Thermo-elastic vibration analysis and optimization of a nanoresonator composed of a coupled nanotube system for acoustic liner application using the hybrid deep neural network–based white shark algorithm

Abstract

This study explores the potential of nanoresonator systems composed of coupled nanotubes with graphene nanoparticles for enhancing the performance of acoustic liners in aircraft engines. The objective of this study is to develop an analytical model and predict its behavior under various conditions. The acoustic liners consist of perforated metal sheets and honeycomb cavities, which are essential for noise reduction in aircraft engines. The model is tested for variations in natural frequency, mode number (m), size effects (e₀a), viscous constant (C), temperature (T), localness factor (L), and stiffness constant (K). A hybrid deep neural network–based white shark algorithm (DNN-WSA) is used to predict and optimize the performance of nanoresonator-coupled nanotube systems. Four theories were compared, such as wave propagation theory, nonlocal elasticity theory, polynomial eigenvalue approach, and governing equations with respect to natural frequencies in nanoresonator-coupled nanotube systems. The wave propagation theory yielded the lowest natural frequency, which was selected for detailed analysis. The optimized values of size effect of 2 nm, temperature of 5 K, and frequency of 1.971975 THz were obtained. When C = 0.3, K = 10, T = 300, and L = 10×e⁻⁹, the root mean square error (RMSE) value is 0.8421, which indicates improved predictive performance as it continues to decrease. The study’s findings showed that changes in viscous constants impact natural frequencies, while size effects have a minor influence. Temperature variations also affect natural frequencies, with higher temperatures leading to higher frequencies. The optimized model demonstrates enhanced predictive performance, which contributes to a better understanding of nanoresonator systems and their application in noise reduction for aircraft engines.