MODELING THE GROWTH OF PECVD SILICON-NITRIDE FILMS FOR SOLAR-CELL APPLICATIONS USING NEURAL NETWORKS

Silicon nitride films grown by plasma-enhanced chemical vapor depositi on (PECVD) are useful for a variety of applications, including anti-re flection coatings in solar cells, passivation layers, dielectric layer s in metal/insulator structures, and diffusion masks, PECVD nitride fi lms are known to contain hydrogen, and defect passivation by hydrogena tion enhances efficiency in polycrystalline silicon solar cells, PECVD systems are controlled by many operating variables, including RF powe r, pressure, gas how rate, reactant composition, and substrate tempera ture, The wide variety of processing conditions, as well as the comple x nature of particle dynamics within a plasma, makes tailoring Si3N4 f ilm properties very challenging, since it is difficult to determine th e exact relationship between desired film properties and controllable deposition conditions, In this study, silicon nitride PECVD modeling u sing neural networks has been investigated, The deposition of Si3N4 wa s characterized via a central composite experimental design, and data from this experiment was used to train optimized feed-forward neural n etworks using the back-propagation algorithm, From these neural proces s models, the effect of deposition conditions on film properties has b een studied, It was found that the process parameters critical to incr easing hydrogenation and therefore enhancing carrier lifetime in polys ilicon solar cells are temperature, silane, and ammonia flow rate, The deposition experiments were carried out in a Plasma Therm 700 series PECVD system.