Results 1  10
of
38
Deadzone Compensation in Motion Control Systems Using Neural Networks
, 2000
"... A compensation scheme is presented for general nonlinear actuator deadzones of unknown width. The compensator uses two neural networks (NN's), one to estimate the unknown deadzone and another to provide adaptive compensation in the feedforward path. The compensator NN has a special augmented fo ..."
Abstract

Cited by 22 (3 self)
 Add to MetaCart
A compensation scheme is presented for general nonlinear actuator deadzones of unknown width. The compensator uses two neural networks (NN's), one to estimate the unknown deadzone and another to provide adaptive compensation in the feedforward path. The compensator NN has a special augmented form containing extra neurons whose activation functions provide a "jump function basis set" for approximating piecewise continuous functions. Rigorous proofs of closedloop stability for the deadzone compensator are provided and yield tuning algorithms for the weights of the two NN's. The technique provides a general procedure for using NN's to determine the preinverse of an unknown rightinvertible function. I. INTRODUCTION A GENERAL class of industrial motion control systems has the structure of a dynamical system, usually of the Lagrangian form, preceded by some nonlinearities in the actuator, either deadzone, backlash, saturation, etc. [7]. This includespositioning tables [17], robot manip...
Reinforcement Learning NeuralNetworkBased Controller for Nonlinear DiscreteTime Systems With Input Constraints
"... Abstract—A novel adaptivecriticbased neural network (NN) controller in discrete time is designed to deliver a desired tracking performance for a class of nonlinear systems in the presence of actuator constraints. The constraints of the actuator are treated in the controller design as the saturatio ..."
Abstract

Cited by 18 (0 self)
 Add to MetaCart
(Show Context)
Abstract—A novel adaptivecriticbased neural network (NN) controller in discrete time is designed to deliver a desired tracking performance for a class of nonlinear systems in the presence of actuator constraints. The constraints of the actuator are treated in the controller design as the saturation nonlinearity. The adaptive critic NN controller architecture based on state feedback includes two NNs: the critic NN is used to approximate the “strategic” utility function, whereas the action NN is employed to minimize both the strategic utility function and the unknown nonlinear dynamic estimation errors. The critic and action NN weight updates are derived by minimizing certain quadratic performance indexes. Using the Lyapunov approach and with novel weight updates, the uniformly ultimate boundedness of the closedloop tracking error and weight estimates is shown in the presence of NN approximation errors and bounded unknown disturbances. The proposed NN controller works in the presence of multiple nonlinearities, unlike other schemes that normally approximate one nonlinearity. Moreover, the adaptive critic NN controller does not require an explicit offline training phase, and the NN weights can be initialized at zero or random. Simulation results justify the theoretical analysis. Index Terms—Approximate dynamic programming, neural network control, optimal control, reinforcement learning. I.
Incremental extreme learning machine with fully complex hidden nodes
, 2007
"... Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks 17(4) (2006) 879–892] has recently proposed an incremental extreme learning machine (IELM), which randomly adds hidden nodes incrementally and analytically ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks 17(4) (2006) 879–892] has recently proposed an incremental extreme learning machine (IELM), which randomly adds hidden nodes incrementally and analytically determines the output weights. Although hidden nodes are generated randomly, the network constructed by IELM remains as a universal approximator. This paper extends IELM from the real domain to the complex domain. We show that, as long as the hidden layer activation function is complex continuous discriminatory or complex bounded nonlinear piecewise continuous, IELM can still approximate any target functions in the complex domain. The universal capability of the IELM in the complex domain is further verified by two function approximations and one channel equalization problems.
Backlash Compensation In Nonlinear Systems Using Dynamic Inversion By Neural Networks
, 1999
"... 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 ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
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 closedloop system. 1 INTRODUCTION A general class of industrial motion control systems has the structure of a nonlinear dynamical system preceded by some nonlinearities in the actuator, either deadzone, backlash, saturation, etc. This includes xypositioning tables [19], robot manipulators [14], overhead crane mechanisms, and more. The problems are particularly exacerbated when the required accuracy is high, as in micropositioning devices. Due to the nonanalytic nature of the actuator nonlinearities and the fact that their exact nonlinear functions are unknown, such systems...
Agnostic Learning and Single Hidden Layer Neural Networks
, 1996
"... This thesis is concerned with some theoretical aspects of supervised learning of realvalued functions. We study a formal model of learning called agnostic learning. The agnostic learning model assumes a joint probability distribution on the observations (inputs and outputs) and requires the learnin ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
This thesis is concerned with some theoretical aspects of supervised learning of realvalued functions. We study a formal model of learning called agnostic learning. The agnostic learning model assumes a joint probability distribution on the observations (inputs and outputs) and requires the learning algorithm to produce an hypothesis with performance close to that of the best function within a specified class of functions. It is a very general model of learning which includes function learning, learning with additive noise and learning the best approximation in a class of functions as special cases. Within the agnostic learning model, we concentrate on learning functions which can be well approximated by single hidden layer neural networks. Artificial neural networks are often used as black box models for modelling phenomena for which very little prior knowledge is available. Agnostic learning is a natural model for such learning problems. The class of single hidden layer neural netwo...
Control of Nonaffine Nonlinear DiscreteTime Systems Using ReinforcementLearningBased Linearly Parameterized Neural Networks
"... Abstract—A nonaffine discretetime system represented by the nonlinear autoregressive moving average with eXogenous input (NARMAX) representation with unknown nonlinear system dynamics is considered. An equivalent affinelike representation in terms of the tracking error dynamics is first obtained fr ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
Abstract—A nonaffine discretetime system represented by the nonlinear autoregressive moving average with eXogenous input (NARMAX) representation with unknown nonlinear system dynamics is considered. An equivalent affinelike representation in terms of the tracking error dynamics is first obtained from the original nonaffine nonlinear discretetime system so that reinforcementlearningbased nearoptimal neural network (NN) controller can be developed. The control scheme consists of two linearly parameterized NNs. One NN is designated as the critic NN, which approximates a predefined longterm cost function, and an action NN is employed to derive a nearoptimal control signal for the system to track a desired trajectory while minimizing the cost function simultaneously. The NN weights are tuned online. By using the standard Lyapunov approach, the stability of the closedloop system is shown. The net result is a supervised actorcritic NN controller scheme which can be applied to a general nonaffine nonlinear discretetime system without needing the affinelike representation. Simulation results demonstrate satisfactory performance of the controller. Index Terms—Adaptive critic, adaptive dynamic programming, Lyapunov stability, neural network control, reinforcement learning control. I.
Backlash Compensation with Filtered Prediction in Discrete Time Nonlinear Systems by Dynamic Inversion Using Neural Networks
 Journal of Control
, 1999
"... A dynamics inversion compensation scheme is designed for control of nonlinear discretetime systems with input backlash. This paper extends the dynamic inversion technique to discretetime systems by using a filtered prediction, and shows how to use a neural network (NN) for inverting the backlash no ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
A dynamics inversion compensation scheme is designed for control of nonlinear discretetime systems with input backlash. This paper extends the dynamic inversion technique to discretetime systems by using a filtered prediction, and shows how to use a neural network (NN) for inverting the backlash nonlinearity in the feedforward path. The technique provides a general procedure for using NN to determine the dynamics preinverse of an invertible discrete time dynamical system. A discretetime tuning algorithm is given for the NN weights so that the backlash compensation scheme guarantees bounded tracking and backlash errors, and also bounded parameter estimates. A rigorous proof of stability and performance is given and a simulation example verifies performance. Unlike standard discretetime adaptive control techniques, no certainty equivalence (CE) or linearinthe parameters (LIP) assumptions are needed. 1 Introduction Many physical components of control systems have nonsmooth nonlinea...
Design and Implementation of Industrial Neural Network Controller Using Backstepping
, 2001
"... In this paper a novel neural network (NN) backstepping controller is modified for application to an industrial motor drive system. A control system structure and NN tuning algorithms are presented that are shown to guarantee stability and performance of the closedloop system. The NN backstepping co ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
In this paper a novel neural network (NN) backstepping controller is modified for application to an industrial motor drive system. A control system structure and NN tuning algorithms are presented that are shown to guarantee stability and performance of the closedloop system. The NN backstepping controller is implemented on an actual motor drive system using a twoPC control system developed at UTA. The implementation results show that the NN backstepping controller is highly effective in controlling the industrial motor drive system. It is also shown that the NN controller gives better results on actual systems than a standard backstepping controller developed assuming full knowledge of the dynamics. Moreover, the NN controller does not require the linearintheparameters assumption or the computation of regression matrices required by standard backstepping.
ThA18.4 Reinforcement Learningbased Output Feedback Control of Nonlinear Systems with Input Constraints
"... feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multiinputmultiautput (MIMO) discretetime strict feedback nonlinear systems. Reinforcement learning in discrete time is proposed for the output feedback controller, which uses three ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
(Show Context)
feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multiinputmultiautput (MIMO) discretetime strict feedback nonlinear systems. Reinforcement learning in discrete time is proposed for the output feedback controller, which uses three NNs: 1) a NN observer to estimate the system states with the inputoutput data; 2) a critic NN to approximate certain strategic utility function; and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. The magnitude constraints are manifested as saturation nonlinearities in the output feedback controller design. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the state estimation errors, the tracking errors and weight estimates is shown. I.