The method for the control of an industrial process through an electronic processing system associated with a production line includes performing a statistical test ¦ verifying the properties of a group of products obtained through the process, the power of which provides reproducibility/sensitivity information about the test and comprises the operations of: producing a pilot sample including n exemplars of the product obtained through that process, acquiring measured data ( X 1 , ..., X n ) for an observed variable relating to that sample having a distribution F n approximating to the unknown F distribution for the observed variable, determining a minimum sample size on which the test is performed such that the lower bound ( À ^ F n , , l ± 1 ( m ) ) for a confidence interval of predetermined level (1-±1) associated with the bootstrap distribution for the pointwise estimate of the power of the test performed on a sample of that size extracted from the pilot sample of distribution F n , is equal to or greater than a predetermined desired power value, and producing a sample of products to be subjected to that ¦ test including m exemplars equal to the sample size determined, where the outcome of the test determines control of the process in accordance with a predetermined criterion.
展开▼
机译:通过与生产线关联的电子处理系统控制工业过程的方法包括执行统计测试¦验证通过该过程获得的一组产品的属性,其能力提供有关该测试的可重复性/敏感性信息并包括以下操作:产生包括n个通过该过程获得的产品样本的中试样品,获取与该样品有关的观测变量的测量数据(X 1,...,X n),其分布F n近似为观察变量的未知F分布,确定执行测试的最小样本量,以使下限(^ F n,,l±1(m))达到预定水平(1-± 1)与bootstrap分布相关联,以对th个样本执行的测试的功效进行逐点估计从分布F n的试验样本中提取的样本的大小等于或大于预定的期望功效值,并生成要进行该γ测试的产品样本,其中包括等于所确定样本大小的m个样本,其中结果测试的“确定”根据预定标准确定对过程的控制。
展开▼