Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity

Maolong Lv; Ying Wang; Simone Baldi; Zongcheng Liu; Chao Shi; Chaoqi Fu; Xiangfei Meng; Yao Qi

doi:10.1007/978-3-319-70136-3_22

Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity

Maolong Lv^*, Ying Wang, Simone Baldi, Zongcheng Liu, Chao Shi, Chaoqi Fu, Xiangfei Meng, Yao Qi

^*Corresponding author for this work

Team Bart De Schutter

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

4 Citations (Scopus)

Abstract

For the pure feedback systems with uncertain actuator nonlinearity and non-differentiable non-affine function, a novel adaptive neural control scheme is proposed. Firstly, the assumption that the non-affine function must be differentiable everywhere with respect to control input has been canceled; in addition, the proposed approach can not only be applicable to actuator input dead zone nonlinearity, but also to backlash nonlinearity without changing the controller. Secondly, the neural network (NN) is used to approximate unknown nonlinear functions of system generated in the process of control design and a nonlinear robust term is introduced to eliminate the actuator nonlinearity modeling error, the NN approximation error and the external disturbances. Semi-globally uniformly ultimately boundedness of all signals in the closed loop system is analytically proved by utilizing Lyapunov theory. Finally, the effectiveness of the designed method is demonstrated via two examples.

Original language	English
Title of host publication	Neural Information Processing
Subtitle of host publication	Proceedings of the 24th International Conference (ICONIP 2017)
Editors	Derong Liu, Shengli Xie, Yuanqing Li, Dongbin Zhao, El-Sayed M. El-Alfy
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	201-211
ISBN (Electronic)	978-3-319-70136-3
ISBN (Print)	978-3-319-70135-6
DOIs	https://doi.org/10.1007/978-3-319-70136-3_22
Publication status	Published - 2017
Event	ICONIP 2017: 24th International Conference on Neural Information Processing - Guangzhou, China Duration: 14 Nov 2017 → 18 Nov 2017

Publication series

Name	Lecture Notes in Computer Science
Volume	10639
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	ICONIP 2017: 24th International Conference on Neural Information Processing
Country/Territory	China
City	Guangzhou
Period	14/11/17 → 18/11/17

Keywords

Actuator input nonlinearity
Adaptive neural control
Non-affine function
Robust control

Access to Document

10.1007/978-3-319-70136-3_22

Cite this

Lv, M., Wang, Y., Baldi, S., Liu, Z., Shi, C., Fu, C., Meng, X., & Qi, Y. (2017). Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity. In D. Liu, S. Xie, Y. Li, D. Zhao, & E.-S. M. El-Alfy (Eds.), Neural Information Processing: Proceedings of the 24th International Conference (ICONIP 2017) (pp. 201-211). (Lecture Notes in Computer Science ; Vol. 10639). Springer. https://doi.org/10.1007/978-3-319-70136-3_22

Lv, Maolong ; Wang, Ying ; Baldi, Simone et al. / Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity. Neural Information Processing: Proceedings of the 24th International Conference (ICONIP 2017). editor / Derong Liu ; Shengli Xie ; Yuanqing Li ; Dongbin Zhao ; El-Sayed M. El-Alfy. Cham, Switzerland : Springer, 2017. pp. 201-211 (Lecture Notes in Computer Science ).

@inproceedings{6796824f65a7421b8fe5383fe24f1f18,

title = "Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity",

abstract = "For the pure feedback systems with uncertain actuator nonlinearity and non-differentiable non-affine function, a novel adaptive neural control scheme is proposed. Firstly, the assumption that the non-affine function must be differentiable everywhere with respect to control input has been canceled; in addition, the proposed approach can not only be applicable to actuator input dead zone nonlinearity, but also to backlash nonlinearity without changing the controller. Secondly, the neural network (NN) is used to approximate unknown nonlinear functions of system generated in the process of control design and a nonlinear robust term is introduced to eliminate the actuator nonlinearity modeling error, the NN approximation error and the external disturbances. Semi-globally uniformly ultimately boundedness of all signals in the closed loop system is analytically proved by utilizing Lyapunov theory. Finally, the effectiveness of the designed method is demonstrated via two examples.",

keywords = "Actuator input nonlinearity, Adaptive neural control, Non-affine function, Robust control",

author = "Maolong Lv and Ying Wang and Simone Baldi and Zongcheng Liu and Chao Shi and Chaoqi Fu and Xiangfei Meng and Yao Qi",

year = "2017",

doi = "10.1007/978-3-319-70136-3_22",

language = "English",

isbn = "978-3-319-70135-6",

series = "Lecture Notes in Computer Science ",

publisher = "Springer",

pages = "201--211",

editor = "Derong Liu and Shengli Xie and Li, {Yuanqing } and Zhao, {Dongbin } and El-Alfy, {El-Sayed M. }",

booktitle = "Neural Information Processing",

note = "ICONIP 2017: 24th International Conference on Neural Information Processing ; Conference date: 14-11-2017 Through 18-11-2017",

}

Lv, M, Wang, Y, Baldi, S, Liu, Z, Shi, C, Fu, C, Meng, X & Qi, Y 2017, Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity. in D Liu, S Xie, Y Li, D Zhao & E-SM El-Alfy (eds), Neural Information Processing: Proceedings of the 24th International Conference (ICONIP 2017). Lecture Notes in Computer Science , vol. 10639, Springer, Cham, Switzerland, pp. 201-211, ICONIP 2017: 24th International Conference on Neural Information Processing, Guangzhou, China, 14/11/17. https://doi.org/10.1007/978-3-319-70136-3_22

Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity. / Lv, Maolong; Wang, Ying; Baldi, Simone et al.
Neural Information Processing: Proceedings of the 24th International Conference (ICONIP 2017). ed. / Derong Liu; Shengli Xie; Yuanqing Li; Dongbin Zhao; El-Sayed M. El-Alfy. Cham, Switzerland: Springer, 2017. p. 201-211 (Lecture Notes in Computer Science ; Vol. 10639).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity

AU - Lv, Maolong

AU - Wang, Ying

AU - Baldi, Simone

AU - Liu, Zongcheng

AU - Shi, Chao

AU - Fu, Chaoqi

AU - Meng, Xiangfei

AU - Qi, Yao

PY - 2017

Y1 - 2017

N2 - For the pure feedback systems with uncertain actuator nonlinearity and non-differentiable non-affine function, a novel adaptive neural control scheme is proposed. Firstly, the assumption that the non-affine function must be differentiable everywhere with respect to control input has been canceled; in addition, the proposed approach can not only be applicable to actuator input dead zone nonlinearity, but also to backlash nonlinearity without changing the controller. Secondly, the neural network (NN) is used to approximate unknown nonlinear functions of system generated in the process of control design and a nonlinear robust term is introduced to eliminate the actuator nonlinearity modeling error, the NN approximation error and the external disturbances. Semi-globally uniformly ultimately boundedness of all signals in the closed loop system is analytically proved by utilizing Lyapunov theory. Finally, the effectiveness of the designed method is demonstrated via two examples.

AB - For the pure feedback systems with uncertain actuator nonlinearity and non-differentiable non-affine function, a novel adaptive neural control scheme is proposed. Firstly, the assumption that the non-affine function must be differentiable everywhere with respect to control input has been canceled; in addition, the proposed approach can not only be applicable to actuator input dead zone nonlinearity, but also to backlash nonlinearity without changing the controller. Secondly, the neural network (NN) is used to approximate unknown nonlinear functions of system generated in the process of control design and a nonlinear robust term is introduced to eliminate the actuator nonlinearity modeling error, the NN approximation error and the external disturbances. Semi-globally uniformly ultimately boundedness of all signals in the closed loop system is analytically proved by utilizing Lyapunov theory. Finally, the effectiveness of the designed method is demonstrated via two examples.

KW - Actuator input nonlinearity

KW - Adaptive neural control

KW - Non-affine function

KW - Robust control

UR - http://www.scopus.com/inward/record.url?scp=85035125695&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-70136-3_22

DO - 10.1007/978-3-319-70136-3_22

M3 - Conference contribution

AN - SCOPUS:85035125695

SN - 978-3-319-70135-6

T3 - Lecture Notes in Computer Science

SP - 201

EP - 211

BT - Neural Information Processing

A2 - Liu, Derong

A2 - Xie, Shengli

A2 - Li, Yuanqing

A2 - Zhao, Dongbin

A2 - El-Alfy, El-Sayed M.

PB - Springer

CY - Cham, Switzerland

T2 - ICONIP 2017: 24th International Conference on Neural Information Processing

Y2 - 14 November 2017 through 18 November 2017

ER -

Lv M, Wang Y, Baldi S, Liu Z, Shi C, Fu C et al. Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity. In Liu D, Xie S, Li Y, Zhao D, El-Alfy ESM, editors, Neural Information Processing: Proceedings of the 24th International Conference (ICONIP 2017). Cham, Switzerland: Springer. 2017. p. 201-211. (Lecture Notes in Computer Science ). doi: 10.1007/978-3-319-70136-3_22

Adaptive neural control for pure feedback nonlinear systems with uncertain actuator nonlinearity

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this