基于Sobol序列采样点分布策略的研究与应用

Research and application of sampling point distribution strategy based on Sobol sequence

随着我国机械制造业的迅猛发展,人们对机械产品的质量提出了越来越高的要求。其中,零部件的尺寸精度被认为是保证产品质量的最重要的指标之一。为了提高零部件的尺寸测量精度,本文提出了Sobol序列采样点分布策略,选取了有效的采样点数量并对采样点分布质量进行优化。通过数值计算与对实际零件的检测试验,研究了采样点的数量和分布特征对测量精度的影响。通过测量实验选出最佳的采样点数量并利用拟蒙特卡洛随机序列进行对比和分析,得到分布均匀性更好、收敛速度更快的Sobol序列模型。将Sobol序列模型的输出结果作为三坐标测量机的输入数据,通过对实际产品的实测证明了Sobol序列采样点分布策略优于测量机自带的采样点策略。

With the rapid development of China's machinery manufacturing industry,people have put forward higher and higher requirements for the quality of mechanical products.Among them,the dimensional accuracy of parts is considered to be one of the most important indicators to ensure product quality.In order to improve the dimensional measurement accuracy of parts,the Sobol sequence sampling point distribution strategy has been proposed in the text.The effective number of sampling points have been selected and sampling point distribution quality has been optimized.The influence of the number and distribution characteristics of the sampling points on the measurement accuracy has been studied through numerical calculations and testing tests on actual parts.The best number of sampling points has been selected through measurement experiments,and a pseudo-Monte Carlo random sequence has been used for comparison and analysis.The Sobol sequence model with better distribution uniformity and faster convergence speed has been obtained.Taking the output of the Sobol sequence model as the input data of a three-coordinate measuring machine,the actual measurement of actual products proves that the Sobol sequence sampling point distribution strategy is better than the sampling point strategy of the measuring machine.