Abstract

Modern design codes ensure a large displacement capacity and prevent total collapse for bridges under earthquakes. However, this performance objective is usually attained at the cost of damage to target ductile members. For conventional reinforced concrete (RC) bridges, columns are usually the main source of ductility during an earthquake in which concrete cover, core, and reinforcement may damage, and the column may experience a large permanent lateral deformation. Visual inspection is currently the preferred method of bridge assessment after an event. Nevertheless, sending inspectors to all affected bridges is time consuming and logistically challenging. An alternative method may save time, costs, and lives. The main goal of the present study was to accelerate post-earthquake assessment of standard RC bridge columns using computer vision and seismic analyses. Standard columns are those that are designed following seismic requirements. To achieve the project goal, a new quantitative definition was proposed for RC bridge column damage states suited for computer programming, the most comprehensive experimental database of standard RC bridge columns consisting of 290 specimens was compiled, then the database was statistically analyzed to relate the proposed column damage states to displacement demands. Furthermore, an artificial intelligence enabled software was developed to quickly detect RC bridge column damages, to comment on the column damage state, and to tag the column. A framework was proposed to assess the serviceability of standard RC bridge columns after earthquakes.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call