• Proceedings of the Korean Geotechical Society Conference
• /
• 2000.11a
• /
• pp.673-680
• /
• 2000

Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a consolidation behavior of clay from soil parameter, site investigation data and the first settlement curve is proposed. The training and testing of the network were based on a database of 63 settlement curve from two different sites. Five different network models were used to study the ability of the neural network to predict the desired output to increasing degree of accuracy. The study showed that the neural network model predicted a consolidation behavior of clay reasonably well.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.62-68
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. Authors have already proposed a diagnostic system based on FCM to utilized to identify the true origin of fault by on-line pattern diagnosis. In FCM based fault diagnosis, Temporal Associative Memories (TAM) recall of FCM is utilized to identify the true origin of fault by on-line pattern match where predicted pattern sequences obtained from TAM recall of fault FCM models are compared with actually observed ones. In engineering processes, the propagation delays are induced by the dynamics of processes and may vary with variables involved. However, disregarding such propagation delays in FCM-based fault diagnosis may lead to erroneous diagnostic results. To solve the problem, a concept of FTCM(Fuzzy Time Cognitive Map) is introduced into FCM-based fault diagnosis in this work. Expecially, translation method of FTCM makes it possible to diagnose the fault for some discrete time. Simulation studies through two-tank system is carried out to verify the effectiveness of the proposed diagnostic scheme.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.154-160
• /
• 1998

This study describes a theoretical and experimental investigation of gas wave propagation in the pipe system. Most calculations of compressible flows in the pipe have been based on the method of characteristics. This technique has propensity to truncate waves and is difficult to apply to non-perfect gas. A method that describes the application of a two-step Lax-Wendroff acheme to solution of the unsteady one-dimentional flow in the pipe was developed. Theoretical calculations using both the method of characteristics and the two-step Lax-Wendroff method are presented including a realistic model for heat transfer and friction processes. In the present work, account is taken of the nonlinear behavior. For sections of parallel pipe, an one dimensional unsteady homentropic analysis is employed, and a numerical solution is obtained with the aid of a digital computer, using the method of characteristics and two-step Lax-Wendroff method. This analysis is then combined with boundary models, based on a quasi-steady flow approach, to give a complete treatment of the flow behavior in the pipe system.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11b
• /
• pp.110-113
• /
• 2005

Theoretical models to study the vibro-acoustic performance of a sandwich panel are proposed. The wave propagation characteristics are analyzed, and dispersion relation is derived. The vibration Is analyzed using the Mindlin plate theory. The vibration of the compliantly supported Mindlin plate is investigated using the Rayleigh-Ritz method. The Timoshenko beam functions are used as trial functions. The model is applied to numerically investigate the influence of the plate mechanical properties. The vibro-acoustic properties are mostly determined by bending deformation at low frequencies. At higher frequencies, the shear deformation has a strong influence. The proposed numerical model is used to estimate the optimal panel properties that result in minimum sound radiation. With increasing dynamic stiffnesses the vibration response decreases but the radiating wavenumber components increase.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.113-117
• /
• 1995

Grinding operations is accomplished by rotating a gfinding wheel with lots of random abrasive at high speed, and its object is generally obtained the fanal workpiece surface of high quality as well as the maximization of workpiece removal rate. But, especiallysince grinding operations is related with a large amount of functional parameter, it is actually difficult to therapy that the grinding trouble occurs during the grinding process. Therefore, we trytodesign grinding trouble-shooting system utilizing the back-propagation model of neural network. The conceptual method is produced byidentifying the four parameters derived from the grinding power, and we are design te to the grinding trouble-shooting system on the basis of their data. In this paper, cognition and therapy method tothe grinding trouble which utilizes neural network based four identified models are suggested, and implementation results of computer simulation with respect to the grinding burn and chatter vibration is presented.

• Journal of Bio-Environment Control
• /
• v.1 no.2
• /
• pp.162-168
• /
• 1992

As the automation of nutrient solution management proceeds in the field of hydroponics, effective supporting systems to manage the nutrient solution by computer become needed. This study was attempt to predict the EC of nutrient solution using the neural networks. The multilayer perceptron consisting of 3 layers with the back propagation learning algorithm was selected for EC prediction, of which nine variables in the input layer were the concentrations of each ion and one variable in the output layer the EC of nutrient solution. The meq unit in ion concentration was selected fir input variable in the input layer. After the 10,000 learning sweeps with 108 sample data, the comparison of predicted and measured ECs for 72 test data showed good agreements with the correlation coefficient of 0.998. In addition, the predicted ECs by neural network showed relatively equal or closer to the measured ones than those by current complicated models.

• Transactions of the Society of Information Storage Systems
• /
• v.6 no.1
• /
• pp.18-24
• /
• 2010

The performance of the speech recognition mainly depends on uncertain factors such as speaker's conditions and environmental effects. The present study deals with the speech recognition of a number of multi-syllable isolated Korean words using soft computing techniques such as back-propagation neural network, fuzzy inference system, and fuzzy neural network. Feature patterns for the speech recognition are analyzed with 12th order thirty frames that are normalized by the linear predictive coding and Cepstrums. Using four models of speech recognizer, actual experiments for both single-speakers and multiple-speakers are conducted. Through this study, the recognizers of combined fuzzy logic and back-propagation neural network and fuzzy neural network show the better performance in identifying the speech recognition.

• ETRI Journal
• /
• v.38 no.6
• /
• pp.1031-1041
• /
• 2016

This paper presents millimeter-wave (mmWave) propagation characteristics and channel model parameters including path loss, delay, and angular properties based on 28 GHz and 38 GHz field measurement data. We conducted measurement campaigns in both outdoor and indoor at the best potential hotspots. In particular, the model parameters are compared to sub-6 GHz parameters, and system design issues are considered for mmWave 5G Giga communications. For path loss modeling, we derived parameters for both the close-in free space model and the alpha-beta-gamma model. For multipath models, we extracted delay and angular dispersion characteristics including clustering results.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.248-255
• /
• 2009

We proposed a power line channel model. We adopted advantages of other power line channel models to calculate channel responses correctly and simply. Infinite geometric series reduced the calculation complexity of the multipath signal propagation. Description Matrices were also adopted to handle the network topology easily. It represents complex power line network precisely and simply. Newly proposed model considered the effect of the adjacent nodes to channel responses, which have been not considered so far. Several simulations were executed to verify the effect of the adjacent nodes. As a result we found out that it affected channel responses but its effect was limited within certain degree.

• Journal of the Society of Naval Architects of Korea
• /
• v.44 no.5
• /
• pp.488-495
• /
• 2007

In this paper, SBN (Structure-Borne Noise) reduction of resiliently mounted machinery and effect of the foundation impedance on mount performance is studied. SBN reduction through the mount is analyzed by using two theoretical models; mass-spring model and wave model, in which longitudinal wave propagation is included. It is found that floor impedance greatly affects SBN reduction through lower mount, while it is almost negligible to SBN reduction through upper mount. Comparisons between measurement and predictions shows that the mass-spring model is valid only in low frequency range below few hundred Hz, while for high frequency ranges longitudinal wave propagation in the mount must be considered.