A grey-ANN approach for optimizing the QFN component assembly process for smart phone application

Abstract

Purpose This paper aims to propose an innovative parametric design for artificial neural network (ANN) modeling for the multi-quality function problem to determine the optimal process scenarios. Design/methodology/approach The innovative hybrid algorithm gray relational analysis (GRA)-ANN and the GRA-Entropy are proposed to effectively solve the multi-response optimization problem. Findings Both the GRA-ANN and the GRA-Entropy analytical approaches find that the optimal process scenario is a stencil aperture of 57 per cent and immediate processing of the printed circuit board after exposure to a room environment. Originality/value A six-week confirmation test indicates that the optimal process has improved quad flat non-lead assembly yield from 99.12 to 99.78 per cent.