A machine learning-based surrogate model for optimization of truss structures with geometrically nonlinear behavior

Abstract

Design optimization of geometrically nonlinear structures is well known as a computationally expensive problem by using incremental-iterative solution techniques. To handle the problem effectively the optimization algorithm needs to ensure that the trade-off between the computational time and the quality of the solution is found. In this study, a deep neural network (DNN)-based surrogate model which integrates with differential evolution (DE) algorithm is developed and applied for solving the optimum design problem of geometrically nonlinear space truss under displacement constraints and refer to the approach as DNN-DE. Accordingly, this surrogate model, also is known as a deep neural network, is established to replace conventional finite element analyses (FEAs). Each dataset is created based on FEA which employs the total Lagrangian formulation and the arc-length procedure. Several numerical examples are given to demonstrate the efficiency and validity of the proposed paradigm. These results indicate that the proposed approach not only reduces the computational cost dramatically but also guarantees convergence. • A machine learning-based surrogate model is proposed to integrate with DE algorithm for solving the optimum structure. • The deep neural network is capable of exactly predicting the displacement of nonlinear response. • The combining method is effective, reduces the computational time, and guarantees solution accuracy.