Deep-Neural-Networks-Based Data-Driven Methods for Characterizing the Mechanical Behavior of Hydroxyl-Terminated Polyether Propellants.

Abstract

Hydroxyl-terminated polyether (HTPE) propellants are attractive in the weapons materials and equipment industry for their insensitive properties. Storage, combustion, and explosion of solid propellants are affected by their mechanical properties, so accurate mechanical modeling is vital. In this study, deep neural networks are applied to model composite solid-propellant mechanical behavior for the first time. A data-driven framework incorporating a novel training-testing splitting strategy is proposed. By building Neural Networks (FFNNs), Kolmogorov-Arnold Networks (KANs) and Long Short-Term Memory (LSTM) networks and optimizing the model framework and parameters using a Bayesian optimization algorithm, the results show that the LSTM model predicts the stress-strain curve of HTPE propellant with an RMSE of 0.053 MPa, which is 62.7% and 48.5% higher than the FFNNs and the KANs, respectively. The R² values of the LSTM model for the testing set exceed 0.99, which can effectively capture the effects of tensile rate and temperature changes on tensile strength, and accurately predict the yield point and the slope change of the stress-strain curve. Using the interpretable Shapley Additive Explanations (SHAP) method, fine-grained ammonium perchlorate (AP) can increase its tensile strength, and plasticizers can increase their elongation at break; this method provides an effective approach for HTPE propellant formulation.