• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1530-1533
• /
• 2005

In this paper, we design a Linear Quadratic Gaussian controller for the active suspension. We can improve the inherent suspension problem, trade-off between the ride quality and the suspension travel by selecting appropriate weights in the LQ-objective function. Because any definite rules for selecting weights do not exist, we use an optimization-algorithm, Evolution Strategy (ES) to find the proper control gains for selected frequencies, which have major effects on the vibrations of the vehicle's state variables. The frequencies and proper control gains are used for the neural network data. During a vehicle running, the trained on-line neural network is activated and provides the proper gains for non-trained frequencies. For the full-state feedback control, Kalman filter observes the full states and Fourier transform is used to detect the frequency of the road.

• The Plant Pathology Journal
• /
• v.38 no.4
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.188-194
• /
• 2015

This paper proposes a generalized regression neural network (GRNN) based algorithm for data interpolation and design optimization of brushless dc (BLDC) motor. The procedure makes use of magnet length, stator slot opening and air gap length as design variables. Cogging torque and average torque are treated as performance indices. The optimal design necessitates mitigating the cogging torque and maximizing the average torque by varying design variables. The data set for interpolation and ensuing design optimisation using GRNN is obtained by modeling a standard BLDC motor using finite element analysis (FEA) tool MagNet 7.1.1. The performance indices of the standard motor obtained using FEA are validated with an experimental model and an analytical method. The optimal design is authenticated using particle swarm optimization (PSO) algorithm and the performance indices of the optimal design obtained using GRNN is validated using FEA. The results indicate the suitability of GRNN as an interpolation and design optimization tool for a BLDC motor.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.563-565
• /
• 2005

This paper is proposed an efficiency optimization control algorithm for a synchronous reluctance motor(SynRM) which minimizes the copper and iron losses. ALso, this paper presents a sensorless control scheme of SynRM using artificial neural network(ANN). The proposed algorithm allows the electromagnetic losses in variable speed and torque drives to be reduced while keeping good torque control dynamics. The control performance of ANN is evaluated by analysis for various operating conditions. Analysis results are presented to show the validity of the proposed algorithm

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.8
• /
• pp.54-63
• /
• 1993

This paper proposes a method for improving the performances of the neural network for optimization by an optimal estimation of initial states. The optimal initial state that leads to the global minimum is estimated by using the stochastic approximation. And then the update rule of Hopfield model, which is the high speed deterministic algorithm using the steepest descent rule, is applied to speed up the optimization. The proposed method has been applied to the tavelling salesman problems and an optimal task partition problems to evaluate the performances. The simulation results show that the convergence speed of the proposed method is higher than conventinal Hopfield model. Abe's method and Boltzmann machine with random initial neuron output setting, and the convergence rate to the global minimum is guaranteed with probability of 1. The proposed method gives better result as the problem size increases where it is more difficult for the randomized initial setting to give a good convergence.

• Structural Engineering and Mechanics
• /
• v.78 no.2
• /
• pp.145-161
• /
• 2021

Dynamic compaction of Aluminum powder using gas detonation forming technique was investigated. The experiments were carried out on four different conditions of total pre-detonation pressure. The effects of the initial powder mass and grain particle size on the green density and strength of compacted specimens were investigated. The relationships between the mentioned powder design parameters and the final features of specimens were characterized using Response Surface Methodology (RSM). Artificial Neural Network (ANN) models using the Group Method of Data Handling (GMDH) algorithm were also developed to predict the green density and green strength of compacted specimens. Furthermore, the desirability function was employed for multi-objective optimization purposes. The obtained optimal solutions were verified with three new experiments and ANN models. The obtained experimental results corresponding to the best optimal setting with the desirability of 1 are 2714 kg·m-3 and 21.5 MPa for the green density and green strength, respectively, which are very close to the predicted values.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.349-353
• /
• 2007

The main functions of excavator are mainly carried out by excavator attachments such as arm and boom. These components should be designed to be light as well as durable enough because their effects on the whole structure are significant. In this paper, an optimization procedure for lightweight design considering fatigue strength for excavator attachments is presented. The weight of attachments and allowable fatigue stresses at critical areas are used as objective function and constraints, respectively, in which design variables are the thickness of the plates of attachments. The simulated annealing search method is adopted for a global optimization solution. Besides, the response surface method using the artificial neural network is used to simulate constraint function for the sake of practical fast calculation. Some example case of optimization is presented here for a sample excavator. This weight optimization is expected to contribute to a considerable improvement of fuel efficiency of excavator.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.8
• /
• pp.24-32
• /
• 2006

Using a deterministic design optimization, the effect of uncertainty can result in violation of constraints and deterioration of performances. For this reason, design optimization is required to guarantee reliability for constraints and ensure robustness for an objective function under uncertainty. Therefore, this study drew Monte Carlo Simulation(MCS) for the evaluation of reliability and robustness, and selected an artificial neural network as an approximate model that is suitable for MCS. Applying to the aero-structural optimization problem of aircraft wing, we can explore robuster optima satisfying the sigma level of reliability than the baseline.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.