• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.71-77
• /
• 1995

In this paper are proposed robust iterative learning control(ILC) algorithms for both linear continuous time-invariant system and linear discrete-time system. In contrast to conventional methods, the proposed learning algorithms are constructed based on both time domain performance and iteration-domain performance. The convergence of the proposed learning algorithms is proved. Also, it is shown that the proposed method has robustness in the presence of external disturbances and the convergence accuracy can be improved. A numerical external disturbances and the convergence accuracy can be improved. A numerical example is provided to show the effectiveness of the proposed algorithm.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.768-770
• /
• 1996

This paper propose neural network which is one of self-organizing techniques. It is composed neural network controller as input signal is error and change of error which is optimal output, and is learned system by using a error back-propagation learning algorithm is one of error mimizing learning methods. In order to achieve practical real time control reduce on learning time, it is applied to load-frequency control of nonlinear power system with using a moment learning method. It is described in such a case considering constraints for a rate of increace generation-rate.

• Structural Engineering and Mechanics
• /
• v.81 no.5
• /
• pp.647-664
• /
• 2022

The powerful data mapping capability of computational deep learning methods has been recently explored in academic works to develop strategies for structural health monitoring through appropriate characterization of dynamic responses. In many cases, these studies concern laboratory prototypes and finite element models to validate the proposed methodologies. Therefore, the present work aims to investigate the capability of a deep learning algorithm called Sparse Autoencoder (SAE) specifically focused on detecting structural alterations in real-case studies. The idea is to characterize the dynamic responses via SAE models and, subsequently, to detect the onset of abnormal behavior through the Shewhart T control chart, calculated with SAE extracted features. The anomaly detection approach is exemplified using data from the Z24 bridge, a classical benchmark, and data from the continuous monitoring of the San Vittore bell-tower, Italy. In both cases, the influence of temperature is also evaluated. The proposed approach achieved good performance, detecting structural changes even under temperature variations.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_1
• /
• pp.521-531
• /
• 2022

This study proposed a new approach to intelligent control of a mobile robot system by back properpagation based on multi-layer neural network. A experiment result is given in which some artificial assumptions about the linear and the angluar velocities of mobile robots from recent literature are dropped. In this study, we proposed a new thinique to impliment the real time conrol of he position and velocity of mobile robots. With the proposed control techinique, mobile robots can now globally follow any path such as a straight line, a circle and the path approaching th toe origin using proposed controller. Computer simulations are presented, which confirm the effectiveness of the proposed control algorithm. Moreover, practical experimental results concerning the real time control are reported with several real line constraints for mobile robots with two wheel driving.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.953-955
• /
• 1995

Studied on identification of nonlinear system with unknown variables and adaptive control were successful. We need a mathmatical model when control a dynamic system using adaptive control technique, but it is very difficult due to its nonlinearity. In this paper, we described about performance improvement of error back-propagation algorithm and learning algorithm of non-linear dynamic system. We examined the proposed back-propagation learn algorithm for through an experiment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.40-45
• /
• 2016

This paper presents the neuro-fuzzy control method for balancing a two-wheel mobile robot. A two-wheel mobile robot is built for the experimental studies. On-line learning algorithm based on the back-propagation(BP) method is derived for the Takagi-Sugeno(T-S) neuro-fuzzy controller. The modified error is proposed to learn the B-P algorithm for the balancing control of a two-wheel mobile robot. The T-S controller is implemented on a DSP chip. Experimental studies of the balancing control performance are conducted. Balancing control performances with disturbance are also conducted and results are evaluated.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.292-297
• /
• 1999

Evolving in artificial agent is an extremely difficult problem, but on the other hand, a challenging task. At present the studies mainly centered on single agent learning problem. In our case, we use simulated soccer to investigate multi-agent cooperative learning. Consider the fundamental differences in learning mechanism, existing reinforcement learning algorithms can be roughly classified into two types-that based on evaluation functions and that of searching policy space directly. Genetic Programming developed from Genetic Algorithms is one of the most well known approaches belonging to the latter. In this paper, we give detailed algorithm description as well as data construction that are necessary for learning single agent strategies at first. In following step moreover, we will extend developed methods into multiple robot domains. game. We investigate and contrast two different methods-simple team learning and sub-group loaming and conclude the paper with some experimental results.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.65-68
• /
• 1995

This paper describes trajectory generation of a riobot arm by self-organizing neural networks. These neural networks are based on competitive learning without a teacher and this algorithm which is suitable for problems in which solutions as teaching signal cannot be defined-e.g. inverse dynamics analysis-is adopted to the trajectory generation problem of a robot arm. Utility of unsupervised learning algorithm is confirmed by applying the approximated solution of each joint calculated through learning to an actual robot arm in giving the experiment of tracking for reference trajectory.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.939-942
• /
• 1996

This paper presents a stable learning algorithm for diagonal recurrent neural network(DRNN). DRNN is applied to a problem of controlling nonlinear dynamical systems. A architecture of DRNN is a modified model of the Recurrent Neural Network(RNN) with one hidden layer, and the hidden layer is comprised of self-recurrent neurons. DRNN has considerably fewer weights than RNN. Since there is no interlinks amongs in the hidden layer. DRNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. To guarantee convergence and for faster learning, an adaptive learning rate is developed by using Lyapunov function. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed algorithm is demonstrated by computer simulation.