In order to find out the optimal press bend forming path in fabricating aircraft integral panels, this article proposes a new method on the basis of the authors' previous work. It is composed of the finite element me...In order to find out the optimal press bend forming path in fabricating aircraft integral panels, this article proposes a new method on the basis of the authors' previous work. It is composed of the finite element method (FEM) equivalent model, the surface curvature analysis, the artificial neural network response surface and the genetic algorithm. The method begins with analyzing the objective's shape curvature to determine the bending position. Then it optimizes the punch travel at each bending position by the following steps: (1) Establish a multi-step press bend forming FEM equivalent model, with which the FEM ex- periments designed with the Taguchi method are performed. (2) Construct a back-propagation (BP) neural network response surface with the data from the FEM experiments. (3) Use the genetic algorithm to optimize the neural network response surface as the objective function. Finally, this method is verified by press bending a complicated double-curvature grid-type stiffened panel and bears out its effectiveness and intrinsic worth in designing the press bend forming path.展开更多
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 techniq...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.展开更多
Pulsed TIG welding–brazing process was applied to join aluminum with stainless steel dissimilar metals. Major parameters that affect the joint property significantly were identified as pulsed peak current, base curre...Pulsed TIG welding–brazing process was applied to join aluminum with stainless steel dissimilar metals. Major parameters that affect the joint property significantly were identified as pulsed peak current, base current, pulse on time,and frequency by pre-experiments. A sample was established according to central composite design. Based on the sample,response surface methodology(RSM) and artificial neural networks(ANN) were employed to predict the tensile strength of the joints separately. With RSM, a significant and rational mathematical model was established to predict the joint strength.With ANN, a modified back-propagation algorithm consisting of one input layer with four neurons, one hidden layer with eight neurons, and one output layer with one neuron was trained for predicting the strength. Compared with RSM, average relative prediction error of ANN was /10% and it obtained more stable and precise results.展开更多
基金Specialized Research Fund for the Doctoral Program of High Education of China (20091102110021)
文摘In order to find out the optimal press bend forming path in fabricating aircraft integral panels, this article proposes a new method on the basis of the authors' previous work. It is composed of the finite element method (FEM) equivalent model, the surface curvature analysis, the artificial neural network response surface and the genetic algorithm. The method begins with analyzing the objective's shape curvature to determine the bending position. Then it optimizes the punch travel at each bending position by the following steps: (1) Establish a multi-step press bend forming FEM equivalent model, with which the FEM ex- periments designed with the Taguchi method are performed. (2) Construct a back-propagation (BP) neural network response surface with the data from the FEM experiments. (3) Use the genetic algorithm to optimize the neural network response surface as the objective function. Finally, this method is verified by press bending a complicated double-curvature grid-type stiffened panel and bears out its effectiveness and intrinsic worth in designing the press bend forming path.
基金the National Natural Science Foundation of China(Nos.51205004 and 51005010)
文摘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.
基金financially supported by the National Natural Science Foundation of China (No. 50874033)
文摘Pulsed TIG welding–brazing process was applied to join aluminum with stainless steel dissimilar metals. Major parameters that affect the joint property significantly were identified as pulsed peak current, base current, pulse on time,and frequency by pre-experiments. A sample was established according to central composite design. Based on the sample,response surface methodology(RSM) and artificial neural networks(ANN) were employed to predict the tensile strength of the joints separately. With RSM, a significant and rational mathematical model was established to predict the joint strength.With ANN, a modified back-propagation algorithm consisting of one input layer with four neurons, one hidden layer with eight neurons, and one output layer with one neuron was trained for predicting the strength. Compared with RSM, average relative prediction error of ANN was /10% and it obtained more stable and precise results.