Theory-guided machine learning for damage characterization of composites

Abstract A novel approach for damage characterization through machine learning is presented where theoretical knowledge of failure and strain-softening is linked to the macroscopic response of quasi-isotropic composite laminates in over-height compact tension tests. A highly efficient continuum damage finite element model enables the training of a system of interconnected Neural Networks (NNs) in series solely based on the macroscopic load-displacement data. Using experimental results, the trained NNs predict suitable damage parameters for progressive damage modeling of IM7/8552 composite laminates. The predicted damage properties are validated successfully using experimental measurements obtained through cumbersome non-destructive data analysis. The proposed strategy demonstrates the effectiveness of machine learning to reduce experimental efforts for damage characterization in composites.