During the design cycle of safety critical vehicle components such as B-pillars, crashworthiness performance is a key metric for passenger protection assessment in vehicle accidents. Traditional finite element simulations for crashworthiness analysis involve complex modelling, leading to an increased computational demand. Although a few machine learning-based surrogate models have been developed for rapid predictions for crashworthiness analysis, they exhibit limitations in detailed representation of complex 3D components. Graph Neural Networks (GNNs) have emerged as a promising solution for processing data with complex structures. However, existing GNN models often lack sufficient accuracy and computational efficiency to meet industrial demands. This paper proposes Recurrent Graph U-Net (ReGUNet), a new graph-based surrogate model for crashworthiness analysis of vehicle panel components. ReGUNet adoptes a U-Net architecture with multiple graph downsampling and upsampling layers, which improves the model's computational efficiency and accuracy; the introduction of recurrence enhances the accuracy and stability of temporal predictions over multiple time steps. ReGUNet is evaluated through a case study of side crash testing of a B-pillar component with variation in geometric design. The trained model demonstrates great accuracy in predicting the dynamic behaviour of previously unseen component designs within a relative error of 0.74% for the maximum B-pillar intrusion. Compared to the baseline models, ReGUNet can reduce the averaged mean prediction error of the component's deformation by more than 51% with significant improvement in computational efficiency. Provided enhanced accuracy and efficiency, ReGUNet shows greater potential in accurate predictions of large and complex graphs compared to existing models.

Blind spots created by the driver-side B-pillar impair the ability of the driver to assess their surroundings accurately, significantly contributing to the frequency and severity of vehicular accidents. Vehicle manufacturers are unable to readily eliminate the B-pillar due to regulatory guidelines intended to protect vehicular occupants in the event of side collisions and rollover incidents. Furthermore, assistance implements utilized to counteract the adverse effects of blind spots remain ineffective due to technological limitations and optical impediments. This paper introduces mechanisms to quantify the obstruction caused by the B-pillar when the head of the driver is facing forward and turning 90 degrees, typical of an over-the-shoulder blind spot check. It uses the metrics developed to demonstrate the relationship between B-pillar width and the obstruction angle. The paper then creates a methodology to determine the movement required of the driver to eliminate blind spots. Ultimately, this paper proposes a solution, the Blind Spot Eliminator, and demonstrates that it successfully decreases both the obstruction angle and, consequently, the required driver movement. A prototype of the Blind Spot Eliminator is also constructed and experimented with using a mannequin to model human vision in a typical passenger vehicle. The results of this experiment illustrated a substantial improvement in viewing ability, as predicted by earlier calculations. Therefore, this paper concludes that the proposed Blind Spot Eliminator has excellent potential to improve driver safety and reduce vehicular accidents. Keywords: B-pillar, driver vision, active safety, blind spots, transportation, crash avoidance, side-view assist.