• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2898-2901
• /
• 1999

This paper describes the design of nonlinear fuzzy I+PD controller using simplified indirect inference method. First, the fuzzy I+PD controller is derived from the conventional continuous time linear I+PD controller. Then the fuzzification, control-rule base, and defuzzification using SIIM in the design of the fuzzy controller are discussed in detail. The resulting controller is a discrete time fuzzy version of the conventional I+PD controller. which has the same linear structure. but are nonlinear functions of the input signals. The proposed controller enhances the self-tuning control capability. Particularly when the process to be controlled is nonlinear When the SIIM is applied, the fuzzy inference results can be calculated with splitting fuzzy variables into each action component and are determined as the functional form of corresponding variables. So the proposed method has the capability of the high speed inference and adapting with increasing the number of the fuzzy input variables easily. Computer simulation results have demonstrated the superior to the control performance of the one Proposed by D. Misir et at.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2839-2842
• /
• 1999

This paper describes the design of fuzzy PID controller using simplified indirect inference method. First, the fuzzy PID controller is derived from the conventional continuous time linear PID controller. Then the fuzzification, control-rule base, and defuzzification using SIIM in the design of the fuzzy controller are discussed in detail. The resulting controller is a discrete time fuzzy version of the conventional PID controller, which has the same linear structure. but are nonlinear functions of the input signals. The proposed controller enhances the self-tuning control capability, particularly when the process to be controlled is nonlinear. When the SIIM is applied, the fuzzy inference results can be calculated with splitting fuzzy variables into each action component and are determined as the functional form of corresponding variables. So the proposed method has the capability of the high speed inference and adapting with increasing the number of the fuzzy input variables easily. Computer simulation results have demonstrated the superior to the control performance of the one proposed by D. Misir et al.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1377-1379
• /
• 1996

In this paper, each parameter was identified by the gradient descent method to overcome difficulty deciding fuzzy rules of FLC for the unknown process and the type of membership Junctions. Usually PID or optimal control theories have been mostly usee in control field so far. However, optimal control requires much time for calculation because of adaptation for disturbance and nonlinearity. And intricate technique such as MRAS which can be realized only by an expert are limited to be used in the systems requiring rapid and precise response because of comparatively longer calculating time and complicateness. Gradient descent method is a method to find Z minimizing a function about a certain vector Z. And required output of FLC is gained using gradient approaching method in order to adapt control rule parameters of FLC. Simulation proved validation of this algorithm.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1359-1361
• /
• 1996

This paper describes a design of real time fuzzy controller using Minimum fuzzy control Rule Selection Method(MRSM). The control algorithm of dynamic systems needs less computation time and memory. To reduce the computation time of fuzzy logic controller, minimum number of rules are to be selected for the fuzzy input variable. The universe of discourse is divided by the number of linguistic labels to allocate the assigned membership function to the fuzzy input variables. In this case, since fuzzy input variables are continuous, scale factor SU is tuned independently. According to increment of SU control surface is improved to adapt the change of system parameter. At this, crisp control surface is increased. With the increament of crisp control surface, fuzzy control surface is reduced. When error state deviates from desirable error state, crisp control surface is more useful than fuzzy control surface for obtaining fast rising time.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2633-2635
• /
• 2003

In this study, we propose a fuzzy polynomial neural networks (FPNN) and a genetically optimized fuzzy polynomial neural networks(GoFPNN) for identification of non-linear system. GoFPNN architecture is designed by a FPNN based on fuzzy set and its structure and parameters are optimized by genetic algorithms. A fuzzy neural networks(FNN) based on fuzzy set divide into two structures that is simplified inference structure and linear inference structure. The proposed FPNN is resulted from integration and extension of simplified and linear inference structure of FNN. The consequence structure of the FPNN consist of polynomials represented by networks using connection weights for rules. The networks comprehend simplified(Type 0), linear (Type 1), and quadratic(Type 3) inferences. The proposed FPNN can select polynomial type of consequence part for each rule. Therefore, proposed scheme can offer flexible structure design capability for a system characteristics. Moreover, GAs is applied to networks structure and parameters tuning of proposed FPNN, and its efficient application method is discussed, these subjects are result in GoFPNN that is optimal FPNN. To evaluate proposed model performance, a numerical experiment is carried out.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.1958-1960
• /
• 2001

In this paper, we propose the design methodology of target tracking system using the identification of TS fuzzy model based on genetic algorithm(GA) and RLS algorithm. In general, the objective of target tracking is to estimate the future trajectory of the target based on the past position of the target obtained from the sensor. In the conventional and mathematical nonlinear filtering method such as extended Kalman filter(EKF), the performance of the system may be deteriorated in highly nonlinear situation. In this paper, to resolve these problems of nonlinear filtering technique, the error of EKF by nonlinearity is compensated by identifying TS fuzzy model. In the proposed method, after composing training datum from the parameters of EKF, by identifying the premise and consequent parameters and the rule numbers of TS fuzzy model using GA, and by tuning finely the consequent parameters of TS fuzzy model using recursive least square(RLS) algorithm, the error of EKF is compensated. Finally, the proposed method is applied to three dimensional tracking problem, and the simulation results shows that the tracking performance is improved by the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Journal of the Korean association of regional geographers
• /
• v.22 no.3
• /
• pp.681-702
• /
• 2016

Two different modelling approaches to dune dynamics have been established thus far; continuous models that emphasize the precise representation of wind field, and feedback-based models that focus on the interactions between dunes, rather than aerodynamics. Though feedback-based models have proven their capability to capture the essence of dune dynamics, the compatibility issues on these models have less been addressed. This research investigated, mostly from the theoretical point of view, the algorithmic compatibility of three feedback-based dune models: sand slab models, Nishimori model, and de Castro model. Major findings are as follows. First, sand slab models and de Castro model are both compatible in terms of flux perspectives, whereas Nishimori model needs a tuning factor. Second, the algorithm of avalanching can be easily implemented via repetitive spatial smoothing, showing high compatibility between models. Finally, the wind shadow rule might not be a necessary component to reproduce dune patterns unlike the interpretation or assumption of previous studies. The wind shadow rule, rather, might be more important in understanding bedform-level interactions. Overall, three models show high compatibility between them, or seem to require relatively small modification, though more thorough investigation is needed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-64
• /
• 1995

Robot manipulator is a highly nonlinear-time varying system. Therefore, a lot of control theory has been applied to the system. Robot manipulator has two types of control; one is path planning, another is path tracking. In this paper, we select the path tracking, and for this purpose, propose the intelligent control¬ler which is combined with fuzzy logic and neural network. The fuzzy logic provides an inference morphorlogy that enables approximate human reasoning to apply to knowledge-based systems, and also provides a mathematical strength to capture the uncertainties associated with human cognitive processes like thinking and reasoning. Based on this fuzzy logic, the fuzzy logic controller(FLC) provides a means of converhng a linguistic control strategy based on expert knowledge into automahc control strategy. But the construction of rule-base for a nonlinear hme-varying system such as robot, becomes much more com¬plicated because of model uncertainty and parameter variations. To cope with these problems, a auto-tuning method of the fuzzy rule-base is required. In this paper, the GA-based Fuzzy-Neural control system combining Fuzzy-Neural control theory with the genetic algorithm(GA), that is known to be very effective in the optimization problem, will be proposed. The effectiveness of the proposed control system will be demonstrated by computer simulations using a two degree of freedom robot manipulator.

• Journal of Power Electronics
• /
• v.15 no.3
• /
• pp.753-762
• /
• 2015

This paper presents a nonlinear sliding mode control (SMC) scheme with a variable damping ratio for interior permanent magnet synchronous motors (IPMSMs). First, a nonlinear sliding surface whose parameters change continuously with time is designed. Actually, the proposed SMC has the ability to reduce the settling time without an overshoot by giving a low damping ratio at the initial time and a high damping ratio as the output reaches the desired setpoint. At the same time, it enables a fast convergence in finite time and eliminates the singularity problem with the upper bound of an uncertain term, which cannot be measured in practice, by using a simple adaptation law. To improve the efficiency of a system in the constant torque region, the control system incorporates the maximum torque per ampere (MTPA) algorithm. The stability of the nonlinear sliding surface is guaranteed by Lyapunov stability theory. Moreover, a simple sliding mode observer is used to estimate the load torque and system uncertainties. The effectiveness of the proposed nonlinear SMC scheme is verified using comparative experimental results of the linear SMC scheme when the speed reference and load torque change under system uncertainties. From these experimental results, the proposed nonlinear SMC method reveals a faster transient response, smaller steady-state speed error, and less sensitivity to system uncertainties than the linear SMC method.