In order to enhance the learning performance of small-data-set models and improve the computation efficiency of finite element simulations of vehicle collision, the collision mathematical model (VCMM) based on the back-propagation (BP) neural network is established to predict the collision response data of a single car and marshalling cars at unknown velocities. The predicted results of VCMM were compared with the simulation results of the finite element method (FEM) to verify the model. The compared results show that the maximum relative errors of deformation, energy absorption and average interfacial force of a single vehicle are all below 8.5%, and the relative errors of the maximum compression of the C0 coupler and the internal energy of the A1 car among the marshalling cars are all less than 5%. In addition, the calculation time of the single car and marshalling cars collisions based on the VCMM are reduced by 24.36 and 61.8 times, respectively, compared with the FEM results, and the simulation calculation efficiency is greatly improved. The prediction result of VCMM will partially replace experimental and simulation results for crashworthiness and safety design of the vehicle structure in future studies.

To further enhance the crashworthiness of subway vehicle anti-climb energy-absorbing devices, this paper proposes a novel collapsible structure, which is embedded with honeycomb aluminum blocks and consists of an inner and outer double-layer square tube. An impact finite element model of the subway vehicle’s anti-climb energy-absorbing device was established using LS-DYNA (v.17.2). The effects of the connecting diaphragm thickness, the inner and outer tube thicknesses of the thin-walled tubes, and the yield strength of the honeycomb aluminum on the energy absorption and impact force of the anti-climb energy-absorbing device were investigated. The results indicate that changes in the inner and outer tube thicknesses of the thin-walled tubes significantly affect the energy absorption and impact force of the anti-climb energy-absorbing device. However, changes in the connecting diaphragm thickness only increase the maximum energy absorption by up to 7.5% but have a significant impact on the maximum peak force. It was also found that the difference in energy absorption due to changes in the yield strength of the honeycomb aluminum is only 3.6%, suggesting that the yield strength of the honeycomb aluminum and the connecting diaphragm thickness have a limited influence on the crashworthiness design of the anti-climb energy-absorbing device. Furthermore, a multi-objective surrogate model characterizing the specific energy absorption and maximum peak force was established for the aforementioned four influential parameters using the response surface method. The model was then optimized using a genetic algorithm, resulting in optimal parameters that increased the energy absorption and specific energy absorption by 27.3% and 13.8%, respectively, compared to the original values, leading to a significant improvement in crashworthiness. The findings provide valuable references for and insights into the crashworthiness design and optimization of subway vehicles’ anti-climb energy-absorbing devices.

The use of air springs has become widespread in various industries due to their exceptional superelastic properties; however, their strong nonlinear characteristics have become a hindrance to numerical simulations of air springs and have garnered increasing attention. This paper examined the nonlinear dynamic mechanical characteristics of air springs from a fluid–structure interaction perspective and verified the accuracy of the simulation analysis model through quasistatic tension and compression experiments. The average relative errors for air spring load and gas pressure were found to be 8.1% and 7.7%, respectively, which supports the validity of the model. The impact of frequency and amplitude excitations on the axial load characteristics of air springs was investigated through tension and torsion testing. The results showed that increasing the excitation frequency improves the stability of the axial load, while increasing the excitation amplitude enhances the axial load value. The change in axial compression was found to be more significant than that in axial tension, as it was affected not only by the axial load but also by the radial load, which is a key factor affecting the dynamic characteristics of air springs. A radial load analysis model was established to study the influence of frequency and amplitude excitations on the axial load characteristics of air springs. The simulation results indicated that under different amplitudes, the radial load of air springs goes through four stages: a steady period, rising period, steady period, and falling period. Additionally, under the same amplitude, the radial load value increases with an increase in frequency. This research on the dynamic load characteristics of air springs under amplitude and frequency excitations is important for their application in low-frequency and low-amplitude vibration environments, and its findings can be utilized to improve the technical parameters of air springs for suspension damping.

Targeting to improve the calculation efficiency of the finite element simulation, we introduce the back propagation neural network–based machine learning method to carry out the inversion prediction framework. The inversion collision model is established based on the inversion prediction framework. Then, the prediction results are compared with the finite element simulation results of the anti-climbing device to verify the feasibility of the inversion collision model. The average prediction errors of velocity, displacement, interface force, and internal energy of the anti-climbing device are 3.7%, 4.31%, 3.4%, and 1%, respectively, and the cost time of the inversion collision model is less than 5 min. The results show that the inversion collision model constructed by back propagation neural network can significantly improve the calculation efficiency and greatly reduce the calculation time under the condition of ensuring accuracy. It will provide a new evaluation method and possibility for partially replacing the required experimental and simulation results for the crashworthiness and the safety of the anti-climbing device.

We have performed magnetoresistivity measurements ${\rho }_{xx}\left(B\right)$ on an $\mathrm{Al}\mathrm{Ga}\mathrm{As}∕\mathrm{Ga}\mathrm{As}$ high electron mobility transistor (HEMT) structure at high temperatures $T$ . The observed positive magnetoresistance (MR) in the HEMT structure can be greatly enhanced simply by increasing the driving current. At $T=80\mathrm{K}$ and $B=6\mathrm{T}$ , the MR value can be increased from $\sim 150\%$ to 4000%, almost a 30-fold increase when a large current of $40\mu \mathrm{A}$ is applied. Such results are due to electron heating effects and our data lay the foundation for practical magnetic device applications which can be readily combined with high-speed electronics, high-frequency amplifiers, and radar using the mature GaAs-based HEMT technology.

In order to improve the impact ejection performance of the flexible airbag and to reveal the airbag inflating mechanism, a simulation model was built and verified by carrying out the flexible airbag impact ejection test. Based on this model, the influence of mass flow, compression displacement, and airbag thickness on flexible airbag ejection impact performance were studied. The results show that the ejection velocity of the flexible airbag increases as mass flow increases, but the excessive air mass flow does not improve the impact ejection performance of the airbag. The simulation results also demonstrate that the flexible airbag will oscillate reciprocally after it has no more contact with the moving rigid body and every node in the flexible airbag model has the same oscillating displacement. The analysis of compression displacement shows that it has a significant effect on the improvement of ejection performance. In conclusion, to improve the impact ejection performance of flexible airbag, the mass flow and compression displacement should be changed in a certain scope, which can provide reference for the topological structure design of the flexible airbag.