Inverse problem based differential evolution for efficient structural health monitoring of trusses

This paper proposes the integration of an inverse problem process using radial basis functions (RBFs) into meta-heuristics (MHs) for performance enhancement in solving structural health monitoring optimisation problems. A differential evolution (DE) algorithm is chosen as the MH for this study. In this work, RBF is integrated into the DE algorithm for generating an approximate solution rather than approximating the function value as with traditional surrogate-assisted optimisation. Four structural damage detection test problems of two trusses are used to examine the search performance of the proposed algorithms. The results obtained from using various MHs and the proposed algorithms indicate that the new algorithm is the best for all test problems. DE search performance for structural damage detection can be considerably improved by integrating RBF into its procedure. (C) 2018 Elsevier B.V. All rights reserved.