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.