This paper investigates AI models for generating synthetic data from highly dynamic and size-limited lateral-sled-test measurements for the purpose of training data augmentation. Given that lateral sled tests serve as a cost-efficient proxy for full-scale crash experiments while covering only a limited subset of deceleration, intrusion, and restraint-system configurations, the problem is formulated as the conditional generation of multivariate transient response signals under varying boundary conditions. The study benchmarks modern generative models for multivariate time-series synthesis with the future objective of using synthetic training data augmentation to improve robustness of data-driven models on previously unseen test configurations. Rather than treating this augmentation as a simple increase in sample size, the generated data are assessed along three complementary dimensions: temporal and distributional fidelity, diversity and coverage of underrepresented operating regimes, and physical plausibility of the synthesized responses.

This study investigates the influence of offset vehicle impacts on the performance of anchored vehicle security barriers using finite element simulations in LS-DYNA. Increasing occurrences of terrorist attacks in public spaces have led to the deployment of both mobile and permanent protective barriers; however, current testing methodologies assume central impacts. The FEM model of an M1 vehicle was coupled with a multifunctional anchored barrier system integrated into urban infrastructure elements. Vehicle impacts at velocities of 15, 50, and 80 km/h were analysed with lateral offsets up to 1000 mm, resulting in 19 configurations for each velocity. The study evaluates barrier effectiveness through analysis of vehicle penetration, crash progression, anchorage response, and force distribution within the anchors, considering both shear and axial loading. The results demonstrate that increasing lateral offset significantly influences barrier response and vehicle penetration, highlighting the importance of considering non-central impacts in future barrier design and standard development.

This study investigates the performance of mobile and permanent vehicle security barrier systems using finite element simulations under varying impact conditions. The primary objective is to evaluate the influence of barrier rotational angle relative to the vehicle impact direction and anchor placement on barrier performance, while identifying key mechanisms governing vehicle–barrier interaction that may support future barrier development. The proposed barrier system consists of modular units that also serve as flowerpots, representing a multifunctional concept that combines security performance with environmental and aesthetic functions. In addition to conventional assessment metrics such as final penetration and vehicle velocity, the adopted evaluation framework considers their evolution throughout the impact together with vehicle and barrier energy response, front axle motion, and anchor loading and failure. The results indicate that the proposed barrier configurations predominantly function as deceleration systems rather than fully effective restraint systems. The influence of barrier rotational angle on the permanent barrier was more pronounced at the lower impact velocity (15 km·h⁻¹) but diminished at higher impact velocities (50 and 80 km·h⁻¹), with maximum differences of approximately 440 mm in penetration and 2.6 km·h⁻¹ in final vehicle velocity. The influence of anchor placement alone was smaller, resulting in maximum differences of approximately 378 mm in penetration and 1 km·h⁻¹ in final vehicle velocity. Analysis of crash progression provided further insight into the relationship between anchorage failure, barrier mobilization, front axle motion, and changes in vehicle deceleration. These observations may support the further development and assessment of vehicle security barrier systems.