About this document
1 s2.0 S0041624X2200169X Main by Mahender is a document available to read on EtoBox.
This paper presents the optimization of hyperparameters for a Data-driven simulation-assisted-Physics learned AI (DPAI) model aimed at simulating ultrasonic wave propagation with reduced compounding error. The DPAI model employs a modified convolutional long short-term memory (ConvLSTM) architecture and is trained on a finite element simulation dataset to improve accuracy in modeling deeper simulations. The results demonstrate significant reductions in mean absolute error and mean absolute percentage error
- Author
- Mahender
- Language
- EN