• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.58-64
• /
• 1997

FLC(Fuzzy Logic Controller) is stronger to the disturbance than a classical controller and its overshoot of the intialized value is excellent. In case an unknown process or the mathematical modeling of a complicated system is impossible, a fit control quantity can be acquired by the Fuzzy inference. But FLC can not converge correctly to the desirable value because the FLC's output value by the size of the quantization level of the Fuzzy variable always has a minor error. There are many ways to eliminate the minor error, but I will suggest GA-FLC and EP-FLC Hybrid controller which csombines FLC with GA(Genetic Algorithm) and EP(Evo1ution Programming). In this paper, the output characteristics of this Hybrid controller will be compared and analyzed with those of FLC, it will he showed that this Hybrid controller converge correctly to the desirable value without any error, and !he convergence speed performance of these two kinds of Hyhrid controller also will be compared.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.279-284
• /
• 2014

This paper proposes a optimum design method for the Fuzzy PID controller of magnetic levitation-based Rail-Guided Vehicle(RGV). Since an attraction type levitation system is intrinsically unstable, it is difficult to completely satisfy the desired performance through the methods designed by conventional controllers. In the paper, the Fuzzy PID controller with fixed parameters are applied and then the optimum parameters of fuzzy PID controller are selected by genetic algorithm. For the fitness function of genetic algorithm, the performance index of PID controller is used. To verify the performance of the proposed method, we used Matlab/simulink model of Maglev and compared the proposed method with the performance of PID controller. The simulation results show that the proposed method is more effective than conventional PID controller.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.166-169
• /
• 2002

The accuracy in maneuvering target tracking using multiple models is caused by the suitability of each target motion model to be used. The interacting multiple model (IMM) algorithm and the adaptive IMM algorithm require the predefined sub-models and the predetermined acceleration intervals, respectively, in consideration of the properties of maneuvers to construct multiple models. In this paper, to solve these problems intelligently, a genetic algorithm (GA) based-IMM method using fuzzy logic is proposed. In the proposed method, a sub-model is represented as a set of fuzzy rules to model the time-varying variances of the process noises of a new piecewise constant white acceleration model, and the GA is applied to identify this fuzzy model. The proposed method is compared with the AIMM algorithm in simulations.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.160-162
• /
• 1999

This paper presents an optimal design method for fuzzy controllers of HVDC system using adaptive evolutionary algorithm(AEA). We have proposed an adaptive evolutionary algorithm which uses a genetic algorithm and an evolution strategy in an adaptive manner in order to take merits of two different evolutionary computations. AEA is used for tuning fuzzy membership functions, scaling constants and PD gains. The simulation results show that the disturbances are well damped by both controllers and the dynamic performances of fuzzy controllers have better responses than those of PD controllers when mechanical torque changes suddenly.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.302-309
• /
• 2005

We have studied a model and application that evolves the behavioral knowledge of a virtual robot. The knowledge is represented in classification rules and a neural network, and is learned by a genetic algorithm. The model consists of a virtual robot with behavior knowledge, an environment that it moves in, and an evolution performer that includes a genetic algorithm. We have also applied our model to an environment where the robots gather food into a nest. When comparing our model with the conventional method on various test cases, our model showed superior overall learning.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.223-225
• /
• 2002

In this paper, we designed fuzzy legit controller(FLC) for HVDC current control using genetic algorithm. The proposed method was applied to HVDC power system simulator in Korea Electrotechnology Research Institute(KERI). We are adjusted input/output gain of FLC by real-time using genetic algorithm. Experimental results show that FLC has the better control performance than PI controller in terms of settling time, rising time.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2386-2388
• /
• 2000

This paper proposes a novel method with pseudo-on-line scheme using look-up table based on the genetic algorithm. The technique is a pseudo-on-line method that optimally estimate the parameters of fuzzy PID(FPID) controller for systems with non-linearity using the genetic algorithm which does not use the gradient and finds the global optimum of an un-constraint optimization problem. The proposed controller(GFPID) is applied to speed control of 3-phase induction motor and its computer simulation is carried out. Simulation results show that the proposed method is more excellent than conventional FPID and PID controllers.

• Journal of Intelligence and Information Systems
• /
• v.17 no.2
• /
• pp.1-22
• /
• 2011

In this paper, we propose an adaptive genetic algorithm (aGA) approach for effectively solving the sequencing problem with precedence constraints (SPPC). For effective representation of the SPPC in the aGA approach, a new representation procedure, called the topological sort-based representation procedure, is used. The proposed aGA approach has an adaptive scheme using a fuzzy logic controller and adaptively regulates the rate of the crossover operator during the genetic search process. Experimental results using various types of the SPPC show that the proposed aGA approach outperforms conventional competing approaches. Finally the proposed aGA approach can be a good alternative for locating optimal solutions or sequences for various types of the SPPC.