System reliability-based optimisation for truss structures using genetic algorithm and neural network

• DOI: 10.1504/ijrs.2014.062640
• Publication Date: 2015-04-11T07:01:51Z
• Authors: Yang Liu; Naiwei Lu; Mohammad Noori; Xinfeng Yin
• Keywords: Optimal design; Structural system

Optimum structures must have adequate resistance against external random loads. Since most truss involve a series of failure processes, it is necessary to develop system reliability analyses for the optimum design structures. In this paper, hybrid method reliability-based optimisation (SRBDO) proposed by combining genetic algorithms (GAs) and radial basis functions (RBFs) neural networks. The applied structures, then validity demonstrated through two specific examples. Detailed discussions sequences such as buckling bending are presented. It concluded that structural weight increases significantly with increase target index or coefficient variation parameters. Results schemes steel girder show cross-sectional areas beams decreased those web members increased.