【摘要】 为确定飞机整体壁板压弯成形的压弯路径,在前期研究所提出的有限元等效模型的基础上,提出一套集成了曲面曲率分析、等效模型、人工神经网络响应面和遗传算法的全新的优化方法。首先通过对目标形面的曲率分析确定压弯位置,再优化确定每个位置的下压量。下压量的优化方法是:建立多道次压弯成形有限元模拟等效模型来进行正交试验,并将试验结果作为选择神经网络样本点来构建BP神经网络响应面,随后以神经网络响应面为目标函数,应用遗传算法进行优化。最后以网格式复杂双曲率整体壁板压弯成形为例验证此方法,结果表明此优化方法对于确定压弯路径具有很高的效率和重要的作用。更多还原

【Abstract】 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 experiments 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.更多还原