Adaptive identification and prediction control for time delay nonlinear systems based on neural networks

Jing Na; Xuemei Ren

Adaptive identification and prediction control for time delay nonlinear systems based on neural networks

Jing Na^*, Xuemei Ren

^*Corresponding author for this work

Department of Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

This paper presents the identification, prediction and control design for nonlinear strict-feedback systems with an input time-delay. The system is firstly transformed into a normal form by defining new state variables. A dynamical identification with a neural network (NN) is proposed to estimate the system states. The predictive NN weights are obtained without iterative calculations and utilized in constructing the adaptive predictor. Feedback control design using the predictive states is finally studied. Simulations are included to validate the effectiveness of the proposed method.

Original language	English
Title of host publication	Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10
Pages	685-688
Number of pages	4
Publication status	Published - 1 Dec 2010
Event	15th International Symposium on Artificial Life and Robotics, AROB '10 - Beppu, Oita, United Kingdom Duration: 4 Feb 2010 → 6 Feb 2010

Conference

Conference	15th International Symposium on Artificial Life and Robotics, AROB '10
Country/Territory	United Kingdom
City	Beppu, Oita
Period	4/02/10 → 6/02/10

Keywords

Neural networks
Nonlinear predictor
State observer
Time-delay systems

Handle.net

Persistent link

Cite this

@inproceedings{37fc81fc563f47478bd4d4983e837147,

title = "Adaptive identification and prediction control for time delay nonlinear systems based on neural networks",

abstract = "This paper presents the identification, prediction and control design for nonlinear strict-feedback systems with an input time-delay. The system is firstly transformed into a normal form by defining new state variables. A dynamical identification with a neural network (NN) is proposed to estimate the system states. The predictive NN weights are obtained without iterative calculations and utilized in constructing the adaptive predictor. Feedback control design using the predictive states is finally studied. Simulations are included to validate the effectiveness of the proposed method.",

keywords = "Neural networks, Nonlinear predictor, State observer, Time-delay systems",

author = "Jing Na and Xuemei Ren",

year = "2010",

month = dec,

day = "1",

language = "English",

isbn = "9784990288044",

pages = "685--688",

booktitle = "Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10",

note = "15th International Symposium on Artificial Life and Robotics, AROB '10 ; Conference date: 04-02-2010 Through 06-02-2010",

}

TY - GEN

T1 - Adaptive identification and prediction control for time delay nonlinear systems based on neural networks

AU - Na, Jing

AU - Ren, Xuemei

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents the identification, prediction and control design for nonlinear strict-feedback systems with an input time-delay. The system is firstly transformed into a normal form by defining new state variables. A dynamical identification with a neural network (NN) is proposed to estimate the system states. The predictive NN weights are obtained without iterative calculations and utilized in constructing the adaptive predictor. Feedback control design using the predictive states is finally studied. Simulations are included to validate the effectiveness of the proposed method.

AB - This paper presents the identification, prediction and control design for nonlinear strict-feedback systems with an input time-delay. The system is firstly transformed into a normal form by defining new state variables. A dynamical identification with a neural network (NN) is proposed to estimate the system states. The predictive NN weights are obtained without iterative calculations and utilized in constructing the adaptive predictor. Feedback control design using the predictive states is finally studied. Simulations are included to validate the effectiveness of the proposed method.

KW - Neural networks

KW - Nonlinear predictor

KW - State observer

KW - Time-delay systems

UR - http://www.scopus.com/inward/record.url?scp=84866640348&partnerID=8YFLogxK

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:84866640348

SN - 9784990288044

SP - 685

EP - 688

BT - Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10

T2 - 15th International Symposium on Artificial Life and Robotics, AROB '10

Y2 - 4 February 2010 through 6 February 2010

ER -

Adaptive identification and prediction control for time delay nonlinear systems based on neural networks

Abstract

Conference

Keywords

Handle.net

Other files and links

Fingerprint

Cite this