Development and deep neural network modeling of MWCNT-reinforced hybrid composites for lightweight UAV structures with enhanced energy absorption characteristics

This study focused on improving composite materials for unmanned aerial vehicle (UAV) frames by reinforcing hybrid laminates with multi-walled carbon nanotubes (MWCNTs). Researchers fabricated these laminates using Kevlar and S-glass woven fibers in an epoxy matrix, while varying MWCNT content across 0, 0.5, 1, 1.5, and 2 weight percent. Careful control of stacking sequences (0°4K/45°4S−G/0°4K) ensured strong interfacial adhesion and structural stability. Mechanical properties were evaluated using standardized testing protocols, including tensile strength, flexural strength, interlaminar shear strength, punch shear strength, and energy absorption performance. The optimal laminate, which included 1.5 wt.% MWCNTs, delivered the highest mechanical and energy absorption behavior, achieving a tensile strength of 213.06 MPa, flexural strength of 296.67 MPa, interlaminar shear strength of 1598.1 J/m, punch shear strength of 58.57 MPa, total energy absorption of 8.8 J, and a specific energy absorption of 0.27 J/m. Experimental results were further used to train a deep neural network (DNN) for accurate prediction and optimization. The DNN achieved strong results, indicated by R2 values of 0.98 and low error metrics, confirming the approach’s reliability. These findings confirm that MWCNT-reinforced composites provide substantial mechanical resilience and puncture resistance for the next generation of UAV structures.