BACKLASH COMPENSATION IN NONLINEAR SYSTEMS USING DYNAMIC INVERSION BY NEURAL NETWORKS
Asian Journal of ControlPublished 1 June 2000
Rastko R. Šelmić, Frank L. Lewis
Citations43
SJR quartileQ2
SJR score0.64
SNIP0.94
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
ABSTRACT A dynamic inversion compensation scheme is presented for backlash. The compensator uses the backstepping technique with neural networks (NN) for inverting the backlash nonlinearity in the feedforward path. The technique provides a general procedure for using NN to determine the dynamic preinverse of an invertible dynamical system. A tuning algorithm is presented for the NN backlash compensator which yields a stable closed‐loop system.
Keywords
EngineeringPhysics and Astronomy
CERN Document Server (European Organization for Nuclear Research)Applied Nonlinear Control
18,983 Citations1991Jean-Jacques Slotine, Weiping Li
Covers in a progressive fashion a number of analysis tools and design techniques directly applicable to nonlinear control problems in high performance systems (in aerospace, robotics and automotive areas).
Mathematics of Control Signals and SystemsApproximation by superpositions of a sigmoidal function
13,684 Citations1989George Cybenko
Nonlinear and adaptive control design
10,450 Citations1995Miroslav Krstić, P.V. Kokotović +1 more
Using a pedagogical style along with detailed proofs and illustrative examples, this book opens a view to the largely unexplored area of nonlinear systems with uncertainties--adaptive backstepping.
IEEE Transactions on Neural NetworksIdentification and control of dynamical systems using neural networks
8,008 Citations1990Kumpati S. Narendra, K. Parthasarathy
It is demonstrated that neural networks can be used effectively for the identification and control of nonlinear dynamical systems and the models introduced are practically feasible.
IEEE Transactions on Information TheoryUniversal approximation bounds for superpositions of a sigmoidal function
2,849 Citations1993Andrew R. Barron
The approximation rate and the parsimony of the parameterization of the networks are shown to be advantageous in high-dimensional settings and the integrated squared approximation error cannot be made smaller than order 1/n/sup 2/d/ uniformly for functions satisfying the same smoothness assumption.
The International Journal of Robotics ResearchOn the Adaptive Control of Robot Manipulators
2,259 Citations1987Jean-Jacques Slotine, Weiping Li
Neural Network Control Of Robot Manipulators And Non-Linear Systems
1,846 Citations2020Frank L. Lewis, Suresh Jagannathan +1 more
This graduate text provides an authoritative account of neural network (NN) controllers for robotics and nonlinear systems and gives the first textbook treatment of a general and streamlined design procedure for NN controllers.
IEEE Transactions on Automatic ControlContinuous state feedback guaranteeing uniform ultimate boundedness for uncertain dynamic systems
1,631 Citations1981M. Corless, G. Leitmann
IEEE Transactions on Automatic ControlStable adaptive neural control scheme for nonlinear systems
1,485 Citations1996Marios M. Polycarpou
A design methodology is developed that expands the class of nonlinear systems that adaptive neural control schemes can be applied to and relaxes some of the restrictive assumptions that are usually made.
Medical Entomology and ZoologyControl of Robot Manipulators
1,259 Citations1993Frank L. Lewis, D.M. Dawson +1 more
IEEE Transactions on Neural NetworksMultilayer neural-net robot controller with guaranteed tracking performance
1,099 Citations1996Frank L. Lewis, Aydın Yeşildirek +1 more
A multilayer neural-net (NN) controller for a general serial-link rigid robot arm is developed using a filtered error/passivity approach and novel online weight tuning algorithms guarantee bounded tracking errors as well as bounded NN weights.
IEEE Transactions on Neural NetworksStochastic choice of basis functions in adaptive function approximation and the functional-link net
957 Citations1995B. Igelnik, Yoh‐Han Pao
A theoretical justification for the random vector version of the functional-link (RVFL) net is presented, based on a general approach to adaptive function approximation, which results are that the RVFL is a universal approximator for continuous functions on bounded finite dimensional sets.
IEEE Transactions on Automatic ControlA new adaptive law for robust adaptation without persistent excitation
825 Citations1987Kumpati S. Narendra, Anuradha M. Annaswamy
Swarthmore College Works (Swarthmore College Libraries)The Elements of Real Analysis
685 Citations1964Robert G. Bartle
Adaptive Control of Systems with Actuator and Sensor Nonlinearities
633 Citations1996Gang Tao, P.V. Kokotović
An in-depth examination of intelligent approaches to increasing the accuracy of a variety of system components using electrical, mechanical, chemical, aeronautical and computer engineers methods for controlling many of the "hard" nonlinearities of frequently-employed control systems.
Journal of Guidance Control and DynamicsNonlinear Flight Control Using Neural Networks
591 Citations1997Byoung S. Kim, Anthony Calise
The theoretical development of a direct adaptive tracking control architecture using neural networks based on feedback linearization of the aircraft dynamics is presented and a stable weights adjustment rule for the on-line neural network is derived.
IEEE Transactions on Automatic ControlAdaptive control of plants with unknown dead-zones
467 Citations1994Gang Tao, P.V. Kokotović
IEEE Transactions on Systems Man and CyberneticsAdaptive control of unknown plants using dynamical neural networks
424 Citations1994George A. Rovithakis, M.A. Christodoulou
The algorithm is divided into two phases, a dynamical neural network identifier is employed to perform "black box" identification and then a dynamic state feedback is developed to appropriately control the unknown system.
International Journal of ControlAdaptive control of nonlinear systems using neural networks
382 Citations1992Fu-Chuang Chen, Hassan K. Khalil
Deadzone compensation in motion control systems using neural networks
327 Citations2002Rastko R. Šelmić, Frank L. Lewis
The technique provides a general procedure for using NN to determine the pre-inverse of an unknown right-invertible function.
IEEE Transactions on Neural NetworksA perceptron network for functional identification and control of nonlinear systems
286 Citations1993Nader Sadegh
A novel discrete-time control strategy is introduced that employs the PNN for direct online estimation of the required feedforward control input.
IEEE Transactions on Neural NetworksFeedback stabilization using two-hidden-layer nets
204 Citations1992Eduardo D. Sontag
It is shown that, contrary to what might have been expected from the well-known representation theorems, three-layer nets are not sufficient for stabilization, but four-layernets are enough, assuming that threshold processors are used.
Adaptive nonlinear control of systems containing a deadzone
192 Citations2002Darrel Recker, P.V. Kokotović +2 more
Journal of Guidance Control and DynamicsAnalysis of Adaptive Neural Networks for Helicopter Flight Control
179 Citations1997Jesse Leitner, Anthony Calise +1 more
It is shown that the performance varies gracefully and monotonically improves as the adaptation gain parameter is increased, and the effect on control effort is modest and is mainly perceptible only during a short training episode that can be associated with transition from hover to forward.
IEEE Transactions on Automatic ControlContinuous-time adaptive control of systems with unknown backlash
158 Citations1995Gang Tao, P.V. Kokotović
IEEE Transactions on Neural NetworksRobust neural-network control of rigid-link electrically driven robots
148 Citations1998Chiman Kwan, Frank L. Lewis +1 more
A robust neural-network (NN) controller is proposed for the motion control of rigid-link electrically driven (RLED) robots that can be regarded as a universal reusable controller because the same controller can be applied to any type of RLED robots without any modifications.
Neural network approximation of piecewise continuous functions: application to friction compensation
139 Citations2002Rastko R. Šelmić, Frank L. Lewis
A new neural network structure is given for approximation of piecewise continuous functions of the sort that appear in friction, deadzone, backlash and other motion control actuator nonlinearities, which is ideal for motion control applications in robotics and other industrial systems.
IEEE Transactions on Industrial ElectronicsA two-layered fuzzy logic controller for systems with deadzones
129 Citations1994Jong-Hwan Kim, Jong-Hwan Park +2 more
A novel two-layered fuzzy logic controller for controlling systems with deadzones that exhibits superior transient and steady-state performance compared to usual fuzzy PD controllers and is robust to variations in deadzone nonlinearities.
Stable adaptive control and recursive identification using radial Gaussian networks
117 Citations2002R.M. Sanner, J.-J.E. Slotine
The original adaptive control algorithm is modified to permit incorporation of additional prior knowledge of the system dynamics, allowing the neurocontroller to operate in parallel with conventional fixed or adaptive controllers.
IEEE Transactions on Control Systems TechnologyAdaptive nonlinear control of agile antiair missiles using neural networks
107 Citations2000Michael McFarland, Anthony Calise
A control scheme based on approximate inversion of the vehicle dynamics is presented, and this nonlinear control system is augmented by the addition of a feedforward neural network with online learning, thus assuring the stability of the closed-loop system.
International Journal of ControlStability of dithered non-linear systems with backlash or hysteresis†
98 Citations1986C. Desoer, S.M. Shahruz
The stability of the dithered system and an approximate equivalent system (in which the non-linearity is a smooth function) are compared and conditions on the input and on the dither frequency are obtained so that the approximate-system stability guarantees that of the given hysteretic system.
Birkhäuser Boston eBooksNeural Networks for Control
92 Citations1993Eduardo D. Sontag
This paper starts by placing neural net techniques in a general nonlinear control framework, and several basic theoretical results on networks are surveyed.
IEEE Transactions on Control Systems TechnologyAdaptive high-precision control of positioning tables-theory and experiments
88 Citations1994Weiping Li, Cheng Xu
The development and experimentation of a new adaptive controller for precise table motion control is described and the global stability of the controller and global convergence of tracking errors are proven using Lyapunov stability theory under mild conditions.
IEEE Transactions on Neural NetworksGuest Editorial Neural Networks Council Awards
34 Citations1996M.H. Hassoun
IEEE Transactions on Industrial ElectronicsNeural network control for DC motor micromaneuvering
34 Citations1995Anthony Tzes, Pei-Yuan Peng +1 more
The application of a neural network controller for compensating the effects induced by the friction in a DC motor micromaneuvering system is considered and the effect of the number of neurons in the input and hidden layers on the transient system response is explored.
IEEE Transactions on Automatic ControlControl of a class of nonlinear uncertain systems via compensated inverse dynamics approach
27 Citations1994Y.D. Song, T.L. Mitchell +1 more
The tracking control problem of a class of nonlinear systems via inverse dynamics method is addressed and a compensated inverse dynamics approach is proposed to account for the effect of uncertainties.
Control of systems with deadzones using neural-network based learning controller
26 Citations2002Seon‐Woo Lee, Jong-Hwan Kim
This paper presents a neural-network based learning controller for systems having a non-smooth nonlinearity with unknown parameters, specifically, a deadzone.
IEEE Transactions on Circuits and Systems I Fundamental Theory and ApplicationsCriteria for the approximation of nonlinear systems
25 Citations1992Jihun Park, Irwin W. Sandberg
Results are given that, for a certain broad class of system approximation problems, conditions introduced earlier and certain variations of other conditions are all equivalent, and are in fact necessary as well as sufficient.
Journal of Robotic SystemsRobot learning control based on recurrent neural network inverse model
22 Citations1997Lilai Yan, C. James Li
A non-linear model based feedforward and feedback controller for a robot arm that can learn the inverse dynamics of a robot, perform an accurate tracking for a general trajectory, and improve its own performance over the repetitions of a trajectory is described.
Deadzone compensation in nonlinear systems using neural networks
21 Citations2002Rastko R. Šelmić, Frank L. Lewis
The technique provides a general procedure for using NN to determine the pre-inverse of an unknown right-invertible function.
Circuits Systems and Signal ProcessingNonlinear approximations using elliptic basis function networks
20 Citations1994Jooyoung Park, Irwin W. Sandberg