论文部分内容阅读
采用模拟退火算法优化基于加权平均法的拉丁超立方设计,获得了拉延筋阻力样本。采用Dynaform对翼子板成形进行仿真,以最大增厚和最大减薄作为输出目标,采用改进的粒子群优化BP算法,建立拉延筋映射模型,与单纯采用PSO-BP建立的映射模型进行对比,预测精度大幅提高。采用粒子群算法对映射模型进行优化,得到最优拉延筋阻力,采用非线性函数优化方法求得最优的拉延筋几何参数。采用等效拉延筋阻力模型,避免了有限元网格的重划分和采用真实拉延筋带来的计算效率低的问题,成形效果图说明了采用该方法可以获得较好的最优拉延筋几何参数。
The simulated annealing algorithm was used to optimize the Latin hypercube design based on the weighted average method, and the drawbead resistance samples were obtained. The fender forming is simulated by Dynaform, the maximum thickening and the maximum thinning are taken as the output targets. The improved Particle Swarm Optimization (BP) algorithm is used to establish the drawbead mapping model, which is compared with the mapping model established solely by PSO-BP , The prediction accuracy is greatly improved. Particle swarm optimization is used to optimize the mapping model to obtain the optimal drawbead resistance. The optimal drawbead geometrical parameters are obtained by the nonlinear function optimization method. The equivalent drawbead resistance model is adopted to avoid the problem of re-division of the finite element mesh and the calculation inefficiency caused by the actual drawbead. The forming effect diagram shows that the optimal drawbead can be obtained by using the method Geometrical parameters.