Metamodel Sensitivity to Sampling Strategies: A Crashworthiness Design Study

A study is conducted to determine the sensitivity of 2 topologically distinct metamodel types to variations in the experimental design brought about by sequential adaptive sampling strategies. The study focuses on examples encountered in crashworthiness design. Three sampling strategies are considered for updating the experimental designs, namely (i) a single stage approach, (ii) a sequential approach and (iii) a sequential approach, but with higher densities in local regions. The experimental design type is the Space Filling Method based on maximizing the minimum distance between any two design points within a subdomain. Feedforward Neural Networks (NN) and Radial Basis Function Networks (RBF) are compared with respect to their sensitivity when applied to these strategies. A large set of independent checkpoints, constructed using a Latin Hypercube Sampling method is used to evaluate the accuracy of the various strategies. Four examples are used in the evaluation, namely (i) simple two- variable two-bar truss, (ii) the 21 variable Svanberg problem, (iii) a 7 variable full vehicle crash example and (iv) a 11 variable knee impact crash example. The example, analyzed using LS-OPT® for metamodeling and LS-DYNA® for FE modeling, reveal the following: while expensive to construct, NN committees tend to be superior in predictability whereas the much cheaper RBF networks, can sometimes be highly sensitive to irregularity of experimental designs caused by subdomain updating. However, this conclusion cannot be extended to the crash problems tested, since the RBF networks performed consistently well for these examples.