Multi-source uncertainty considered assembly process quality control based on surrogate model and information entropy

Abstract

As an indispensable stage of product manufacturing, assembly process plays an important role in assuring product reliability by curbing the variation of assembly quality characters. The characters, mainly affected by the uncertainty components quality and assembly process parameters, are formed in a complex process. This paper approaches the uncertainty analysis of the assembly quality characters and the determination of key quality influence factors under multi-source uncertainty. Firstly, the fuzzy theory-based analytic hierarchy process(FAHP) is carried out to identify the main factors and the information entropy method is used to transfer them into uniform uncertainty variables. Secondly, the support vector regression (SVR) method is used to establish the surrogate model between the influence factors and assembly quality characters. Monte Carlo simulation (MCS) is employed for uncertainty analysis and sensitivity analysis of assembly process on the basis of the surrogate model and data sampling, which realize the prediction of assembly quality and the determination of key process parameters. Finally, a case study of a bolt assembly process is used to verify the effectiveness of the proposed method. The proposed method in this paper is efficient and simple to apply in manufacturing applications directly.