The hot deformation behavior of titanium matrix composites plays a crucial role in determining the performance of the formed components. Therefore, it is significant to establish an accurate constitutive relationship between material deformation parameters and flow stress. In this study, hot compression experiments were conducted on a (2.5 vol%TiB + 2.5 vol%TiC)/TC4. The experiments were performed under temperatures ranging from 1013.15 to 1133.15 K and strain rates ranging from 0.001 to 0.1 s⁻¹. Based on the stress–strain data obtained from the experiment, the constitutive models were established by using the Arrhenius model and the BP neural network algorithm, respectively. Considering the relationship between strain rate, hot working temperature, and flow stress, a comparative analysis was conducted to evaluate the prediction accuracy of two different constitutive models. The research results indicate that the flow stress of (2.5 vol%TiB + 2.5 vol%TiC)/TC4 increases with decreasing temperature and increasing strain rate, and the stress–strain curve shows obvious work hardening and softening behaviors. Both the Arrhenius model and the BP neural network algorithm are effective in predicting the hot compression flow stress of (2.5 vol%TiB + 2.5 vol%TiC)/TC4, but the average relative error and root mean square error of the BP neural network algorithm are smaller and the correlation coefficient is higher, thus possessing higher accuracy and reliability.

The Dujiangyan–Siguniangshan mountain rack railway project is China’s first mountain rail transit. Most of its lines are located in mountainous areas and close to natural ecological protection areas, which have strict restrictions on the vibration and noise of train operation. At the same time, the vibration of mountain rack railway trains is also an important factor affecting the safety and riding comfort of trains. However, due to the multi-source vibration of gear teeth, wheels, rails, and suspensions, it is difficult to clearly define the vibration characteristics and vibration transmission path of the train, which has a serious impact on its vibration noise suppression and optimization. To this end, this study proposed a set of evaluation methods for the vibration characteristics and transfer paths of mountain rack trains based on a combination of dynamics and operational transfer path analysis (OTPA). Considering the interaction between the dynamic behaviors of the primary and secondary suspensions, the gear tooth contact behavior, the wheel–rail contact behavior and the dynamic behaviors of the track system, a dynamic model of a mountain rack train based on the finite element method was established, and the effectiveness of the model was verified through field experiments. On this basis, the OTPA method was used to establish a vibration transfer path model between the secondary suspension and the center of mass of the car body, and it was used to analyze the vibration mechanism and transfer path of the train body at the rated speed (20 km/h) and the limited speed (30 km/h). This study is of great significance for suppressing the vibration noise of mountain rack trains, reducing the impact on the ecological environment and improving ride comfort.