Assistant professor, The University of Alabama, Tuscaloosa, Alabama
Programmer/analyst, American Express Travel Related Services Co., Phoenix, AZ
The poor performance of composite materials under transverse quasi-static and impact loading is of major concern in their application as primary load carrying components in advanced structural applications. These materials sustain substantial internal damage in the form of matrix cracking, delaminations and fiber fracture. The present paper reports the results of a modeling exercise which used neural networks as a tool to predict the loss in residual strength resulting from localized damage in impacted laminates. Several measured fiber fracture parameters, as well as matrix damage areas, obtained from damaged laminates were used as inputs. Neural networks were used to identify those damage parameters that were essential for effective residual strength prediction. Development of the neural network models was performed using experimental data from specimens fabricated from the Fiberite IM7/977-2 material system which were first damaged via quasi-static contact loading, and then loaded in tension to failure. Data obtained from specimens tested for residual strength after impact were used to test the model’s generalization capability. A pruning study was also conducted to determine an optimally connected, robust neural network model that generalized better than conventional fully connected feedforward networks. The predicted strength values were found to be in very good agreement with those obtained from experiments indicating the suitability of neural networks in this application.
Paper ID: CTR10118J