Flexural analysis of 3D-printed sandwich beams with chiral cores using deep neural networks and response surface methodology DOI
Saeed Kamarian, Ali Khalvandi,

Ehsan Heidarizadi

et al.

Mechanics of Advanced Materials and Structures, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 16

Published: Dec. 3, 2024

This study employed Deep Neural Networks (DNNs) and Response Surface Methodology (RSM) for flexural analysis of 3D-printed sandwich beams with chiral cores. The cores were configured varying parameters: diameter, thickness, angle the unit cell. trained DNN demonstrated high predictive accuracy RSM polynomials statistically significant p-values below 0.05. Increased cell thickness resulted in higher maximum force stiffness/mass. Smaller diameters enhanced forces stiffness/mass due to better material density structural integrity. Moreover, increasing values improved stiffness while minimizing mass.

Language: Английский

Flexural analysis of 3D-printed sandwich beams with chiral cores using deep neural networks and response surface methodology DOI
Saeed Kamarian, Ali Khalvandi,

Ehsan Heidarizadi

et al.

Mechanics of Advanced Materials and Structures, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 16

Published: Dec. 3, 2024

This study employed Deep Neural Networks (DNNs) and Response Surface Methodology (RSM) for flexural analysis of 3D-printed sandwich beams with chiral cores. The cores were configured varying parameters: diameter, thickness, angle the unit cell. trained DNN demonstrated high predictive accuracy RSM polynomials statistically significant p-values below 0.05. Increased cell thickness resulted in higher maximum force stiffness/mass. Smaller diameters enhanced forces stiffness/mass due to better material density structural integrity. Moreover, increasing values improved stiffness while minimizing mass.

Language: Английский

Citations

1