Modeling the growth of PECVD silicon nitride films for solar cell applications using neural networks

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflection coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks, PECVD nitride films are known to contain hydrogen, and defect passivation by hydrogenation enhances efficiency in polycrystalline silicon solar cells. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring Si/sub 3/N/sub 4/ film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, silicon nitride PECVD modeling using neural networks has been investigated. The deposition of Si/sub 3/N/sub 4/ was characterized via a central composite experimental design, and data from this experiment was used to train optimized feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. It was found that the process parameters critical to increasing hydrogenation and therefore enhancing carrier lifetime in polysilicon solar cells are temperature, silane, and ammonia flow rate. The deposition experiments were carried out in a Plasma Therm 700 series PECVD system.

[1]  M. Lemiti,et al.  Hydrogenation of multicrystalline silicon from a backside silicon nitride layer , 1991, The Conference Record of the Twenty-Second IEEE Photovoltaic Specialists Conference - 1991.

[2]  C. Denisse,et al.  Hydrogen passivation of polycrystalline silicon solar cells by plasma deposition of silicon nitride , 1990, IEEE Conference on Photovoltaic Specialists.

[3]  Terry R. Turner,et al.  Etch process characterization using neural network methodology: a case study , 1992, Other Conferences.

[4]  Gary S. May,et al.  Modeling the properties of PECVD silicon dioxide films using optimized back-propagation neural networks , 1994 .

[5]  K. S. Chari,et al.  Plasma enhanced chemical vapour deposition silicon nitride for microelectronic applications , 1988 .

[6]  Thomas F. Edgar,et al.  Constructing a reliable neural network model for a plasma etching process using limited experimental data , 1994 .

[7]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[8]  Ajeet Rohatgi,et al.  A novel and effective PECVD SiO/sub 2//SiN antireflection coating for Si solar cells , 1993 .

[9]  C. Spanos,et al.  Statistical experimental design in plasma etch modeling , 1991 .

[10]  T. Wydeven,et al.  Plasma-enhanced CVD silicon nitride antireflection coatings for solar cells , 1983 .

[11]  W. Lau.  The Identification and Suppression of Defects Responsible for Electrical Hysteresis in Metal-Nitride-Silicon Capacitors , 1990 .

[12]  Gary S. May,et al.  An optimal neural network process model for plasma etching , 1994 .

[13]  Chinmoy B. Bose,et al.  Neural network models in wafer fabrication , 1993, Defense, Security, and Sensing.

[14]  Ajeet Rohatgi,et al.  Modeling and characterization of interface state parameters and surface recombination velocity at plasma enhanced chemical vapor deposited SiO2–Si interface , 1994 .

[15]  Gary S. May,et al.  Advantages of plasma etch modeling using neural networks over statistical techniques , 1993 .

[16]  P. E. Castro.  Compact Numerical Methods for Computers: Linear Algebra and Function Minimization , 1978 .

[17]  B. Irie,et al.  Capabilities of three-layered perceptrons , 1988, IEEE 1988 International Conference on Neural Networks.