Load balancing and neural dynamic model to optimize replicator dynamics controllers for vibration reduction of highway bridge structures

Earthquakes cause irreparable damages to the built environment, which has led bridge engineers develop structural control systems mitigate damage and improve vibration reduction in real-time. Among systems, base isolation is one of most commonly used passive strategies for seismic protection civil structures. Yet, it lacks real-time adaptability, lower energy dissipation, poor performance during near-fault earthquakes. To overcome these limitations, a hybrid system comprised semi-active magneto-rheological (MR) dampers bearings installed at deck piers highway This paper, inspired by evolutionary game theory artificial intelligence, proposes data-driven replicator dynamic algorithms distribute command voltage current driver MR dampers. It incorporates load balancing strategy reallocate additional resources. achieve high-performance design game-theory-inspired controllers, patented neural model optimize parameters. The evaluation proposed methodology uses benchmark problem based on 91/5 Southern California subjected near-field earthquake accelerograms. five different controllers compared with conventional Lyapunov fuzzy logic using 21 criteria. Results show capability vibrations experienced structure further increase durability devices. novelty impacts how game-theory make decisions among multiple devices engineering problems.