A novel neural network-based adaptive control for a class of uncertain nonlinear systems in strict-feedback form

Miao, Baobin; Li, Tieshan

doi:10.1007/s11071-014-1717-2

Cited by 37 publications

(24 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…이러한 비선형 불확실성 문제를 해결하기 위해 신경 회로망(neural network) 또는 퍼지 논리 시 스템(fuzzy logic system)을 이용한 함수 근사화 기반 제어 기법 들이 연구되었다 [1][2]. 이러한 기법들에서 외부의 시변 외란은 적응 제어 방식을 통하여 외란의 유계치를 추정하거나 [3], 르아 브노브 안정도 증명과정에서 균일 궁극 유계(uniform ultimate bounds) 분석을 통해 유계치로 간주되었다 [4]. 따라서 보다 시변 외란의 효율적인 보상을 위해 외란 관측기 이용한 방법들이 다양 한 비선형 시스템에 적용되고 있다 [5].…”

Section: 서 론 불확실성을 갖는 비선형 시스템을 위한 제어이론은 다양한 기 계 전기 시스템 등의 응용 분야에 적용되unclassified

Neural-networks-based Disturbance Observer and Tracker Design in the Presence of Unknown Control Direction and Non-affine Nonlinearities

Kim¹,

Yoo²

2017

The Transactions of The Korean Institute of Electrical Engineer

View full text Add to dashboard Cite

-A disturbance-observer-based adaptive neural tracker design problem is investigated for a class of perturbed uncertain non-affine nonlinear systems with unknown control direction. A nonlinear disturbance observer (NDO) design methodology using neural networks is presented to construct a tracking control scheme with the attenuation effect of an external disturbance. Compared with previous control results using NDO for nonlinear systems in non-affine form, the major contribution of this paper is to design a NDO-based adaptive tracker without the sign information of the control coefficient. The stability of the closed-loop system is analyzed in the sense of Lyapunov stability.

show abstract

Section: 서 론 불확실성을 갖는 비선형 시스템을 위한 제어이론은 다양한 기 계 전기 시스템 등의 응용 분야에 적용되unclassified

Neural-networks-based Disturbance Observer and Tracker Design in the Presence of Unknown Control Direction and Non-affine Nonlinearities

Kim¹,

Yoo²

2017

The Transactions of The Korean Institute of Electrical Engineer

View full text Add to dashboard Cite

show abstract

“…Compared with the existing controls in [2,8,10,11,40,62], the adaptive fuzzy control laws presented in [47][48][49] have solved the tracking problem for nonlinear uncertain discrete-time systems with unknown control direction and input nonlinearities (such as dead zone, backlash-like hysteresis, and backlash), by using the reinforcement learning algorithm. • Uncertainty: In most practical situations, the systems under control are unknown or partially unknown [4,7,12,13,17,19,22,31,42,56,57,61]. These facts require specific control tools to deal with the controller design process, being one of the most extended ones the adaptive control paradigm.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, the SPR condition, the Razumikhin Lemma, the frequency-distributed model, and the Lyapunov method are adopted for deriving the parameter adaptive laws. The main contribution of this manuscript lies in the following: (1) compared with the existing works [1, 2, 5-14, 16-34, 63], the considered class of systems is relatively large; (2) unlike [6,7,9,[23][24][25][26][31][32][33][34], the proposed design approach does not require a priori knowledge of the signs of control gains nor any information of the bound of input saturation; (3) in contrast to the adaptive control schemes [1-26, 31-34, 63], the number of adjustable parameters is reduced; (4) our work can handle systems with both constant and distributed time-varying delays; (5) all signals of the closedloop system are bounded; and (6) unlike the closely related works [1,4,63], the tracking errors converge asymptotically to zero.…”

Section: Introductionmentioning

confidence: 99%

Observer-based adaptive neural network control for a class of MIMO uncertain nonlinear time-delay non-integer-order systems with asymmetric actuator saturation

Zouari

Boulkroune

Ibeas

et al. 2016

Neural Comput & Applic

View full text Add to dashboard Cite

This paper focuses on the adaptive neural output feedback control of a class of uncertain multi-input-multioutput nonlinear time-delay non-integer-order systems with unmeasured states, unknown control direction, and unknown asymmetric saturation actuator. Thus, the mean value theorem and a Gaussian error function-based continuous differentiable model are used in the paper to describe the unknown asymmetric saturation actuator and to get an affine model in which the control input appears in a linear fashion, respectively. The design of the controller follows a number of steps. Firstly, based on the semigroup property of fractional-order derivative, the system is transformed into a normalized fractional-order system by means of a state transformation in order to facilitate the control design. Then, a simple linear state observer is constructed to estimate the unmeasured states of the transformed system. A neural network is incorporated to approximate the unknown nonlinear functions while a Nussbaum function is used to deal with the unknown control direction. In addition, the strictly positive real condition, the Razumikhin Lemma, the frequency-distributed model, and the Lyapunov method are utilized to derive the parameter adaptive laws and to perform the stability proof. The main advantages of this work are that:(1) it can handle systems with constant, time-varying, and distributed time-varying delays, (2) the considered class of systems is relatively large, (3) the number of adjustable parameters is reduced, (4) the tracking errors converge asymptotically to zero and all signals of the closed-loop system are bounded. Finally, some simulation examples are provided to demonstrate the validity and effectiveness of the proposed scheme.

show abstract

“…[1][2][3][4][5][6][7][8][9][10][11][12] For example, Sarma et al [4] propose an approach combined with ANN to make out primal phonemes of Assamese language. RBF neural network is employed as an accessorial method to weaken the impact of nonlinearity and uncertainty on the nonlinear system.…”

Section: Introductionmentioning

confidence: 99%

“…RBF neural network is employed as an accessorial method to weaken the impact of nonlinearity and uncertainty on the nonlinear system. [5] Generally, according to structures, neural network (NN) can be categorized into two types, i.e., feed-forward neural network (FNN) [1,2,10,13,14] and recurrent neural network (RNN). [6,9,11,[15][16][17][18]20] We know that FNN can only represent static mappings and its approximation performance is easily influenced by training data because the scheme of weights update does not depend on internal network information.…”

Section: Introductionmentioning

confidence: 99%

Adaptive control for uncertain discrete-time systems with unknown disturbance based on RNN

Cui

Guo

Feng

et al. 2016

AIR

View full text Add to dashboard Cite

A new robust adaptive control algorithm is developed for a class of uncertain discrete-time SISO systems. Different from the existing investigated systems, the concerned discrete system here is with both uncertain smooth nonlinear functions and unknown disturbance. On the basis of the idea of neural network (NN) approximation, a novel recurrent neural network (RNN) is first proposed and used to approximate a backstepping control law following the transformation of the original system into a predictor form. According to Lyapunov stability theorem, a new on-line tuning law for parameters of RNN is obtained. Meanwhile, in order to achieve satisfying robust tracking performance, a novel controller is constructed by virtue of the approximation error of RNN. It has been proved that all the concerned signals are uniformly ultimately bounded. In addition, a very small tracking error can be obtained through appropriate selection of control parameters. Finally, we give a simulation example to demonstrate the validness of the newly proposed control algorithm for the investigated systems.

show abstract

A novel neural network-based adaptive control for a class of uncertain nonlinear systems in strict-feedback form

Cited by 37 publications

References 38 publications

Neural-networks-based Disturbance Observer and Tracker Design in the Presence of Unknown Control Direction and Non-affine Nonlinearities

Neural-networks-based Disturbance Observer and Tracker Design in the Presence of Unknown Control Direction and Non-affine Nonlinearities

Observer-based adaptive neural network control for a class of MIMO uncertain nonlinear time-delay non-integer-order systems with asymmetric actuator saturation

Adaptive control for uncertain discrete-time systems with unknown disturbance based on RNN

Contact Info

Product

Resources

About