Modelling and optimization of fluid dispensing for electronic packaging using neural fuzzy networks and genetic algorithms

Abstract

Determination of process conditions for a fluid dispensing process of microchip encapsulation is a highly skilled task, which is usually based on engineers' knowledge and intuitive sense acquired through long-term experience rather than on a theoretical and analytical approach. Facing with the global competition, the current trial-and-error approach is inadequate. Modelling the fluid dispensing process is important because it enables us to understand the process behaviour, as well as determine the optimum operating conditions of the process for a high yield, low cost and robust operation. In this research, modelling and optimization of fluid dispensing processes based on neural fuzzy networks and genetic algorithms are described. First, neural fuzzy networks approach is used to model fluid dispensing process for microchip encapsulation. An N-fold validation tests were conducted. Results of the tests indicate that the mean errors and variances of errors of the modeling based on the neural fuzzy networks approach are all better than those of the other existing approaches, statistical regression, fuzzy regression and neural networks, on modeling the fluid dispensing. It is then followed by the determination of process conditions of the process based on a genetic algorithm approach. Validation tests were conducted. Results of them indicate that process conditions determined based on the proposed approaches can achieve the specified quality requirements.