• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.55-65
• /
• 2004

When a neural network is used to solve a given problem it is necessary to match the complexity of the network to that of the problem because the complexity of the network significantly affects its learning capability and generalization performance. Thus, it is desirable to have an algorithm that can find appropriate network structures in a self-organizing way. This paper proposes algorithms which automatically organize feed forward multi-layer neural networks with sigmoid hidden neurons for given problems. Using both constructive procedures and pruning procedures, the proposed algorithms try to find the near optimal network, which is compact and shows good generalization performance. The performances of the proposed algorithms are tested on four function regression problems. The results demonstrate that our algorithms successfully generate near-optimal networks in comparison with the previous method and the neural networks of fixed topology.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.195-200
• /
• 1998

Since the neural network was introduced, significant progress has been made on data handling and learning algorithms. Currently, the most popular learning algorithm in neural network training is feed forward error back-propagation (FFEBP) algorithm. Aside from the success of the FFEBP algorithm, polynomial neural networks (PNN) learning has been proposed as a new learning method. The PNN learning is a self-organizing process designed to determine an appropriate set of Ivakhnenko polynomials that allow the activation of many neurons to achieve a desired state of activation that mimics a given set of sampled patterns. These neurons are interconnected in such a way that the knowledge is stored in Ivakhnenko coefficients. In this paper, the PNN model has been developed using the plasma enhanced chemical vapor deposition (PECVD) experimental data. To characterize the PECVD process using PNN, SiO$_2$films deposited under varying conditions were analyzed using fractional factorial experimental design with three center points. Parameters varied in these experiments included substrate temperature, pressure, RF power, silane flow rate and nitrous oxide flow rate. Approximately five microns of SiO$_2$were deposited on (100) silicon wafers in a Plasma-Therm 700 series PECVD system at 13.56 MHz.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.6
• /
• pp.556-561
• /
• 2009

The UAV(Unmanned Aerial Vehicle) that is remotely operating in various and long flight environments must have a very reliable propulsion system. Precise fault diagnosis of the turbo shaft engine for the Smart UAV that has the vertical take-off, landing and forward flight behaviors can promote reliability and availability. This work proposes a new diagnostic method that can identify the faulted components from engine measuring parameter changes using Fuzzy Logic and quantify its faults from the identified fault pattern using Neural Network Algorithms. The proposed diagnostic method can detect not only single fault but also multiple faults.

• 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.

• Structural Engineering and Mechanics
• /
• v.52 no.1
• /
• pp.97-113
• /
• 2014

In the present work appropriate concrete material models have been proposed to predict drying shrinkage and specific creep of High-performance concrete (HPC) using Artificial Neural Network (ANN). The ANN models are trained, tested and validated using 106 different experimental measured set of data collected from different literatures. The developed models consist of 12 input parameters which include quantities of ingredients namely ordinary Portland cement, fly ash, silica fume, ground granulated blast-furnace slag, water, and other aggregate to cement ratio, volume to surface area ratio, compressive strength at age of loading, relative humidity, age of drying commencement and age of concrete. The Feed-forward backpropagation networks with Levenberg-Marquardt training function are chosen for proposed ANN models and same implemented on MATLAB platform. The results shows that the proposed ANN models are more rational as well as computationally more efficient to predict time-dependent properties of drying shrinkage and specific creep of HPC with high level accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.737-741
• /
• 1994

We show an application of a genetic algorithm to, control systems including neural networks. Genetic algorithms are getting more popular nowadays because of their simplicity and robustness. Genetic algorithms are global search techniques for optimization and many other problems. A feed-forward neural network which is widely used in control applications usually learns by error back propagation algorithm(EBP). But, when there exist certain constraints, EBP can not be applied. We apply a modified genetic algorithm to such a case. We show simulation examples of two cart-pole nonlinear systems: single pole and double pole.

• Structural Engineering and Mechanics
• /
• v.51 no.2
• /
• pp.299-313
• /
• 2014

In the first part of this paper, the influences of some of crack parameters on natural frequencies of a cracked cantilever Functionally Graded Beam (FGB) are studied. A cantilever beam is modeled using Finite Element Method (FEM) and its natural frequencies are obtained for different conditions of cracks. Then effect of variation of depth and location of cracks on natural frequencies of FGB with single and multiple cracks are investigated. In the second part, two Multi-Layer Feed Forward (MLFF) Artificial Neural Networks (ANNs) are designed for prediction of FGB's Cracks' location and depth. Particle Swarm Optimization (PSO) and Back-Error Propagation (BEP) algorithms are applied for training ANNs. The accuracy of two training methods' results are investigated.

• Structural Engineering and Mechanics
• /
• v.29 no.1
• /
• pp.77-89
• /
• 2008

Presence of high degree of orthotropy enhances shear lag phenomenon in laminated composite box-beams and it persists till failure. In this paper three key parameters governing shear lag behavior of laminated composite box beams are identified and defined by simple expressions. Uniqueness of the identified key parameters is proved with the help of finite element method (FEM) based studies. In addition to this, for the sake of generalization of prediction of shear lag effect in symmetrical laminated composite box beams a feed forward back propagation neural network (BPNN) model is developed. The network is trained and tested using the data base generated by extensive FEM studies carried out for various b/D, b/tF, tF/tW and laminate configurations. An optimum network architecture has been established which can effectively learn the pattern. Computational efficiency of the developed ANN makes it suitable for use in optimum design of laminated composite box-beams.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.158-165
• /
• 1999

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure, a method is presented in this paper which uses hybrid neuro-genetic technique. Feed-forward multilayer neural networks trained by back-propagation are used to learn the input)the location and dept of a crack)-output(the structural eigenfrequencies) relation of the structural system. With this neural network and genetic algorithm, it is possible to formulate the inverse problem. Neural network training algorithm is the back propagation algorithm with the momentum method to attain stable convergence in the training process and with the adaptive learning rate method to speed up convergence. Finally, genetic algorithm is used to fine the minimum square error.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.157-157
• /
• 2018

A reliable and accurate downscaling model which can provide climate change information, obtained from global climate models (GCMs), at finer resolution has been always of great interest to researchers. In order to achieve this model, linear methods widely have been studied in the past decades. However, nonlinear methods also can be potentially beneficial to solve downscaling problem. Therefore, this study explored the applicability of some nonlinear machine learning techniques such as neural network (NN), extreme learning machine (ELM), and ELM autoencoder (ELM-AE) as well as a linear method, least absolute shrinkage and selection operator (LASSO), to build a reliable temperature downscaling model. ELM is an efficient learning algorithm for generalized single layer feed-forward neural networks (SLFNs). Its excellent training speed and good generalization capability make ELM an efficient solution for SLFNs compared to traditional time-consuming learning methods like back propagation (BP). However, due to its shallow architecture, ELM may not capture all of nonlinear relationships between input features. To address this issue, ELM-AE was tested in the current study for temperature downscaling.