Acoustic emission-based failure load prediction for plain woven laminates under quasi-static indentation

Composites are widely used in engineering applications, and their penetration resistance is critical for performance and safety. However, testing the failure load of composites directly leads to component failure, making it challenging to evaluate the expected residual capacity. To address this issue, this study proposes an artificial neural network (ANN) method that accurately predicts the penetration failure load of composites using acoustic emission (AE) data. A cyclic loading test schedule is designed to capture the AE data during each cycle, and a relationship between AE data and load ratio (LR) is established. To predict the failure load, an extrapolation method (EM) based on uncertainty is proposed in this paper. This approach enables the prediction of failure load intervals when LR equals 1, with relative errors of less than 7.66%. In cases where multiple loads are not feasible, the single-point prediction method (SPM) can be used instead of the extrapolation method. However, it is crucial to avoid training AE data during the initial loading stage for accurate predictions. This study recommends a loading ratio of more than 0.1 for optimal results with this approach.