论文部分内容阅读
有限元(FE)分析已成为轮胎行业虚拟研究轮胎备受青睐的工具,因为它能模拟轮胎胎体的接合部细节。然而,在轮胎设计开发中应用有限元分析依然非常耗时,且花费不菲。在此,对应用各种人工神经网络(ANN)结构来预测轮胎性能进行了评估,以便选择最有效和最高效的结构。这样我们可在用花费高得多的全过程有限元分析进行证实预测的性能之前,以花费不多的费用进行广泛的参数研究,以便优化轮胎设计。
Finite element (FE) analysis has become a popular tool for virtual tire research in the tire industry as it can simulate the joint details of the tire carcass. However, applying finite element analysis to tire design and development is still time-consuming and costly. Here, the application of various artificial neural network (ANN) structures to evaluate tire performance was evaluated in order to select the most efficient and efficient structure. This allows us to conduct a wide range of parametric studies at a fraction of the cost to optimize the tire design, before using the full-process FEA to prove the predicted performance.