Bionic thin-walled structures, due to their excellent energy absorbing capacity, low manufacturing cost, and remarkable level of lightweight, have been widely applied in the field of traffic safety protection. Combinatorial structures that incorporate the prototypical characteristics of multiple organisms also turn into the hotspot of the research on safety protection structure, which can achieve more excellent overall performance. However, how to select the optimal alternative considering the performance of different attributes and different accident conditions has become an urgent problem to be solved. This paper proposes 12 kinds of bionic thin-walled energy absorption structures with different cross sections and bamboo of tubes, which is inspired by the structural characteristics of bamboo. A comprehensive performance analysis, including specific energy absorption, peak crushing force, and undulation of the load-carrying capacity under quasi-static and dynamic conditions, is carried out based on the finite element simulation. The gray relational analysis method is applied to select the optimal structure. In addition, sensitivity analysis of each structural variable is conducted. The result shows that the “+-3” bionic thin-walled structure has the best comprehensive performance, and the structural variable has great impact on the PCF. This study provides an effective decision-making support tool for performance evaluation of bionic thin-walled structures.

No abstract

No abstract

A practical solution to the power allocation problem in ultra-dense small cell networks can be achieved by using deep reinforcement learning (DRL) methods. Unlike traditional algorithms, DRL methods are capable of achieving low latency and operating without the need for global real-time channel state information (CSI). Based on the actor–critic framework, we propose a policy optimization of the power allocation algorithm (POPA) for small cell networks in this paper. The POPA adopts the proximal policy optimization (PPO) algorithm to update the policy, which has been shown to have stable exploration and convergence effects in our simulations. Thanks to our proposed actor–critic architecture with distributed execution and centralized exploration training, the POPA can meet real-time requirements and has multi-dimensional scalability. Through simulations, we demonstrate that the POPA outperforms existing methods in terms of spectral efficiency. Our findings suggest that the POPA can be of practical value for power allocation in small cell networks.