• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2876-2878
• /
• 2005

In this paper, we propose Genetic Algorithms(GAs)-based Optimal Polynomial Neural Networks(PNN). The proposed algorithm is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. The study is illustrated with the ACI Distance Relay Data for application to power systems.

• Journal of Korean Society on Water Environment
• /
• v.29 no.1
• /
• pp.19-28
• /
• 2013

Artificial neural networks were used for time series modelling of algal dynamics of whole year and by season at the Paldang dam station (confluence area). The modelling was based on comprehensive weekly water quality data from 1997 to 2004 at the Paldang dam station. The results of validation of seasonal models showed that the timing and magnitude of the observed chlorophyll a concentration was predicted better, compared with the ANN model for whole year. Internal weightings of the inputs in trained neural networks were obtained by sensitivity analysis for identification of the primary driving mechanisms in the system dynamics. pH, COD, TP determined most the dynamics of chlorophyll a, although these inputs were not the real driving variable for algal growth. Short-term prediction models that perform one or two weeks ahead predictions of chlorophyll a concentration were designed for the application of Harmful Algal Alert System in Lake Paldang. Short-term-ahead ANN models showed the possibilities of application of Harmful Algal Alert System after increasing ANN model's performance.

• Journal of Mechanical Science and Technology
• /
• v.19 no.7
• /
• pp.1393-1404
• /
• 2005

Fatigue crack growth and life have been estimated based on established empirical equations. In this paper, an alternative method using artificial neural network (ANN) -based model developed to predict fatigue damages simultaneously. To learn and generalize the ANN, fatigue crack growth rate and life data were built up using in-plane bending fatigue test results. Single fracture mechanical parameter or nondestructive parameter can't predict fatigue damage accurately but multiple fracture mechanical parameters or nondestructive parameters can. Existing fatigue damage modeling used this merit but limited real-time damage monitoring. Therefore, this study shows fatigue damage model using backpropagation neural networks on the basis of X -ray half breadth ratio B / $B_o$, fractal dimension $D_f$ and fracture mechanical parameters can estimate fatigue crack growth rate da/ dN and cycle ratio N / $N_f$ at the same time within engineering limit error ($5\%$).

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.303-308
• /
• 2022

Simulating the heat transfer in a composite material is an important topic in material science. Difficulties arise from the fact that adjacent materials cannot match perfectly, resulting in discontinuity in the temperature variables. Although there have been several numerical methods for solving the heat-transfer problem in imperfect contact conditions, the methods known so far are complicated to implement, and the computational times are non-negligible. In this study, we developed a ResNet-type deep neural network for simulating a heat transfer model in a composite material. To train the neural network, we generated datasets by numerically solving the heat-transfer equations with Kapitza thermal resistance conditions. Because datasets involve various configurations of composite materials, our neural networks are robust to the shapes of material-material interfaces. Our algorithm can predict the thermal behavior in real time once the networks are trained. The performance of the proposed neural networks is documented, where the root mean square error (RMSE) and mean absolute error (MAE) are below 2.47E-6, and 7.00E-4, respectively.

• 한국생물공학회:학술대회논문집
• /
• 2000.04a
• /
• pp.133-136
• /
• 2000

In recent years, hybrid neural network approaches which combine neural networks and mechanistic models have been gaining considerable interests. These approaches are potentially very efficient to obtain more accurate predictions of process dynamics by combining mechanistic and neural models in such a way that the neural network model properly captures unknown and nonlinear parts of the mechanistic model. In this work, such an approach was applied in the modeling of a full-scale coke wastewater treatment process. First, a simplified mechanistic model was developed based on the Activated Sludge Model No.1 and the specific process knowledge, Then neural network was incorporated with the mechanistic model to compensate the errors between the mechanistic model and the process data. Simulation and actual process data showed that the hybrid modeling approach could predict accurate process dynamics of industrial wastewater treatment plant. The promising results indicated that the hybrid modeling approach could be a useful tool for accurate and cost-effective modeling of biochemical processes.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.57-60
• /
• 2011

Updating model parameters are required in order to simulate the actual behavior of the dynamic structure. A new strategy, mean-iterative neural networks (MINNs) has been proposed in this paper for model parameter updating of a steel box girder bridge. With new strategy for structural dynamic model updating, it offers many advantages such as potential savings of computational effort, more consistent in reaching convergence. The dynamic response obtained from the experimental test on a two span continuous bridge is used as the target for model updating. And the presented algorithm is applied to update the model parameters. These results show a good possible of using MINNs in practice for dynamic model updating.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.446-449
• /
• 1997

We propose a control law in discrete time domain of the bilateral feedback teleoperation system using neural network and the reference model type of adaptive control. Different from traditional teleoperation systems, the transmission time delay irregularly changes. The proposed control method controls master and slave systems through identification of master and slave models using neural networks.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.227-233
• /
• 1996

The Inverted Pendulum has been one of most popular nonlinear dynamic systems for the exploration of control techniques. This paper presents a new linear optimal control techniques and nonlinear neural network learning methods. The multiayered neural networks are used to add nonlinear effects on the linear optimal regulator(LQR). The new regulator can compensate nonlinear system uncertainties that are not considered in the LQR design, and can tolerated a wider range of uncertainties than the LQR alone. The new regulator has two neural networks for modeling and control. The neural network for modeling is used to obtain a more accurate model than the given mathematical equations. The neural network for control is used to overcome deficiencies by adding corrections to the linear coefficients of the LQR and by adding nonlinear effects on the LQR. Computer simulations are performed to show the applicability and a more robust regulator than the LQR alone.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.157-160
• /
• 1995

Neural networks potentially offer a general framework for modeling and control of nonlinear systems. The conventional neural network models are a parody of biological neural structures, and have very slow learning. In order to emulate some, dynamic functions, such as learning and adaption, and to better reflect the dynamics of biological neurons, M.M.Gupta and D.H.Rao have developed a 'dynamic neural model'(DNU). Proposed neural unit model is to introduce some dynamics to the neuron transfer function, such that the neuron activity depends on internal states. Numerical examples are presented for a model system. Those case studies showed that the proposed DNU is so useful in practical sense.