Surrogate-assisted two-phase tensioning strategy optimization for the system transformation process of a cable-stayed bridge

摘要

This article proposes an efficient computational framework addressing optimal two-phase tensioning planning for the system transformation process (STP) of a cable-stayed bridge erected by the incremental launching method. The Phase I problem consists of identifying one-off stretching of stayed cables to minimize construction expense. A back propagation neural network (BPNN)-assisted global sensitivity analysis is presented to address problems in Phase I. The Phase II problem is to decide two-step stayed-cable stretching lengths such that the optimized scheme satisfies multiple control principles for a successful STP. A BPNN-assisted reliability-based design optimization method is presented to achieve this goal. The applicability and efficiency of the framework is demonstrated with a real cable-stayed bridge. The results indicate that the proposed framework can deliver an optimal tensioning strategy effectively for the system transformation process of a cable-stayed bridge during the complex construction process.