Bayesian optimization of tailgate rib structures enhancing structural stiffness under manufacturing constraints of injection molding

Abstract

The shift towards environmentally friendly transportation has driven significant attention to lightweight vehicle design, especially to counterbalance the substantial weight of batteries in electric vehicles. Reinforced polymer composites offer a promising alternative to traditional steel due to their lower density. However, to overcome the inherent stiffness limitations of mass-produced short fiber reinforced polymer composites manufactured through compounding and injection molding, the use of internal reinforcing structures, such as ribs, is essential. This study proposes a cost-effective, data-driven approach to parametrize and optimize rib placement within automotive tailgate components. The primary objective is to maximize structural stiffness, evaluated with industry-standard testing methods for tailgate components, while adhering to mass constraints. Rib structures are parametrized with a focus on simplicity to reduce data requirements, accounting for manufacturing constraints inherent to injection molding and maintaining permutation invariance of rib designs. Given the high cost of evaluating variety of rib configurations, Bayesian optimization is applied for efficient data utilization. Gaussian process regression is used as a surrogate model to predict structural stiffness, based on finite element analysis data from various rib configurations. The optimized design is then fabricated as full-scale prototypes through injection molding, and their performance is validated against numerical predictions. This approach exemplifies a practical, data-driven methodology for designing rib structures in complex industrial components, integrating computational design with manufacturing processes.