Show simple item record

dc.contributor.authorDong-Hyawn Kim
dc.contributor.authorSeung-Nam Seo
dc.contributor.authorIn-Won Lee
dc.date.accessioned2017-05-08T22:40:22Z
dc.date.available2017-05-08T22:40:22Z
dc.date.copyrightApril 2004
dc.date.issued2004
dc.identifier.other%28asce%290733-9399%282004%29130%3A4%28424%29.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl/handle/yetl/85902
dc.description.abstractA neurocontrol method is applied to the nonlinear benchmark control problem. A neurocontroller is trained based on a reduced-order linear design model, then it is used to control a nonlinear evaluation model. In training the controller, a sensitivity evaluation scheme is used and weights are updated by minimizing a cost function. Absolute accelerations directly measured from sensors are used as the feedback signals for the controller. Not only the current step acceleration, but delay signals of sensor readings, are used to enhance the training capability. Numerical examples show that the controlled responses are considerably reduced compared with the uncontrolled case. In conclusion, the possibility of the proposed control algorithm as a candidate for the controller of nonlinear building is shown.
dc.publisherAmerican Society of Civil Engineers
dc.titleOptimal Neurocontroller for Nonlinear Benchmark Structure
dc.typeJournal Paper
dc.journal.volume130
dc.journal.issue4
dc.journal.titleJournal of Engineering Mechanics
dc.identifier.doi10.1061/(ASCE)0733-9399(2004)130:4(424)
dc.treeJournal of Engineering Mechanics:;2004:;Volume ( 130 ):;issue: 004
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record