Skip to Main Content
Light-emitting diodes (LEDs) have been adopted in a wide variety of lighting situations. As lighting technology evolves, illumination devices are moving toward miniaturization and high-power applications. Packaging of illumination devices is essential to providing a path for heat dispersion. A full understanding of the viscosity change of the encapsulation material is critical to ensure manufacturability and improved process yield. The typical viscosity model is the initial viscosity plus the change in viscosity over time at a given temperature. The change in viscosity is a function of the reaction rate and the pro-exponential factor. This paper includes the pro-exponential factor in the regression model to improve the prediction accuracy. Through experimental data, the material's viscosity is determined as a function of process temperature, the ratio of the curing agent, and the curing time. A computer-aided parametric design is used to assess the effect of the variation of individual factors on the quality function and proposes a robust LED encapsulation process. An artificial neural network that considers interactions between parameters and establishes fitness functions is used to further enhance the accuracy of predictions and determine the optimal process solution through an iterative training algorithm. The optimal process scenario suggested by this research is a 10% curing agent preheated at 333°K for 40 min. This robust process can improve the signal-to-noise ratios by approximately 43%.