Crashworthiness design of automotive double-cell thin-walled tubes under oblique loading based on data mining

The deformation behavior of automotive double-cell thin-walled tubes under oblique loading is inherently complex. To address this crashworthiness design challenge, this study employs a decision-tree-based data-mining method to guide the structural design of thin-walled tubes. In contrast to conventional black-box optimization approaches, the proposed approach not only accomplishes structural optimization but, more importantly, derives design rules for the tubes, enabling critical parameter identification and design domain reduction. By analyzing the crashworthiness responses of double-cell tubes under oblique loading, the method establishes an interpretable linkage between design variables and crashworthiness performance, thereby providing engineers with design guidance. The results show that the optimization design efficiency based on data mining improved by nearly 10 times relative to traditional methods, highlighting its potential to significantly reduce design time and development cost.