ABSTRACT
A cable-supported bridge is usually the key junction of a highway or a railway demanding a higher safety margin, especially in harsh environmental and complex loading areas. In comparison to short-span girder bridges, long-span flexible structures have unique characteristics leading to the complexity of structural mechanical behaviors. Thus, the system safety of cable-supported bridges is critical but difficult to evaluate. This study presents a novel and intelligent approach for system reliability evaluation of cable-supported bridges under stochastic traffic load using deep belief networks (DBNs). Mathematical models for the system reliability of cable-supported bridges were derived with consideration of structural nonlinearities and high order statically indeterminate characteristics. A computational framework was presented to show the procedures for system reliability evaluation using DBNs. In the case study, a prototype suspension bridge was selected to investigate the system reliability under stochastic traffic loading considering site-specific traffic monitoring data. Numerical results indicate that the DBN provides an accurate approximation for the mechanical behavior accounting for structural nonlinearities and system behaviors, which can be treated as a meta-model to estimate the structural failure probability. The dominant failure mode of the suspension bridge is the rupture of suspenders followed by the bending failure of girders. The degradation of suspenders due to fatigue-corrosion damage has a significant influence on the system reliability of the suspension bridge. The numerical result provides a theoretical basis for the cable replacement strategy.
