Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers
This paper proposes an adaptive neural network composed of Gaussian radial functions for mapping the behavior of civil structures controlled with magnetorheological dampers. The online adaptation takes into account the limited force output of the semi-active dampers using a sliding mode controller,...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | en_US |
Published: |
Society of Photo-Optical Instrumentation Engineers
2010
|
Online Access: | http://hdl.handle.net/1721.1/52638 https://orcid.org/0000-0002-2262-9139 https://orcid.org/0000-0001-5666-3215 |
_version_ | 1826207424933003264 |
---|---|
author | Laflamme, Simon Connor, Jerome J. |
author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Laflamme, Simon Connor, Jerome J. |
author_sort | Laflamme, Simon |
collection | MIT |
description | This paper proposes an adaptive neural network composed of Gaussian radial functions for mapping the behavior of civil structures controlled with magnetorheological dampers. The online adaptation takes into account the limited force output of the semi-active dampers using a sliding mode controller, as their reaction forces are state dependent. The structural response and the actual forces from the dampers are used to adapt the Gaussian network by tuning the radial function widths, centers, and weights. In order to accelerate convergence of the Gaussian radial function network during extraordinary external excitations, the learning rates are also adaptive. The proposed controller is simulated using three types of earthquakes: near-field, mid-field, and far-field. Results show that the neural controller is effective for controlling a structure equipped with a magnetorheological damper, as it achieves a performance similar to the passiveon strategy while requiring as low as half the voltage input. |
first_indexed | 2024-09-23T13:49:47Z |
format | Article |
id | mit-1721.1/52638 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T13:49:47Z |
publishDate | 2010 |
publisher | Society of Photo-Optical Instrumentation Engineers |
record_format | dspace |
spelling | mit-1721.1/526382022-10-01T17:22:08Z Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers Laflamme, Simon Connor, Jerome J. Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Connor, Jerome J. Laflamme, Simon Connor, Jerome J. This paper proposes an adaptive neural network composed of Gaussian radial functions for mapping the behavior of civil structures controlled with magnetorheological dampers. The online adaptation takes into account the limited force output of the semi-active dampers using a sliding mode controller, as their reaction forces are state dependent. The structural response and the actual forces from the dampers are used to adapt the Gaussian network by tuning the radial function widths, centers, and weights. In order to accelerate convergence of the Gaussian radial function network during extraordinary external excitations, the learning rates are also adaptive. The proposed controller is simulated using three types of earthquakes: near-field, mid-field, and far-field. Results show that the neural controller is effective for controlling a structure equipped with a magnetorheological damper, as it achieves a performance similar to the passiveon strategy while requiring as low as half the voltage input. 2010-03-16T20:46:32Z 2010-03-16T20:46:32Z 2009-04 2009-03 Article http://purl.org/eprint/type/JournalArticle 0277-786X SPIE CID: 72880M-12 http://hdl.handle.net/1721.1/52638 Laflamme, Simon, and Jerome J. Connor. “Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers.” Active and Passive Smart Structures and Integrated Systems 2009. Ed. Mehdi Ahmadian & Mehrdad N. Ghasemi-Nejhad. San Diego, CA, USA: SPIE, 2009. 72880M-12. © 2009 SPIE https://orcid.org/0000-0002-2262-9139 https://orcid.org/0000-0001-5666-3215 en_US http://dx.doi.org/10.1117/12.815540 Proceedings of SPIE--the International Society for Optical Engineering Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Society of Photo-Optical Instrumentation Engineers SPIE |
spellingShingle | Laflamme, Simon Connor, Jerome J. Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title | Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title_full | Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title_fullStr | Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title_full_unstemmed | Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title_short | Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers |
title_sort | application of self tuning gaussian networks for control of civil structures equipped with magnetorheological dampers |
url | http://hdl.handle.net/1721.1/52638 https://orcid.org/0000-0002-2262-9139 https://orcid.org/0000-0001-5666-3215 |
work_keys_str_mv | AT laflammesimon applicationofselftuninggaussiannetworksforcontrolofcivilstructuresequippedwithmagnetorheologicaldampers AT connorjeromej applicationofselftuninggaussiannetworksforcontrolofcivilstructuresequippedwithmagnetorheologicaldampers |