Membrane-type acoustic metamaterial (MAM) has exhibited superior sound isolation properties, as well as thin and light characteristics. However, the anti-resonance modes of traditional MAMs are generated intermittently in a wide frequency range causing discontinuities in the anti-resonance modes. Achieving broadband low-frequency sound attenuation with lightweight MAM design is still a pivotal research aspect. Here, we present a strategy to realize wide sound-attenuation bands in low frequency range by introducing the design concept of bionic configuration philosophy into the MAM structures. Built by a polymeric membrane and a set of resonators, two kinds of MAM models are proposed based on the insight of a spider web topology. The sound attenuation performance and physical mechanisms are numerically and experimentally investigated. Multi-state anti-resonance modes, induced by the coupling of the bio-inspired arrangement and the host polymer film, are systematically explored. Significant sound attenuation is numerically and experimentally observed in both the lightweight bio-inspired designs. Remarkably, compared with a traditional MAM configuration, a prominent enhancement in both attenuation bandwidth and weight-reduction performance is verified. In particular, the bio-inspired MAM Model I exhibits a similar isolation performance as the reference model, but the weight is reduced by nearly half. The bio-inspired Model II broadens the sound attenuation bandwidth greatly; meanwhile, it retains a lighter weight design. The proposed bio-inspired strategies provide potential ways for designing sound isolation devices with both high functional and lightweight performance.

The statistical analysis of civil aircraft accidents reveals that the highest incidence of mishaps occurs during the approach and landing stages. Predominantly, these accidents are marked by abnormal energy states, leading to critical situations like stalling and heavy landings. Therefore, it is of great significance to accurately predict the aircraft energy state in the approach and landing stages to ensure a safe landing. In this study, a deep learning method based on time sequence data for the prediction of the aircraft approach and landing energy states is proposed. Firstly, by conducting an extensive overview of the existing literature, three characteristic parameters of altitude, velocity, and glide angle were selected as the indicators to characterize the energy state. Following this, a semi-physical simulation platform for a certain type of aircraft was developed. The approach and landing experiments were carried out with different throttle sizes and flap deflection under different wind speeds and wind directions. Then, a deep learning prediction model based on Long Short-Term Memory (LSTM) was established based on the experimental data to predict the energy state indicators during the approach and landing phases. Finally, the established LSTM model underwent rigorous training and testing under different strategies, and a comparative analysis was carried out. The results demonstrated that the proposed LSTM model exhibited high accuracy and a strong generalization ability in predicting energy states during the approach and landing phases. These results offer a theoretical basis for designing energy early warning systems and formulating the relevant flight control laws in the approach and landing stages.