• Structural Engineering and Mechanics
• /
• v.16 no.5
• /
• pp.581-595
• /
• 2003

Since the conventional direct approaches are hard to be applied for damage diagnosis of complex large-scale structures, a two-step approach for diagnosing the joint damage of framed structures is presented in this paper by using artificial neural networks. The first step is to judge the damaged areas of a structure, which is divided into several sub-areas, using probabilistic neural networks with natural Frequencies Shift Ratio inputs. The next step is to diagnose the exact damage locations and extents by using the Radial Basis Function (RBF) neural network with the second Element End Strain Mode of the damaged sub-area input. The results of numerical simulation show that the proposed approach could diagnose the joint damage of framed structures induced by earthquake action effectively and has reliable anti-jamming abilities.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.351-356
• /
• 2007

Factory location selection is very important to the success of operation of the whole supply chain, but few effective solutions exist to deliver a good result, motivated by this, this paper tries to introduce a new factory location selection methodology by employing the artificial neural networks technology. First, we reviewed previous research related to factory location selection problems, and then developed a (neural network-based factory selection model) NNFSM which adopted back-propagation neural network theory, next, we developed computer program using C++ to demonstrate our proposed model. then we did case study by choosing a Korean steelmaking company P to show how our proposed model works,. Finnaly, we concluded by highlighting the key contributions of this paper and pointing out the limitations and future research directions of this paper. Compared to other traditional factory location selection methods, our proposed model is time-saving; more efficient.and can produce a much better result.

• Smart Structures and Systems
• /
• v.5 no.5
• /
• pp.507-515
• /
• 2009

The present work is an alternative methodology in order to balance a nonlinear highly flexible rotor by using neural networks. This procedure was developed aiming at improving the performance of classical balancing methods, which are developed in the context of linearity between acting forces and resulting displacements and are not well adapted to these situations. In this paper a fully experimental procedure using neural networks is implemented for dealing with the adaptive balancing of nonlinear rotors. The nonlinearity results from the large displacements measured due to the high flexibility of the foundation. A neural network based meta-model was developed to represent the system. The initialization of the learning procedure of the network is performed by using the influence coefficient method and the adaptive balancing strategy is prone to converge rapidly to a satisfactory solution. The methodology is tested successfully experimentally.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.742-745
• /
• 1994

In this paper we show the performance of neural Chandrasekhar filtering which is a special case for the new method of neural filtering using the artificial neural network systems developed recently for the filtering problems of linear and nonlinear, stationary and nonstationary stochastic signals. The neurofilter developed has either the finite impulse response(FIR) structure or the infinite impulse response(IIR) structure. The neurofilter differs from the conventional linear digital FIR and IIR filters because the artificial neural network system used in the neurofilter has nonlinear structure due to the sigmoid function. Numerical studies for the estimation of a second order Butterworth process are performed by changing the structures of the neurofilter in order to evaluate the performance indices under the changes of the output noises or disturbances. In the numerical studies both Chandrasekhar filtering estimates and true signals are used as the training signals for the neurofilter. The results obtained from the studies verified the capabilities which are essentially necessary for on-line filtering of various stochastic signals.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.11
• /
• pp.95-103
• /
• 1997

A robust center estimation tecnique of n-fold engineering parts is presented, which use self-organizing neural networks with generating and merging learning for training neural units. To estimate the center of the n-fold engineering parts using neural networks, the segmented boundaries of the interested part are approximated to strainght lines, and the temporal estimated centers by thecosine theorem which formed between the approximaged straight line and the reference point, , are indexed as (.sigma.-.theta.) parameteric vecstors. Then the entries of parametric vectors are fed into self-organizing nerual network. Finally, the center of the n-fold part is extracted by mean of generating and merging learning of the neurons. To accelerate the learning process, neural network uses an adaptive learning rate function to the merging process and a self-adjusting activation to generating process. Simulation results show that the centers of n-fold engineering parts are effectively estimated by proposed technique, though not knowing the error distribution of estimated centers and having less information of boundaries.

• Earthquakes and Structures
• /
• v.17 no.6
• /
• pp.591-598
• /
• 2019

The most recent shaking experiences have demonstrated that the predictions of the seismic models are not always in agreement with the registered responses, especially in the face of extreme earthquakes. Records collected from 1960 to 2011 at a rock-like site are used to develop a neural network that permits to estimate peak ground accelerations via the magnitude, the focal depth, the site-source distance and a seismogenic zone. The neural model is applied to the 8th and 19th September 2017 events that hit Mexican territory and the obtained results show that the network is flexible enough to work appropriately to various conditions of intensity and sites-sources with remarkably predictive capacity. The neural-attenuation curves are compared with those obtained from Ground Motion Prediction Equations and their performance is assessed for events, in addition to the devastating Mexican events, from Japan, Taiwan, Chile and USA.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.3
• /
• pp.137-144
• /
• 1990

We describe how single layer perceptrons and new nonsymmetry feedback type neural networks can be implemented by VLSI CMOS technology. The network described provides a flexible tool for evaluation of boolean expressions and arithmetic equations. About 50 CMOS VLSI chips with an architecture based on two neural networks have been designed and me being fabricated by 2-micrometer double metal design rules. These chips have been developed to study the potential of neural network models for the use in character recognition and for a neural compute.

• Journal of the Korea Society for Simulation
• /
• v.14 no.4
• /
• pp.55-68
• /
• 2005

The advancement in semiconductor technology is leading toward smaller critical dimension designs and larger wafer manufactures. Due to such phenomena, semiconductor industry is in need of an accurate control of the process. Photolithography is one of the key processes where the pattern of each layer is formed. In this process, precise superposition of the current layer to the previous layer is critical. Therefore overlay parameters of the semiconductor photolithography process is targeted for this research. The complex relationship among the input parameters and the output metrologies is difficult to understand and harder yet to model. Because of the superiority in modeling multi-nonlinear relationships, neural networks is used for the simulator modeling. For training the neural networks, conjugate gradient method is employed. An experiment is performed to evaluate the performance among the proposed neural network simulator, stepwise regression model, and the currently practiced prediction model from the test site.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.61-65
• /
• 1997

In control of complex system, like robot manipulators, BP neural network have several drawbacks. To overcome this problems, the modified BP neural networks have proposed To find neural network of proper structure for robot manipulator, in this paper, actual experiments using ADSP-21020 for SCARA robot were implemented and have shown the possibility of real-time control and industrial application, without neural chip.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.310-314
• /
• 2000

This paper proposes a new parallel architecture for extracting the object from binarized images using recurrent linear threshold neural networks. Binary functions are initially obtained from the existing iterative thinning algorithms, and the linear threshold neural threshold neural networks are then synthesized using the MSP term grouping algorithm. Experimental results show that the proposed architectures can be implemented easier than with other existing methods.