Optimization of mechanical performance in bioinspired FDM-printed PLA sandwich structures using machine learning.

Additive manufacturing via Fused Deposition Modeling (FDM) enables the fabrication of complex, bioinspired core geometries for lightweight sandwich structures in aerospace applications. However, the multi-dimensional parameter space governing the mechanical performance of Polylactic Acid (PLA) sandwich panels presents significant optimization challenges. This research direction explores the integration of machine learning algorithms to predict and optimize the mechanical response, specifically energy absorption and specific stiffness, of bioinspired core topologies. By utilizing experimental datasets and finite element analysis (FEA) simulations, predictive models can map the relationships between structural parameters—such as cell wall thickness, core height, and biomimetic geometric configurations—and their resulting load-bearing capacities. The methodology involves training regression models, such as random

forests or artificial neural networks, to bypass computationally expensive iterative simulations. Implementation support focuses on establishing robust validation protocols comparing machine learning predictions against physical three-point bending and compression tests. Ultimately, this framework provides systematic guidance for the rapid design optimization of sustainable, high-performance polymeric sandwich structures, facilitating their potential integration into secondary aerospace structural components.

Message: Hi FE, I need help with “Optimization of mechanical performance in bioinspired FDM-printed PLA sandwich structures using machine learning.” in “Aerospace Engineering”