• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.1 no.1
• /
• pp.87-94
• /
• 2001

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.3B no.3
• /
• pp.128-132
• /
• 2003

This paper presents the optimum design of a Linear Induction Motor (LIM) using Genetic algorithm, Niching Genetic algorithm and Neural Network. The design variables are optimized by different optimization methods and the results are discussed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.9
• /
• pp.1462-1469
• /
• 1997

This study presents a genetic algorithm-based method for optimizing control parameters in fluid power systems. Genetic algorithms are general-purpose optimization methods based on natural evolution and genetics. A genetic algorithm seeks control parameters maximizing a measure that evaluates system performance. Five control gains of the PID-PD cascade controller fr an electrohydraulic speed control system with a variable displacement hydraulic motor are optimized using a genetic algorithm in the experiment. Optimized gains are confirmed by inspecting the fitness distribution which represents system performance in gain spaces. It is shown that optimization of the five gains by manual tuning should be a task of great difficulty and that a genetic algorithm is an efficient scheme giving economy of time and in labor in optimizing control parameters of fluid power systems.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.1
• /
• pp.40-45
• /
• 2008

This paper presents an optimal design of a permanent magnet actuator(PMA) using a parallel genetic algorithm. Dynamic characteristics of permanent magnet actuator model are analyzed by coupled electromagnetic-mechanical finite element method. Dynamic characteristics of PMA such as holding force, operating time, and peak current are obtained by no load test and compared with the analyzed results by coupled finite element method. The permanent magnet actuator model is optimized using a parallel genetic algorithm. Some design parameters of vertical length of permanent magnet, horizontal length of plunger, and depth of permanent magnet actuator are predefined for an optimal design of permanent magnet actuator model. Furthermore dynamic characteristics of the optimized permanent magnet actuator model are analyzed by coupled finite element method. A displacement of plunger, flowing current of the coil, force of plunger, and velocity of plunger of the optimized permanent magnet actuator model are compared with the results of a primary permanent magnet actuator model.

• Proceeding of EDISON Challenge
• /
• 2015.03a
• /
• pp.543-546
• /
• 2015

There have been subway conflagrations such as Daegu subway conflagration at 2003, Washington D.C conflagration last month and so on. Compared to that, proper evacuation route is far from satisfactory. So this paper suggests optimized route when subway's passengers evacuate from passenger cars. For conducting our experiment, We made temporarily a model of subway station which is made up with 8 passengers cars and 3 exits. Using genetic algorithm, we found the optimized route that first and second passenger cars are optimized to first exit and third, fourth, fifth and sixth passengers cars are optimized to second exit and finally seventh, eighth passengers cars are optimized to third exit. It is expected that real subway station is applied to our experiment by developing passenger distribution algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.612-618
• /
• 1998

The success of a fuzzy logic control system solving any given problem critically depends on the architecture of th network. Various attempts have been made in optimizing its structure its structure using genetic algorithm automated designs. In a regular genetic algorithm , a difficulty exists which lies in the encoding of the problem by highly fit gene combinations of a fixed-length. This paper presents a new approach to structurally optimized designs of a fuzzy model. We use a messy genetic algorithm, whose main characteristics is the variable length of chromosomes. A messy genetic algorithms used to obtain structurally optimized fuzzy models. Structural optimization is regarded important before neural network based learning is switched into. We have applied the method to the exampled of a cart-pole balancing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.2925-2948
• /
• 2019

In order to improve the utilization of irrigation water resources of greenhouse tomatoes, a water-saving irrigation decision-making model based on genetic optimization T-S fuzzy neural network is proposed in this paper. The main work are as follows: Firstly, the traditional genetic algorithm is optimized by introducing the constraint operator and update operator of the Krill herd (KH) algorithm. Secondly, the weights and thresholds of T-S fuzzy neural network are optimized by using the improved genetic algorithm. Finally, on the basis of the real data set, the genetic optimization T-S fuzzy neural network is used to simulate and predict the irrigation volume for greenhouse tomatoes. The performance of the genetic algorithm improved T-S fuzzy neural network (GA-TSFNN), the traditional T-S fuzzy neural network algorithm (TSFNN), BP neural network algorithm(BPNN) and the genetic algorithm improved BP neural network algorithm (GA-BPNN) is compared by simulation. The simulation experiment results show that compared with the TSFNN, BPNN and the GA-BPNN, the error of the GA-TSFNN between the predicted value and the actual value of the irrigation volume is smaller, and the proposed method has a better prediction effect. This paper provides new ideas for the water-saving irrigation decision in greenhouse tomatoes.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.2
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.263-272
• /
• 2024

A model based on genetic algorithm optimization, GA-SVM, is proposed to warn university students of their status. This model improves the predictive effect of support vector machines. The genetic optimization algorithm is used to train the hyperparameters and adjust the kernel parameters, kernel penalty factor C, and gamma to optimize the support vector machine model, which can rapidly achieve convergence to obtain the optimal solution. The experimental model was trained on open-source datasets and validated through comparisons with random forest, backpropagation neural network, and GA-SVM models. The test results show that the genetic algorithm-optimized radial basis kernel support vector machine model GA-SVM can obtain higher accuracy rates when used for early warning in university learning.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1460-1463
• /
• 1997

The aim of this paper is to suggest a design method of the model following optimal boiler-turbine H.inf. control system using genetic algorithm. This boiler-turbine H.inf. control system is designed by applying genetic algortihm with reference model to the optimal determination of weighting functions and design parameter .gamma. that are given by Glover-Doyle algornithm whch can design H.inf. contrlaaer in the sate. space. The first method to do this is ghat the gains of weightinf functions and .gamma. are optimized simultaneously by genetic algroithm. And the second method is that not only the gains and .gamma. but also the dynamics of weighting functions are optimized at the same time by genetic algonithm. The effectiveness of this boiler-turbine H.inf. control system is verified and compared with LQG/LTR control system by computer simulation.