• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.4
• /
• pp.379-386
• /
• 2003

The goal of this research is to develop a Heel/Side Laster and control GUI(Graphic User Interface) for adaptive manufacturing. For this purpose, we have analyzed the working sequences of heel/side laster, and developed a control program that will facilitate the machineries with functions that are suitable for adaptive manufacturing. We also made it possible to modify the gluing path with simple manipulation of CAD data. By providing a user-friendly GUI, we made it possible for unskilled workers use the system without difficulty. In addition, we have developed a flexible environment where the already available CAD data can be modified and saved with ease. Automatic feeding and path control algorithms for thermoplastic cement were also implemented. By using the Heel/Side Laster for adaptive manufacturing, we are able to achieve increased productivity and work efficiency while improving the quality of the product with self-diagnosis and fine adjustment function.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.92-100
• /
• 2018

This paper presents a link adaptation scheme for adaptive full duplex (AFD) systems. The signal modulation levels and communication link patterns are adaptively selected according to the changing channel conditions. The link pattern selection process consists of two successive steps such as a transmit-receive antenna pair selection based on maximum sum rate or minimum maximum symbol error rate, and an adaptive modulation based on maximum minimum norm. In AFD systems, the antennas of both nodes are jointly determined with modulation levels depending on the channel conditions. An adaptive algorithm with relatively low complexity is also proposed to select the link parameters. Simulation results show that the proposed AFD system offers significant bit error rate (BER) performance improvement compared with conventional full duplex systems with perfect or imperfect self-interference cancellation under the same fixed sum rate.

• Journal of the Korea Society for Simulation
• /
• v.25 no.3
• /
• pp.65-76
• /
• 2016

Self-adaptive software is software that adapts by itself to system requirements about the recognized problems without stopping the software cycle. In order to reduce the unnecessary adaptation in the system having the critical points, we propose proactive approach which can predict the future operation after a critical point. In this paper, we predict the future operation after a critical point using a hybrid model to deal with the characteristics of the observed data with the linear and non-linear pattern. The operation of the prediction method is determined on a timing decision indicator based on the prediction accuracy. The two main points of contributions of this paper are to reduce uncertainty about the future operation by predicting the situation after a critical point using hybrid model and to reduce unnecessary adaptation implementation by deciding a timing based on a timing decision indicator.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1161-1167
• /
• 2006

본 논문에서는 구조, 행위, 리소스, 환경의 여러 관점을 적용한 다양한 모델들을 이용하는 적응 프레임워크를 제안한다. 또한, 대상 시스템에 대해 앞에서 언급한 4 가지 모델을 위한 모델링 방법론과 각 모델링 요소들에 대한 효과적인 표기법을 제시하였다. 다양한 모델들을 통해 시스템의 구성 요소들 간의 관계 구조와 시스템의 계층적 상태와 행위 정보, 실행 환경을 구성하는 시스템 의존적인 요소 및 독립적인 요소까지의 정보들이 표현된다. 이들 모델간의 유기적인 상호 운용으로 통합적인 추론과 보다 정확한 평가가 가능하다. 이를 통해 시스템은 예상치 못한 변화에 대해 통합된 관점의 더욱 정확한 진단과 반영할 수 있다. 이를 기반으로 다양한 수준에서 적응 동작의 조절을 수행함으로써 하이브리드하고 보다 확장된 적응이 가능해진다. 논문에서 정의한 모델과 제안 프레임워크는 다른 도메인으로 재사용이 가능하다. 제안 시스템은 평가를 위해 프로토타입을 구현하여 원격 화상 회의 시스템에 적용하였으며, 그 기능과 유효성을 확인하였다.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.519-520
• /
• 2016

BLSRM is a nonlinear, strong coupling and multi-variable system. The conventional control method is vulnerable to uncertain factors such as the load disturbance and satellite parameters change. It is difficult to obtain satisfactory control effect. Basing on a 8/10 BLSRM, whose suspending force control is separated with the torque control, this paper presents adaptive fuzzy PID controller for levitation control, which apply the fuzzy logic control to the conventional PID controller for parameters self-tuning. Both fuzzy and parameters of PID controller are self-tuning on-line, which improve the performance of controller. Finally, simulation and experimental results show the performance of the proposed method.

• Proceedings of the KIEE Conference
• /
• 1991.11a
• /
• pp.223-226
• /
• 1991

In this paper, the problem of designing on adaptive controller for dc drives using state observers, which is operated under varying load conditions, is addressed. A robust self-tuning controller that can track a constant reference and reject constant load disturbances is also studied. This scheme is very attractive since the estimates of system parameters are available in real time. Parameter estimation is based on the recursive least squares method and the control algorithm of the pole placement technique. Also, state observer systems are applied. State observer systems are required to estimate the states quickly and exactly without being affected by the disturbances.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.9
• /
• pp.1463-1468
• /
• 2003

This paper presented the real-time self-tuning learning control based on evolutionary computation, which proves its superiority in finding of the optimal solution at the off-line learning method. The individuals of the populations are reduced in order to learn the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations is proposed. It is possible to control the control object slightly varied as time changes. As the state value of the control object is generated, evolutionary strategy is applied each sampling time because the learning process of an estimation, selection, mutation is done in real-time. These algorithms can be applied; the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes.

• Proceedings of the KIEE Conference
• /
• 1992.07b
• /
• pp.1231-1234
• /
• 1992

In this paper a self-tuning control algorithm has been utilized to control speed of a rolling mill DC drive system. Inner current control loop is composed of predictive current controller and the outer speed control loop is composed of the self-tuning PI or IP controller. Computer simulation results reveal that the adaptive control algorithm using self-tuning control is capable of following the typical set point variations required for a rolling mill in conjunction with load torque variations on the shaft of the drive.

• 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 the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.231-240
• /
• 2001

Conventional expert systems has been criticized due to its lack of capability to adapt to the changing decision-making environments. In literature, many methods have been proposed to make expert systems more environment-adaptive by incorporating fuzzy logic and neural networks. The objective of this paper is to propose a new approach to building a self-evolving expert system inference mechanism by integrating fuzzy neural network and fuzzy rule extraction technique. The main recipe of our proposed approach is to fuzzify the training data, train them by a fuzzy neural network, extract a set of fuzzy rules from the trained network, organize a knowledge base, and refine the fuzzy rules by applying a pruning algorithm when the decision-making environments are detected to be changed significantly. To prove the validity, we tested our proposed self-evolving expert systems inference mechanism by using the bankruptcy data, and compared its results with the conventional neural network. Non-parametric statistical analysis of the experimental results showed that our proposed approach is valid significantly.