筒形件错距旋压成形工艺参数优化

Optimization of process parameters for tubular parts stagger spinning

错距旋压成形过程高度非线性,特别是对于多目标优化问题,其工艺参数与目标函数之间的关系一般很难用精确的数学函数表达。该文基于正交试验,以旋压件椭圆度、直线度、壁厚偏差为评价指标,选择旋压进给比、总减薄率、轴向错距为试验因素,获得16组正交试验数据。采用灰色关联度方法对所构造的正交试验数据进行分析处理,将多目标优化问题转化为单目标优化问题;应用支持向量机网络回归模型,并结合遗传算法对错距旋压过程进行寻优,获得了优化的20钢筒形件错距旋压成形工艺参数。试验结果表明,所获得的优化工艺参数可有效提高旋压制件的成形质量。

Process of tubular parts stagger spinning has the characteristic of high non-linear, and the relationships between the process parameters and the objective function, especially for the multiobjective optimization problem, are generally difficult to express by the precise mathematic equations. The 16 groups of orthogonal experimental data were obtained based on the orthogo nal design method by taking the ovality, straightness and wall thickness deviation as the evaluation indexes, and the feed ratio of roller, total thinning ratio and axial offset between rollers as the experimental factors. The 16 groups of data were analyzed based on Grey Relational Analysis, and the multi-objective optimization problem was then turned to be the single-objective optimization problem. The process of tube stagger spinning was optimized by combining the Support Vector Machine Network Regression Model and Genetic Algorithm, and the optimized process parameters for stagger spinning of steel 20 tube were obtained. The corresponding verification experiment was carried out. The result showed that the forming quality of spun tube could be improved effectively by the optimized process parameters.