Design History Retrieval Based Structural Topology Optimization

This paper presents a novel topology optimization (TO) method which relies on design history retrieval and surrogate modeling. With this method, a new design case starts by retrieving the design history to find similar cases in both design domain geometry and boundary condition (BC), for which an innovative BC similarity evaluation has been developed. For the best-match history case, feature based topological design was available in database and is predictably similar to that of the new design case. Therefore, it can be used as the feature model input of the new design case, and the TO problem is simplified into a sizing optimization problem to find the optimal feature parameter set. Surrogate model based method has been employed to solve the sizing optimization problem. Overall, this new TO method characterizes as: first, the efficiency is much higher than the conventional TO methods; second, it obtains feature-based topological design without post-treatment effort.