General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons).
Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. ABSTRACT: Operation of flood barrier gates is sometimes hampered by flow-induced vibrations. Although the physics is understood for specific gate types, it remains challenging to judge dynamic gate behaviour for unanticipated conditions. This paper presents a hybrid modelling system for predicting vibrations by combining machine learning with physics-based modelling so that critical situations can be avoided. In the outlined data-driven approach gate response data is acquired by sensors and stored in a database. For an underflow gate under submerged flow conditions, gate opening and "reduced velocity" are the attributes for classification into safe and unsafe situations. Results from physical scale model tests are used to illustrate the proposed technique. A finite-element model for computational fluid-structure interaction simulations, presently under development, is applied to provide complementary input to the system's database. The system described in this paper contributes to safer gate control and can become a useful aid in flood barrier management.