Neural PD control with second-order sliding mode compensation for robot manipulators

Debbie Hernandez, Wen Yu, Marco A. Moreno-Armendariz

Research output: Contribution to conferencePaperResearch

6 Citations (Scopus)

Abstract

Both neural network and sliding mode technique can compensate the steady-state error of proportional-derivative (PD) control. The tracking error of PD control with sliding mode is asymptotically stable, but the chattering is big. PD control with neural networks is smooth, but it is not asymptotically stable. PD control combining both neural networks and sliding mode cannot reduce chattering, because the sliding mode control (SMC) is always applied. In this paper, neural control and SMC are connected serially: first a dead-zone neural PD control assures that the tracking error is bounded, then super-twisting second-order sliding-mode is used to guarantee finite time convergence of the sliding mode PD control. © 2011 IEEE.
Original languageAmerican English
Pages2395-2402
Number of pages2154
DOIs
StatePublished - 24 Oct 2011
EventProceedings of the International Joint Conference on Neural Networks -
Duration: 1 Dec 2013 → …

Conference

ConferenceProceedings of the International Joint Conference on Neural Networks
Period1/12/13 → …

Fingerprint

robots
Manipulators
sliding
manipulators
Robots
Derivatives
Sliding mode control
Neural networks
Compensation and Redress
twisting

Cite this

Hernandez, D., Yu, W., & Moreno-Armendariz, M. A. (2011). Neural PD control with second-order sliding mode compensation for robot manipulators. 2395-2402. Paper presented at Proceedings of the International Joint Conference on Neural Networks, . https://doi.org/10.1109/IJCNN.2011.6033529
Hernandez, Debbie ; Yu, Wen ; Moreno-Armendariz, Marco A. / Neural PD control with second-order sliding mode compensation for robot manipulators. Paper presented at Proceedings of the International Joint Conference on Neural Networks, .2154 p.
@conference{f9bde82e3d4d4608a9356dec70d019ea,
title = "Neural PD control with second-order sliding mode compensation for robot manipulators",
abstract = "Both neural network and sliding mode technique can compensate the steady-state error of proportional-derivative (PD) control. The tracking error of PD control with sliding mode is asymptotically stable, but the chattering is big. PD control with neural networks is smooth, but it is not asymptotically stable. PD control combining both neural networks and sliding mode cannot reduce chattering, because the sliding mode control (SMC) is always applied. In this paper, neural control and SMC are connected serially: first a dead-zone neural PD control assures that the tracking error is bounded, then super-twisting second-order sliding-mode is used to guarantee finite time convergence of the sliding mode PD control. {\circledC} 2011 IEEE.",
author = "Debbie Hernandez and Wen Yu and Moreno-Armendariz, {Marco A.}",
year = "2011",
month = "10",
day = "24",
doi = "10.1109/IJCNN.2011.6033529",
language = "American English",
pages = "2395--2402",
note = "Proceedings of the International Joint Conference on Neural Networks ; Conference date: 01-12-2013",

}

Hernandez, D, Yu, W & Moreno-Armendariz, MA 2011, 'Neural PD control with second-order sliding mode compensation for robot manipulators' Paper presented at Proceedings of the International Joint Conference on Neural Networks, 1/12/13, pp. 2395-2402. https://doi.org/10.1109/IJCNN.2011.6033529

Neural PD control with second-order sliding mode compensation for robot manipulators. / Hernandez, Debbie; Yu, Wen; Moreno-Armendariz, Marco A.

2011. 2395-2402 Paper presented at Proceedings of the International Joint Conference on Neural Networks, .

Research output: Contribution to conferencePaperResearch

TY - CONF

T1 - Neural PD control with second-order sliding mode compensation for robot manipulators

AU - Hernandez, Debbie

AU - Yu, Wen

AU - Moreno-Armendariz, Marco A.

PY - 2011/10/24

Y1 - 2011/10/24

N2 - Both neural network and sliding mode technique can compensate the steady-state error of proportional-derivative (PD) control. The tracking error of PD control with sliding mode is asymptotically stable, but the chattering is big. PD control with neural networks is smooth, but it is not asymptotically stable. PD control combining both neural networks and sliding mode cannot reduce chattering, because the sliding mode control (SMC) is always applied. In this paper, neural control and SMC are connected serially: first a dead-zone neural PD control assures that the tracking error is bounded, then super-twisting second-order sliding-mode is used to guarantee finite time convergence of the sliding mode PD control. © 2011 IEEE.

AB - Both neural network and sliding mode technique can compensate the steady-state error of proportional-derivative (PD) control. The tracking error of PD control with sliding mode is asymptotically stable, but the chattering is big. PD control with neural networks is smooth, but it is not asymptotically stable. PD control combining both neural networks and sliding mode cannot reduce chattering, because the sliding mode control (SMC) is always applied. In this paper, neural control and SMC are connected serially: first a dead-zone neural PD control assures that the tracking error is bounded, then super-twisting second-order sliding-mode is used to guarantee finite time convergence of the sliding mode PD control. © 2011 IEEE.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=80054741840&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=80054741840&origin=inward

U2 - 10.1109/IJCNN.2011.6033529

DO - 10.1109/IJCNN.2011.6033529

M3 - Paper

SP - 2395

EP - 2402

ER -

Hernandez D, Yu W, Moreno-Armendariz MA. Neural PD control with second-order sliding mode compensation for robot manipulators. 2011. Paper presented at Proceedings of the International Joint Conference on Neural Networks, . https://doi.org/10.1109/IJCNN.2011.6033529