• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.395-400
• /
• 1993

This paper presents an application of back propagation neural network to the tracking control of line of sight stabilization system. We design a neuro-control system having two neural networks one for learning system dynamics and the other for control. We use a learning method which adjusts learning rate and momentem as a function of plant output error and error change.

• Journal of Power Electronics
• /
• v.16 no.2
• /
• pp.564-571
• /
• 2016

This study proposes an adaptive neuro-fuzzy inference system (ANFIS)-based rotor position controller for brushless direct current (BLDC) motors to improve the control performance of the drive under transient and steady-state conditions. The dynamic response of a BLDC motor to the proposed ANFIS controller is considered as standard reference input. The effectiveness of the proposed controller is compared with that of the proportional integral derivative (PID) controller and fuzzy PID controller. The proposed controller solves the problem of nonlinearities and uncertainties caused by the reference input changes of BLDC motors and guarantees a fast and accurate dynamic response with an outstanding steady-state performance. Furthermore, the ANFIS controller provides low torque ripples and high starting torque. The detailed study includes a MATLAB-based simulation and an experimental prototype to illustrate the feasibility of the proposed topology.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.499-501
• /
• 1998

In this paper, we present a self-compensating PID controller which consists of a conventional PID controller that controls the linear components and a neural controller that controls the higher order and nonlinear components. This controller is based on the Harris's concept where he explained that the adaptive controller consists of the PID control term and the disturbance compensating term. The resulting controller's architecture is also found to be very similar to that of Wang's controller. This controller adds a self-tuning ability to the existing PID controller without replacing it by compensating the control errors through the neuro-controller. When applied to an actual magnetic levitation system which is known to be very nonlinear, it has also produced an excellent results.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.1
• /
• pp.7-17
• /
• 1997

During the past decade, there were many well-established theories for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of industrial robot control. Neural network computing methods provide one approach to the development of adaptive and learning behavior in robotic system for manufacturing. Computational neural networks have been demonstrated which exhibit capabilities for supervised learning, matching, and generalization for problems on an experimental scale. Supervised learning could improve the efficiency of training and development of robotic systems. In this paper, a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital signal processors is proposed. Digital signal processors, DSPs, are micro-processors that are developed particularly for fast numerical computations involving sums and products of variables. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be an efficient control scheme for implementation of real-time control for SCARA robot with four-axes by experiment.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.6
• /
• pp.1439-1450
• /
• 2013

This paper investigates a robust neuro-fuzzy control (NFC) method which can accurately follow the speed reference of an interior permanent magnet synchronous motor (IPMSM) in the existence of nonlinearities and system uncertainties. A neuro-fuzzy control term is proposed to estimate these nonlinear and uncertain factors, therefore, this difficulty is completely solved. To make the global stability analysis simple and systematic, the time derivative of the quadratic Lyapunov function is selected as the cost function to be minimized. Moreover, the design procedure of the online self-tuning algorithm is comparatively simplified to reduce a computational burden of the NFC. Next, a rotor angular acceleration is obtained through the disturbance observer. The proposed observer-based NFC strategy can achieve better control performance (i.e., less steady-state error, less sensitivity) than the feedback linearization control method even when there exist some uncertainties in the electrical and mechanical parameters. Finally, the validity of the proposed neuro-fuzzy speed controller is confirmed through simulation and experimental studies on a prototype IPMSM drive system with a TMS320F28335 DSP.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.2
• /
• pp.38-47
• /
• 2001

In this paper, a new scheme of adaptive-neuro control system is presented to implement real-time control of robot manipulator using Digital Signal Processors. Digital signal processors, DSPs, are micro-processors that are particularly developed for fast numerical computations involving sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of therir prices. These features make DSPs a viable computational tool in digital implementation of sophisticated controllers. Unlike the well-established theory for the adaptive control of linear systems, there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust perfor-mance for application of robot control. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method.The proposed adaptive-neuro control scheme is illustrated to be a efficient control scheme for the implementation of real-time control of robot system by the simulation and experi-ment.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.2
• /
• pp.310-316
• /
• 2003

One of the significant subject in the automatic arc welding is to establish control system of the welding parameters for controlling bead geometry as a criterion to evaluate the quality of arc welding. This paper proposes an inference algorithm for bead geometry in CMA Welding using Neuro-Fuzzy algorithm. The characteristic welding parameters are measured by the circuit composed of hall sensor, voltage divider tachometer, etc. and then the bead geometry of each weld pool is calculated and detected by an image processing with CCD camera and a measuring with microscope. The relationships between the characteristic welding parameters and the bead geometry have been arranged empirically. From the result of experiments, membership functions and fuzzy rules are tuned and determined by the learning of neural network, and then the relationship between actual bead geometry and inferred bead geometry are concluded by fuzzy logic controller. In the applied inference system of bead geometry using Neuro-Fuzzy algorithm, the inference error percent is within -5%∼+4% in case of bead width, -10%∼+10% in bead height, -5%∼+6% in bead area, -10%∼+10% in penetration. Use of the Neuro-Fuzzy algorithm allows the CMA Welding system to evaluate the quality in bead geometry in real time as the welding parameters change.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.712-715
• /
• 1997

In image jacobian based visual servoing, generally, inverse jacobian should be calculated by complicated coordinate transformations. These are required excessive computation and the singularity of the image jacobian should be considered. This paper presents a visual servoing to control the pose of the robotic manipulator for tracking and grasping 3-D moving object whose pose and motion parameters are unknown. Because the object is in motion tracking and grasping must be done on-line and the controller must have continuous learning ability. In order to estimate parameters of a moving object we use the kalman filter. And for tracking and grasping a moving object we use a fuzzy inference based reinforcement learning algorithm of dynamic recurrent neural networks. Computer simulation results are presented to demonstrate the performance of this visual servoing

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.581-586
• /
• 2003

This paper presents control designs using neural networks (NN) for a XY positioning table. The proposed neurocontroller is composed of an outer PD tracking loop for stabilization of the fast flexible-mode dynamics and an NN inner loop used to compensate for the system nonlinearities. A tuning algorithm is given for the NN weights, so that the NN compensation scheme becomes adaptive, guaranteeing small tracking errors and bounded weight estimates. Formal nonlinear stability proofs are given to show that the tracking error is small. The proposed neuro-controller is implemented and tested on an IBM PC-based XY positioning table, and is applicable to many precision XY tables. The algorithm, simulation, and experimental results are described. The experimental results are shown to be superior to those of conventional control.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.8
• /
• pp.647-655
• /
• 2001

In adaptive neuro-control, neural networks are used to approximate unknown plant nonlinearities. Until now, most of the studies in the field of controller design for nonlinear system using neural network considers the affine system with fixed number of neurons. This paper considers nonaffine nonlinear systems and on-line variation of the number of neurons. A control law and adaptive laws for neural network weights are established so that the whole system is stable in the sense of Lyapunov. In addition, at the expense of th input, tracking error converges to the arbitrary small neighborhood of the origin. The efficiency of the proposed scheme is shown through simulations ofa simple nonaffine nonlinear system.