Adaptive recurrent neural network control using a structure adaptation algorithm

Hsu, Chun‐Fei

doi:10.1007/s00521-007-0164-0

Cited by 17 publications

(14 citation statements)

References 25 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[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. However, RNN can memorize the past knowledge in virtue of its delay feedback loops.…”

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

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

show abstract

“…During the past few years, neural-network-based feedback control technique has attracted increasing attentions, because it has provided an efficient and effective way for controlling the complex nonlinear or ill-defined systems [1][2][3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

“…Hence, the parameterized NNs can approximate any unknown system dynamics or the ideal tracking controller with arbitrary degree of accuracy after learning. Moreover, according to the structure, NNs can be mainly classified as feedforward neural networks (FNNs) [1][2][3][4][5] and recurrent neural networks (RNNs) [6][7][8][9]. As known, FNNs represent a static mapping network.…”

Section: Introductionmentioning

confidence: 99%

Recurrent wavelet neural backstepping controller design with a smooth compensator

Chen

Hsu

2010

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Recurrent wavelet neural network (RWNN) has the advantages in its dynamic responses and information storing ability. This paper develops a recurrent wavelet neural backstepping control (RWNBC) scheme for multiple-input multiple-output (MIMO) mechanical systems. This proposed RWNBC comprises a neural controller and a smooth compensator. The neural controller using an RWNN is the principal tracking controller utilized to mimic an ideal backstepping control law; and the parameters of RWNN are online tuned by the derived adaptation laws from the Lyapunov stability theorem. The smooth compensator is designed to dispel the approximation error introduced by the neural controller, so that the asymptotic stability of the closed-loop system can be guaranteed. Finally, two MIMO mechanical systems, a mass-springdamper system and a two-inverted pendulum system, are performed to verify the effectiveness of the proposed RWNBC scheme. From the simulation results, it is verified that the proposed RWNBC scheme can achieve favorable tracking performance without any chattering phenomenon.

show abstract

“…Due to the excellent learning capabilities and parallel processing structures, the applications of the neural networks (NNs) for identification and control of dynamic systems have received a considerable attention over the several years [1][2][3][4][5][6][7][8][9][10]. Some significant results indicate the main property of NNs is adaptive learning so that it can uniformly approximate arbitrary input-output linear or nonlinear mappings on closed subsets.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-based adaptive robust control for a class of MIMO uncertain nonlinear systems

Chen

2010

Neural Comput & Applic

View full text Add to dashboard Cite

In this study, a wavelet neural network (WNN)-based adaptive robust control (WARC) strategy is investigated to resolve the tracking control problem of a class of multi-input multi-output (MIMO) uncertain nonlinear systems. The proposed control system comprises of an adaptive wavelet controller and a robust controller. The adaptive wavelet controller acts as the main tracking controller, which is designed via a WNN to mimic the merits of a feedback linearization control (FLC) law. The proportional-integral (PI) adaptation laws of the MIMO control system are derived from the Lyapunov stability theorem, which are utilized to update the adjustable parameters of WNN on-line for further assuring system stability and obtaining a fast convergence. Moreover, based on H ? control technique, the robust controller is developed to attenuate the effect of the approximation error caused by WNN approximator, so that the desired tracking performance can be achieved. Finally, two MIMO uncertain nonlinear systems, the ecological system and the unified chaotic system, are performed to verify the effectiveness and robustness of the proposed WARC strategy. Furthermore, the salient merits are also indicated in comparison with the FLC system.

show abstract

Adaptive recurrent neural network control using a structure adaptation algorithm

Cited by 17 publications

References 25 publications

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

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

Recurrent wavelet neural backstepping controller design with a smooth compensator

Wavelet-based adaptive robust control for a class of MIMO uncertain nonlinear systems

Contact Info

Product

Resources

About