To achieve lightweight design for an electric light-duty cargo vehicle and enhance its overall reliability and endurance mileage, a finite element modeling of its frame is conducted. Static performance, modal performance and fatigue life analysis are performed to identify the weak spots in its strength under torsional conditions. Through sensitivity analysis, 19 key plate thicknesses and 2 crossbeam section widths are identified as design variables. An Optimal Latin Hypercube Design (OLHD) is employed to generate 260 training samples and 28 validation samples. A high-precision surrogate optimization model is constructed using a Radial Basis Function (RBF) network model. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is utilized for multi-objective optimization, aiming to minimize the frame mass and the maximum deformation under torsional conditions. The validation results showed that after optimization, the total frame mass decreased from 574 kg to 533 kg, the maximum stress reduced by 19.73%, the safety factor increased to 1.58, the maximum deformation under torsional conditions decreased by 5.61%, the first-order natural frequency increased by 4.21%, the fatigue life under the weakest torsional condition improved by 3.96%, and the comprehensive safe driving mileage increased to 87.300×10⁴ km, meeting and exceeding the design requirements.

Commercial vehicle frame  /  Lightweight design  /  Multi-objective optimization  /  Fatigue life analysis