• International Journal of Control, Automation, and Systems
• /
• v.6 no.6
• /
• pp.928-938
• /
• 2008

This study presents an approach for approximation an unknown function from a numerical data set based on the synthesis of a neuro-fuzzy model. An adaptive input data space parting method, which is used for building hyperbox-shaped clusters in the input data space, is proposed. Each data cluster is implemented here as a fuzzy set using a membership function MF with a hyperbox core that is constructed from a min vertex and a max vertex. The focus of interest in proposed approach is to increase degree of fit between characteristics of the given numerical data set and the established fuzzy sets used to approximate it. A new cutting procedure, named NCP, is proposed. The NCP is an adaptive cutting procedure using a pure function $\Psi$ and a penalty function $\tau$ for direction the input data space parting process. New algorithms named CSHL, HLM1 and HLM2 are presented. The first new algorithm, CSHL, built based on the cutting procedure NCP, is used to create hyperbox-shaped data clusters. The second and the third algorithm are used to establish adaptive neuro- fuzzy inference systems. A series of numerical experiments are performed to assess the efficiency of the proposed approach.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.2
• /
• pp.137-143
• /
• 2005

Autonomous mobile robot has an ability to navigate using both map in known environment and sensors for detecting obstacles in unknown environment. In general, autonomous mobile robot navigates by global path planning on the basis of already made map and local path planning on the basis of various kinds of sensors to avoid abrupt obstacles. This paper provides a global path planning method using self-organizing feature map which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Structural Engineering and Mechanics
• /
• v.88 no.2
• /
• pp.141-157
• /
• 2023

In the present paper, the effect of recycled aggregates on the rheological and mechanical properties of self-consolidating concrete is investigated experimentally and numerically. Hence, the specimen with two types of recycled aggregates, i.e., known and unknown resistance origins, are utilized for the studied specimens. The experiments in this study are designed using the Box-Behnken method, which is one of the response surface methods. Input variables in mixtures include silica fume in the range of 5-15% as a percentage substitute for cement weight and recycled coarse and fine aggregates in the range of 0-50% for both series of recycled materials as a substitute for natural materials. The studied responses are slump flow, V funnel, compressive strength, tensile strength, and durability. The results indicate that the increase in the amount of recycled aggregates reduces the rheological and mechanical properties of the mixtures, while silica fume effectively improves the mechanical properties. In addition, the results demonstrate that the fine recycled aggregates affect the total response of the concrete significantly. The results of tensile and compressive strengths indicate that the mixtures including 50% recycled materials with known resistance origin demonstrate better responses up to 8 and 10% compared to the materials with unknown resistance origins, respectively. Recycled materials with a specific resistance origin also show better results than recycled materials with an unknown resistance origin. Durability test results represent those concretes containing recycled coarse aggregates have lower strength compared to recycled fine aggregates. Also, a series of mathematical relationships for all the responses are presented using variance analysis to predict mixtures' rheological and mechanical properties.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.337-340
• /
• 1997

In this paper we propose direct and indirect adaptive controllers for a nonlinear multivariable steam generating unit(200MW). In the direct adaptive scheme the estimation of the controller parameter are achieved from tracking error, while in the indirect approach the unknown parameter of the boiler system is estimated by the Hopfield network-based identifier. The performance of two proposed adaptive controllers is shown through simulations.

• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.163-169
• /
• 2014

A stable neural network control scheme for unknown non-linear systems is developed in this paper. While the control variable is optimised to minimize the performance index, convergence of the index is guaranteed asymptotically stable by a Lyapnov control law. The optimization is achieved using a gradient descent searching algorithm and is consequently slow. A fast convergence algorithm using an adaptive learning rate is employed to speed up the convergence. Application of the stable control to a single input single output (SISO) non-linear system is simulated. The satisfactory control performance is obtained.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.6
• /
• pp.32-40
• /
• 1992

This study shows how the finite element method for the structural problems could be applied in the electromechanical impedance analysis of an in-air piezoelectric cylinder transducer and then compares the numerical results by the FEM with the measured results using the impedance analyzer. The results also show that the comparison between both results could be applied to examine the mechanical properties of the added unknown material to transducer such as an acoustic window.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.70-74
• /
• 1989

To track the target trajectory with maneuvers, unknown maneuvering inputs must be estimated. To do this the direct estimation algorithm using generalized least square technique is developed based on the procedure of failure detection and identification(FDI) theory. Through the simulation using maneuvering target scenario, tracking performance and efficiency of the algorithm developed here are investigated.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.128.3-128
• /
• 2001

In this paper we proposed that the speed of induction motor is controlled by a PI controller, which could control unknown motor using Neural Network for auto-tuning of the PI parameter. The parameters of the PI controller were adjusted to reduce the speed error of the controlled motor. The input parameters of the Neural Network controller are the speed, q-axis current, and speed reference of the induction motor respectively. The usefulness of proposed controller will be confirmed by simulation which we compare with conventional PI controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.286-291
• /
• 1991

This paper discusses sliding made control of robot manipurators assuming that nonlinear terms, which are inertia term, Coriolis force term and centrifugal taffn, are external disturbances. We obtained the unknown parameter of its linear terms by Signal Compression Method. We propose a new control input algorithm to decrease chattering in the application of sliding mode control of manipulator whose nonlinear components are regarded as disturbances. In this experiments, we used DSP(Digital Signal Processor) controller to suppress chattering by obtaining a quick switching speed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1068-1072
• /
• 1991

This paper presents a decentralized model reference adaptive control scheme for an interconnected continuous linear system composed of a number of single-input single-output subsystems in which outgoing interactions pass through the measurement channel and are subject to bounded external disturbance. The scheme can treat the unknown strength of interactions as well as the uncertainty of subsystems.