Stochastic Models of Quality Level of Mechatronic Products

Abstract

Method is offered for synthesis of stochastic distributions of defectivity levels of multiparametric mechatronics products with interindependent parameters. This synthesis can be performed in groups of parameters or for entire product according to known distributions of defectivity levels of separate parameters. Synthesis models of density functions were presented, when defectivity levels of separate parameters are distributed according to beta law, with minimal whole-number values of one of the shape parameters. Limitations were determined, when defectivity levels are also described by beta-distribution according to parameter groups or for entire product. It was shown, that in such case models is considerably simplified, since multi-integration procedure is no longer needed, and also complex density models are not required any more. It was offered to use approximation by beta-density when any values of betadistribution shape parameters are present. Although it was noted, that when the number of product parameters increases, approximation precision decreases. For practical applications it is advisable to differentiate average defectivity levels of separate parameters according to selected defectivity level of entire product, when ratio between defectivity levels in separate groups is selected or according to needed dispersion of parameters (selected variation coefficient). Ill. 7, bibl. 12 (In English; summaries in English, Russian and Lithuanian).