• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.11 no.9
• /
• pp.475-485
• /
• 2001

A study on the structural analysis of the composite laminated cylindrical shell which has simply supported boundary conditions at both ends, was performed. The results were used into the neural networks. Neural networks identify the load characteristics of the composite shells. Momentum Backpropagation which the learning rate can be varied was developed. Input patterns consist of strains at 9 side points which is divided equally. Output layers are the load characteristics. Developed program was used for the training. The training with variable learning rate was converged close to real oad characteristics. Inverse engineering can be applicable to the composite laminated cylindrical shells with developed neural networks.

• Journal of Korean Society of Steel Construction
• /
• v.10 no.4 s.37
• /
• pp.691-700
• /
• 1998

Based on Von Karman-Donnell kinematic assumptions for laminated shells, the nonlinear vibration behaviour of antisymmetrically or asymmetrically laminated cross-ply circular cylindrical shells with clamped and simply-supported ends are studied by a multi-mode approach. A equation is formulated and satisfies the associated compatibility equation and all boundary conditions. The displacement function is assumed to take the form of the lowest linear vibration mode and to satisfy continuity of the circumferential displacement. The nonlinear vibration equation is derived by the Galerkin's method. And nonlinear frequency is obtained by using the harmonic balance method as a function of lamination parameters, material constants, aspect ratio and amplitude of vibration. The effect of initial imperfection is also included. Results of the non-linear vibration are presented for different amplitudes of initial imperfection and four sets of boundary conditions. Present results are compared well with existing analysis results.