Innovative Virtual Evaluation Process for Outer Panel Stiffness Using Deep Learning Technology

During the vehicle lifecycle, customers are able to directly perceive the outer panel stiffness of vehicles in various environmental conditions. The outer panel stiffness is an important factor for customers to perceive the robustness of the vehicle. In the real test of outer panel stiffness after prototype production, evaluators manually press the outer panel in advance to identify vulnerable areas to be tested and evaluate the performance only in those area. However, when developing the outer panel stiffness performance using FEA (Finite Element Analysis) before releasing the drawing, it is not possible to filter out these areas, so the entire outer panel must be evaluated. This requires a significant amount of computing resources and manpower. In this study, an approach utilizing artificial intelligence was proposed to streamline the outer panel stiffness analysis and improve development reliability. A deep learning-based prediction technology was developed to predict force-displacement curves of target evaluation points from structural images extracted from the finite element model. Convolutional neural network-based prediction models for the entire outer panel systems were constructed, and the key factors influencing outer panel stiffness were identified and analyzed using the Grad-CAM technique. Additionally, an innovative virtual process was proposed, which uses AI to predict vulnerable areas in advance and perform confirmation analysis solely on those areas. The effectiveness and innovativeness of this process were verified through pilot application in the regular development stage. This process promises a 90% reduction in analysis workload for outer panel stiffness evaluation, significantly boosting vehicle development efficiency. Furthermore, it is expected to significantly improve the drawing completeness.