BUCKLING ASSESSMENT OF IMPERFECT CYLINDRICAL SHELLS UNDER AXIAL LOADS USING A GEP TECHNIQUE

Abstract

Determination of buckling behavior of shell structures has long been identified as a challenging task. This is largely because the buckling behavior is masked by local large deformations, which occur once the critical load is reached. This research proposes a novel technique to accurately predict the buckling load of imperfect cylindrical shells using gene expression programming (GEP), which is an evolutionary artificial intelligence method. An existing experimental data bank was employed for training and testing the program, and the obtained buckling load of shell structures were accordingly verified. From the results, it is concluded that GEP is a promising and reliable method to determine the buckling load of shell structures subjected to axial compression.