Controlling flow-induced vibrations of flood barrier gates with data-driven and finite-element modelling

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