Process reliability modeling based on nonlinear correlation analysis

Abstract

The analysis of the manufacturing process that formed the product inherent reliability and the determination of the key technological factors that have great influence on product inherent reliability can be the foundation of the process control and process improvement. And in order to improve the prediction accuracy and efficiency of the model, the input variables were selected firstly based on the analysis of input and output variables correlation. Firstly, the regularity of the product inherent reliability formed in manufacturing process was obtained through the analysis of production process. secondly, the estimation method of mutual information based on the copula entropy was given. thirdly, the steps choosing the key process factors were proposed based on the nonlinear correlation analysis. And finally the feasibility and practicability of the method were indicated by an application case.