Failure Prediction of Composite Materials Using Deep Neural Networks

Abstract

Fiber-reinforced polymer (FRP) composite materials are increasingly used in engineering applications. However, an investigation into the precision of conventional failure criteria, known as the World-Wide Failure Exercise (WWFEI), revealed that current theories remain unable to predict failure within an acceptable degree of accuracy. Deep Neural Networks (DNN) are emerging as an alternate and time-efficient technique for predicting the failure strength of FRP composite materials. The present study examined the applicability of DNNs as a tool for creating a data-driven failure model for composite materials. The experimental failure data presented in the WWFE-I were used to develop the datadriven model. A fully connected DNN with 23 input units and 1 output unit trained with a constant learning rate (α=0.0001). The network’s inputs described the laminates and the loading conditions applied to the test specimen, whereas the output was the length of the failure vector (L=(σx+σy+τxy)0.5). The DNN’s performance was evaluated using the mean squared error on a subset of the experimental data unseen during training. Network configurations with a varying number of hidden layers and units per layer were evaluated. The DNN with 3 hidden layers and 20 units per hidden layer performed the best. In fact, the network’s predictions show good agreement with the experimental results. The failure boundaries generated by the DNN were compared to three conventional theories: the Tsai-Wu, Cuntze, and Puck theory. The DNN’s failure envelopes were found to fit the experimental data more closely than the above-mentioned theories. In sum, the DNN’s ability to fit higher-order polynomials to data separates it from conventional failure criteria. This characteristic makes DNNs an effective method for predicting the failure strength of composite laminates.