基于神经网络的矩形钢管混凝土柱承载性能研究-结构工程专业论文.docxVIP

ABSTRACT Nowadays, a lot of research has been done on the mechanical properties and deformation performance of concrete-filled rectangular steel tubular columns by the researchers at home and abroad, but the methods they have chosen mostly are test research, analytical method and numerical analysis method, all of which have some limitations. However, neural network algorithm is an efficient method for solving nonlinear problem. Therefore, a neural network model is created to study the mechanical properties of concrete-filled rectangular steel tubular columns, which makes contribution for further research and application of the concrete-filled rectangular steel tubular members. In the paper, several calculation theories and methods of the bearing capacity of concrete-filled rectangular steel tubular columns were presented, and their defects and limitations were pointed out. The brief introduction to the finite element analysis method of concrete-filled rectangular steel tubular columns was given. The necessity of finding an effective and uniform calculation method of bearing capacity was put forward, and the neural network method was applied in the calculation of bearing capacity of concrete-filled rectangular steel tubular columns. ANSYS, which involves large geometric deformation, material nonlinearity and contact condition, was applied in the analysis of concrete-filled rectangular steel tubular columns under axial compression and eccentric compression. The distribution stress, mechanical property and deformation performance were gained. The results demonstrated that the axial compressive concrete-filled rectangular steel tubular columns mostly occurred local buckling failure caused by the material strength damage, including the drum-shaped damage and shear damage, and shear failure was more and more obvious with the increase of length-width ratio. While eventually destroyed, each column all had one continuous buckling loop. The angle between the buckling loop an