数据驱动的伸缩臂臂架动态应力预测

Dynamic Stress Prediction of Telescopic Boom by Data Driven

为探究伸缩臂叉车在过坎过程中其臂架应力变化,得到一种高效计算过坎时臂架应力的方法。通过试验测试得到俯仰油缸推力与加速度的关系,在俯仰油缸推力的最大值与最小值之间均匀抽取样本点,基于有限元法,计算出样本点对应的等效应力,使用样本点中的自变量与等效应力构建代理模型,通过臂架过坎过程中俯仰油缸推力来预测臂架应力。使用多项式响应面模型预测应力,测点试验值与预测值皮尔逊系数达到0.9以上,预测时间为2.7ms。因此,针对过坎工况臂架应力探究,使用代理模型来预测结构应力,能够大大减少计算时间,节约计算资源,对代理模型在伸缩臂臂架应力预测领域的应用具有指导意义。

In order to explore the stress change of boom of telescopic boom forklift in the process of crossing the sill,an efficient method for calculating the stress of boom when crossing the sill is obtained.The relationship between thrust of pitch cylinder and acceleration is obtained through the test data.The sample points are evenly selected between the maximum and minimum values of the thrust of the pitch cylinder,and the equivalent stress corresponding to the sample points is calculated based on the finite element method.Use the independent variables and equivalent stresses in the sample points to build a surrogate model and predict the boom stress by the pitching cylinder thrust during the boom passing process.Using the polynomial response surface model to predict the stress,the Pearson coefficient of both the test value and the predicted value of the measuring point reached more than 0.9,and the prediction time was 2.7ms.Thus,For the boom stress exploration under sill crossing condition,using an appropriate surrogate model to predict the structural stress can greatly reduce the calculation time and save the calculation resources,which has guiding significance for the application of surrogate model in the field of telescopic boom stress prediction.