Optimization of nanocomposite integral capacitor fabrication using neural networks and genetic algorithms

Thin film integral capacitors using polymer-ceramic composites have been developed for next-generation electronic packaging applications. To achieve a high dielectric constant, bimodal ceramic particle distributions, along with particles modified by a surfactant and mixed ultrasonically with the polymer have been explored. This paper presents a statistically designed experiment for systematic characterization of the dielectric constant and loss tangent of integral capacitors formed in this manner by using barium titanate particles in an epoxy polymer dielectric. We determine these quantities as a function of the particle size of the ceramic, the volume fraction of ceramic in the polymer matrix, the polymer cure time, the polymer cure temperature, the percent of surfactant, the ultrasonic mixing time, and the ball milling time for ceramic surface modification. These factors are examined by means of a partial factorial experiment requiring 32 runs. Further experimentation is performed to generate sufficient data for process modeling. To develop such models, we train neural networks to model the variation as a function of input variables using the experimental data. These models are then used for process optimization using genetic algorithms. Using this methodology, we determine the proper combination of polymer/ceramic materials and process conditions to achieve desirable electrical properties.