Optimal Design of Geometrically Nonlinear Space Trusses Using an Adaptive Neuro-Fuzzy Inference System

An ecient methodology is proposed to optimize space trusses considering geometric nonlinearity. The optimization task is performed by a continuous Particle Swarm Optimization (PSO). Design variables are cross sectional areas of the trusses and their weights are also taken as the objective function. Design constraints are de ned to restrict nodal displacements and element stresses and prevent the overall elastic instability of the structures during the optimization procedure. In order to reduce the computational e ort of the optimization process, an Adaptive Neuro Fuzzy Inference System (ANFIS) is employed to approximate the nonlinear analysis of the structures instead of performing via a time consuming Finite Element Analysis (FEA). The presented ANFIS is compared with a Back Propagation Neural Network (BPNN) and appears to produce a better performance generality for evaluating structure design values. Test example results demonstrate the computational advantages of the suggested methodology for optimum design of geometrically nonlinear space trusses. Keywords: Space truss; Geometric nonlinearity; Particle swarm optimization; Approximation concepts; Adaptive neuro fuzzy inference system.