Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension

Juan C. Tudón-Martínez, Ruben Morales-Menendez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

© Springer International Publishing Switzerland 2014. A model for a Magneto-Rheological (MR) damper based on Artificial Neural Networks (ANN) is proposed. The design of the ANN model is focused to get the best architecture that manages the trade-off between computing cost and performance. Experimental data provided from two MR dampers with different properties have been used to validate the performance of the proposed ANN model in comparison with the classical parametric model of Bingham. Based on the RMSE index, an average error of 7.2% is obtained by the ANN model, by taking into account 5 experiments with 10 replicas each one; while the Bingham model has 13.8% of error. Both model structures were used in a suspension control system for a Quarter of Vehicle (QoV) model in order to evaluate the effect of its accuracy into the design/evaluation of the control system. Simulation results show that the accurate ANN-based damper model fulfills with the control goals; while the Bingham model does not fulfill them, by concluding erroneously that the controller is insufficient and must be redesigned. The accurate MR damper model validates a realistic QoV model response compliance.
Original languageEnglish
Title of host publicationNonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension
Pages295-309
Number of pages15
ISBN (Electronic)9783319112701
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes
EventStudies in Computational Intelligence -
Duration: 1 Jan 2014 → …

Publication series

NameStudies in Computational Intelligence
Volume577
ISSN (Print)1860-949X

Conference

ConferenceStudies in Computational Intelligence
Period1/1/14 → …

Fingerprint

Neural networks
Control systems
Model structures
Controllers
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Tudón-Martínez, J. C., & Morales-Menendez, R. (2014). Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. In Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension (pp. 295-309). (Studies in Computational Intelligence; Vol. 577). https://doi.org/10.1007/978-3-319-11271-8_19
Tudón-Martínez, Juan C. ; Morales-Menendez, Ruben. / Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. 2014. pp. 295-309 (Studies in Computational Intelligence).
@inproceedings{7a93d10880e94bf990e046f4471c6588,
title = "Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension",
abstract = "{\circledC} Springer International Publishing Switzerland 2014. A model for a Magneto-Rheological (MR) damper based on Artificial Neural Networks (ANN) is proposed. The design of the ANN model is focused to get the best architecture that manages the trade-off between computing cost and performance. Experimental data provided from two MR dampers with different properties have been used to validate the performance of the proposed ANN model in comparison with the classical parametric model of Bingham. Based on the RMSE index, an average error of 7.2{\%} is obtained by the ANN model, by taking into account 5 experiments with 10 replicas each one; while the Bingham model has 13.8{\%} of error. Both model structures were used in a suspension control system for a Quarter of Vehicle (QoV) model in order to evaluate the effect of its accuracy into the design/evaluation of the control system. Simulation results show that the accurate ANN-based damper model fulfills with the control goals; while the Bingham model does not fulfill them, by concluding erroneously that the controller is insufficient and must be redesigned. The accurate MR damper model validates a realistic QoV model response compliance.",
author = "Tud{\'o}n-Mart{\'i}nez, {Juan C.} and Ruben Morales-Menendez",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/978-3-319-11271-8_19",
language = "English",
isbn = "9783319112701",
series = "Studies in Computational Intelligence",
pages = "295--309",
booktitle = "Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension",

}

Tudón-Martínez, JC & Morales-Menendez, R 2014, Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. in Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. Studies in Computational Intelligence, vol. 577, pp. 295-309, Studies in Computational Intelligence, 1/1/14. https://doi.org/10.1007/978-3-319-11271-8_19

Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. / Tudón-Martínez, Juan C.; Morales-Menendez, Ruben.

Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. 2014. p. 295-309 (Studies in Computational Intelligence; Vol. 577).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension

AU - Tudón-Martínez, Juan C.

AU - Morales-Menendez, Ruben

PY - 2014/1/1

Y1 - 2014/1/1

N2 - © Springer International Publishing Switzerland 2014. A model for a Magneto-Rheological (MR) damper based on Artificial Neural Networks (ANN) is proposed. The design of the ANN model is focused to get the best architecture that manages the trade-off between computing cost and performance. Experimental data provided from two MR dampers with different properties have been used to validate the performance of the proposed ANN model in comparison with the classical parametric model of Bingham. Based on the RMSE index, an average error of 7.2% is obtained by the ANN model, by taking into account 5 experiments with 10 replicas each one; while the Bingham model has 13.8% of error. Both model structures were used in a suspension control system for a Quarter of Vehicle (QoV) model in order to evaluate the effect of its accuracy into the design/evaluation of the control system. Simulation results show that the accurate ANN-based damper model fulfills with the control goals; while the Bingham model does not fulfill them, by concluding erroneously that the controller is insufficient and must be redesigned. The accurate MR damper model validates a realistic QoV model response compliance.

AB - © Springer International Publishing Switzerland 2014. A model for a Magneto-Rheological (MR) damper based on Artificial Neural Networks (ANN) is proposed. The design of the ANN model is focused to get the best architecture that manages the trade-off between computing cost and performance. Experimental data provided from two MR dampers with different properties have been used to validate the performance of the proposed ANN model in comparison with the classical parametric model of Bingham. Based on the RMSE index, an average error of 7.2% is obtained by the ANN model, by taking into account 5 experiments with 10 replicas each one; while the Bingham model has 13.8% of error. Both model structures were used in a suspension control system for a Quarter of Vehicle (QoV) model in order to evaluate the effect of its accuracy into the design/evaluation of the control system. Simulation results show that the accurate ANN-based damper model fulfills with the control goals; while the Bingham model does not fulfill them, by concluding erroneously that the controller is insufficient and must be redesigned. The accurate MR damper model validates a realistic QoV model response compliance.

U2 - 10.1007/978-3-319-11271-8_19

DO - 10.1007/978-3-319-11271-8_19

M3 - Conference contribution

SN - 9783319112701

T3 - Studies in Computational Intelligence

SP - 295

EP - 309

BT - Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension

ER -

Tudón-Martínez JC, Morales-Menendez R. Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. In Nonparametric modeling of an automotive damper based on ANN: Effect in the control of a semi-active suspension. 2014. p. 295-309. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-319-11271-8_19