and velocity control loops for precise motion control. The neural network compensator plays a role of canceling the effect of nonlinear slipping friction force. This enables the mechatronic systems more precise control and realistic design in the digital computer. It was confirmed that the control accuracy is more improved near zero velocity and the points of changing the moving direction through numerical simulation

• ETRI Journal
• /
• v.42 no.3
• /
• pp.366-375
• /
• 2020

The network traffic prediction of a smart substation is key in strengthening its system security protection. To improve the performance of its traffic prediction, in this paper, we propose an improved gravitational search algorithm (IGSA), then introduce the IGSA into a wavelet neural network (WNN), iteratively optimize the initial connection weighting, scalability factor, and shift factor, and establish a smart substation network traffic prediction model based on the IGSA-WNN. A comparative analysis of the experimental results shows that the performance of the IGSA-WNN-based prediction model further improves the convergence velocity and prediction accuracy, and that the proposed model solves the deficiency issues of the original WNN, such as slow convergence velocity and ease of falling into a locally optimal solution; thus, it is a better smart substation network traffic prediction model.