Identification of crack location and depth in a cantilever beam using a modular neural network approach

In this paper, the flexural vibration in a cantilever beam having a transverse surface crack is considered. The modal frequency parameters are analytically computed for various crack locations and depths using a fracture mechanics based crack model. These computed modal frequencies are used to train a neural network to identify both the crack location and depth. The sensitivity of the modal frequencies to a crack increases when the crack is near the root and decreases as the crack moves to the free end of the cantilever beam. Because of the sensitive nature of this problem, a modular neural network approach is used. First, the crack location is identified with computed modal frequency parameters. Next, the crack depth is identified with computed modal frequency parameters and the identified crack location. A comparative study is made using the modular neural network architecture with two widely used neural networks, namely the multi-layer perceptron network and the radial basis function network. The proposed modular neural network method with a radial basis function network is found to perform better than the multi-layer perceptron network. In addition, the radial basis function network takes less computational time to train the network than the multi-layer perceptron network. This modular neural network architecture can be used as a non-destructive procedure for health monitoring of structures.