Solar cells are crucial in aerospace industries as they provide a reliable and sustainable power source for spacecraft and satellites, enabling long-duration missions without relying on conventional fuel. This study investigates the propagation of nonlinear guided waves in improved silicon solar cells reinforced by graphene platelet (GPL) nanocomposites. The microplate model of the solar cells is developed using the modified couple stress theory (MCST) to capture size-dependent effects, and the sinusoidal shear deformation theory (SSDT) is applied to account for realistic shear deformation behavior. Nonlinear governing equations describing the dynamic response of the system are derived using Hamilton's principle. The equations are then solved numerically using the Runge–Kutta method to analyze the phase velocity and wave characteristics under varying parameters. The effects of GPL weight fraction, length scale parameter, and wavenumber on wave propagation are thoroughly examined. In this investigation, an intelligent model based on deep neural networks as an artificial intelligent algorithm combined with a genetic algorithm (DNN-GA) as a bio-inspired optimization approach, is employed to predict nonlinear phenomena in guided waves within the solar cell, using datasets generated from mathematical simulations. The results demonstrate that the inclusion of GPL nanocomposites enhances the mechanical properties of the silicon solar cells, leading to higher phase velocities and improved wave propagation efficiency. Additionally, the influence of the length scale parameter on phase velocity is found to be significant, particularly for low wavenumbers. This study provides valuable insights into the optimization of advanced nanocomposite-reinforced silicon solar cells for applications requiring efficient guided wave propagation. The findings offer a promising approach for the design and enhancement of next-generation solar cells.
Read full abstract