Adaptive Fusion Graph Network for 3D Strain Field Prediction in Solid Rocket Motor Grains
This work provides a computationally efficient and high-fidelity approach for evaluating structural safety in solid rocket motors, addressing a domain-specific engineering challenge.
The paper tackled the problem of predicting 3D strain fields in solid rocket motor grains to address structural failure risks, proposing GrainGNet which reduced mean squared error by 62.8% compared to a baseline graph U-Net and improved prediction error in high-strain regions by 33% over the second-best method.
Local high strain in solid rocket motor grains is a primary cause of structural failure. However, traditional numerical simulations are computationally expensive, and existing surrogate models cannot explicitly establish geometric models and accurately capture high-strain regions. Therefore, this paper proposes an adaptive graph network, GrainGNet, which employs an adaptive pooling dynamic node selection mechanism to effectively preserve the key mechanical features of structurally critical regions, while concurrently utilising feature fusion to transmit deep features and enhance the model's representational capacity. In the joint prediction task involving four sequential conditions--curing and cooling, storage, overloading, and ignition--GrainGNet reduces the mean squared error by 62.8% compared to the baseline graph U-Net model, with only a 5.2% increase in parameter count and an approximately sevenfold improvement in training efficiency. Furthermore, in the high-strain regions of debonding seams, the prediction error is further reduced by 33% compared to the second-best method, offering a computationally efficient and high-fidelity approach to evaluate motor structural safety.