Novel methodology to mitigate vibrations in nanocomposites reinforced smart systems rested on concrete auxetic foundation by artificial intelligence algorithm

This study presents a novel methodology for mitigating vibrations in sandwich plates with sensor/actuator face sheets and a carbon nanotube (CNT)-reinforced core, resting on a concrete auxetic foundation under external loading. A comprehensive mathematical simulation framework is developed, incorporating higher-order shear deformation theory and Hamilton's principle to model the dynamic behavior of the system. The proposed approach integrates an artificial intelligence-based deep neural network (DNN) to enhance accuracy and validate the numerical results. The sensor/actuator face sheets, equipped with piezoelectric layers, enable active control of vibrations through real-time feedback mechanisms, while the CNT-reinforced core enhances stiffness and damping characteristics. The unique auxetic properties of the concrete foundation further contribute to energy dissipation and vibration reduction. The study systematically examines the effects of CNT distribution, auxetic parameters, and control strategies on the dynamic response of the sandwich plate. The mathematical model is trained using high-fidelity datasets, and the DNN algorithm optimizes predictive accuracy, demonstrating superior agreement with benchmark numerical solutions. Results confirm the efficacy of the proposed methodology in reducing vibrations, offering significant improvements over conventional passive and active control techniques. The developed framework provides valuable insights for designing intelligent structural systems with enhanced vibration suppression capabilities, contributing to the advancement of high-performance aerospace, civil, and mechanical engineering applications. Future research directions include experimental validation and extending the approach to nonlinear dynamic regimes.