论文部分内容阅读
Because of the light weight,high stiffness and high structural efficiency,aluminium alloy integral panels are widely used on modern aircrafts.Press bend forming has many advantages,and it becomes a significant technique in aircraft manufacturing field.In order to design the press bend forming path for aircraft integral panels,we propose a novel optimization method which integrates the finite element method(FEM) equivalent model based on our previous study,the artificial neural network response surface,and the genetic algorithm. First,a multi-step press bend forming FEM equivalent model is established,with which the FEM experiments designed with Taguchi method are performed.Then,the backpropagation(BP) neural network response surface is developed with the sample data from the FEM experiments.Further more,genetic algorithm(GA) is applied with the neural network response surface as the objective function.Finally,experimental and simulation verifications are carried out on a single stiffener specimen.The forming error of the panel formed with the optimal path is only 5.37%and the calculating efficiency has been improved by 90.64%.Therefore,this novel optimization method is quite efficient and indispensable for the press bend forming path designing.
Because of the light weight, high stiffness and high structural efficiency, aluminum alloy integral panels are widely used on modern aircrafts. Press bend forming has many advantages, and it becomes a significant technique in aircraft manufacturing field. Order to design the press bend forming path for aircraft integral panels, we propose a novel optimization method which integrates the finite element method (FEM) equivalent based on our previous study, the artificial neural network response surface, and the genetic algorithm. First, a multi-step press bend forming FEM equivalent model is established, with which the FEM experiments designed with Taguchi method are performed. Chen, the backpropagation (BP) neural network response surface is developed with the sample data from the FEM experiments. Future more, genetic algorithm (GA) is applied with the neural network response surface as the objective function. Finally, experimental and simulation verifications are carried out on a single stiffen er specimen. The forming error of the panel formed with the optimal path is only 5.37% and the calculating efficiency has been improved by 90.64% .Therefore, this novel optimization method is quite efficient and indispensable for the press bend forming path designing.