An artificial neural network-differential evolution approach for optimization of bidirectional functionally graded beams

Abstract

A novel and effective artificial neural network (ANN)-differential evolution (DE) approach as an integration of ANN into DE is first introduced to the material distribution optimization of bidirectional functionally graded (BFG) beams under free vibration. In this methodology, ANN is utilized as an analyzer to predict responses of BFG beams instead of directly solving eigenvalue problems via time-consuming finite element analyses (FEAs). Meanwhile, DE is employed as an optimizer for optimization problems without complex sensitivity analyses. Accordingly, the ANN-DE significantly reduces the computational cost, yet still achieving a high-quality global solution. The material volume fraction at control points defined based on the isogeometric analysis (IGA) concept is taken as continuous design variables. Optimal material profiles are represented by two-dimensional Non-Uniform Rational B-spline (NURBS) basis functions. Obtained results are compared with those of existing literature to demonstrate the accuracy and reliability of the proposed paradigm. Additionally, the ANN-DE is also applied to several other examples to further prove its effectiveness and robustness in dramatically saving the computational efforts, while still yielding optimal outcomes with high accuracy.