Soft Computing

, Volume 14, Issue 2, pp 161–169 | Cite as

Optimization of silicon solar cell fabrication based on neural network and genetic programming modeling

  • Hyeon Bae
  • Tae-Ryong Jeon
  • Sungshin Kim
  • Hyun-Soo Kim
  • Dongseop Kim
  • Seung-Soo Han
  • Gary S. May
Focus
First Online:

Abstract

This study describes techniques for the cascade modeling and the optimization that are required to conduct the simulator-based process optimization of solar cell fabrication. Two modeling approaches, neural networks and genetic programming, are employed to model the crucial relation for the consecutively connected two processes in solar cell fabrication. One model (Model 1) is used to map the five inputs (time, amount of nitrogen and DI water in surface texturing and temperature and time in emitter diffusion) to the two outputs (reflectance and sheet resistance) of the first process. The other model (Model 2) is used to connect the two inputs (reflectance and sheet resistance) to the one output (efficiency) of the second process. After modeling of the two processes, genetic algorithms and particle swarm optimization were applied to search for the optimal recipe. In the first optimization stage, we searched for the optimal reflectance and sheet resistance that can provide the best efficiency in the fabrication process. The optimized reflectance and sheet resistance found by the particle swarm optimization were better than those found by the genetic algorithm. In the second optimization stage, the five input parameters were searched by using the reflectance and sheet resistance values obtained in the first stage. The found five variables such as the texturing time, amount of nitrogen, DI water, diffusion time, and temperature are used as a recipe for the solar cell fabrication. The amount of nitrogen, DI water, and diffusion time in the optimized recipes showed considerable differences according to the modeling approaches. More importantly, repeated applications of particle swarm optimization yielded process conditions with smaller variations, implying greater consistency in recipe generation.

Keywords

Neural network Genetic programming Genetic algorithm Particle swarm optimization Silicon solar cell fabrication 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

This work was supported by the Grant of the Korean Ministry of Education, Science and Technology (The Regional Core Research Program/Institute of Logistics Information Technology) and the ERC program of MOST/KOSEF (Next-generation Power Technology Center).

References

  1. AbdulHadi M, Al-Ibrahim AM, Virk GS (2004) Neuro-fuzzy-based solar cell model. IEEE Trans Energy Convers 19(3):619–624CrossRefGoogle Scholar
  2. Agostinellia G, Batznerb DL, Burgelmanc M (2003) A theoretical model for the front region of cadmium telluride solar cells. Thin Solid Films 431-432(1):407–413CrossRefGoogle Scholar
  3. Appelbaum J, Chait A, Thompson D (1992) Parameterization of solar cells. NASA STI/Recon Technical Report NGoogle Scholar
  4. Baker JE (1987) Reducing bias and inefficiency in the selection algorithm. In: Proceedings of the 2nd international conference on genetic algorithms and their application, pp 14–21Google Scholar
  5. Brameier M, Banzhaf W (2001) Comparison of linear genetic programming and neural network in medical data mining. IEEE Trans Evolu Comput 5:17–26CrossRefGoogle Scholar
  6. Davis C, Hong SJ, Setia R, Pratap R, Brown T, Ku B, Triplett G, May G (2004) An object-oriented neural network simulator for semiconductor manufacturing applications. In: The 8th world multi-conference on systemics cybernetics informatics, vol 5, pp 365–370Google Scholar
  7. Frenzel JF (1993) Genetic algorithms. IEEE Potentials 12(3):21–24CrossRefGoogle Scholar
  8. Goldberg DE (1989) Genetic algorithms in search, optimization & machine Learning. Addison WesleyGoogle Scholar
  9. Green MA, Blakers AW, Shi J, Keller, EM, Wenham SR (1984) High-efficiency silicon solar cells. IEEE Trans Electron Devices 31:679–683CrossRefGoogle Scholar
  10. Han SS, Ceiler M, Bidstrup S, Kohl P, May G (1994) Modeling the properties of PECVD silicon dioxide films using optimized back-propagation neural network. IEEE Trans CPMT 17:174–182Google Scholar
  11. Jervase JA, Bourdoucen H, Lawati AA (2001) Solar cell parameter extraction using genetic algorithms. Meas Sci Technol 12:1922–1925CrossRefGoogle Scholar
  12. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of IEEE international conference on neural networks vol IV, pp 1942–1948Google Scholar
  13. Kim DS, Hilali MM, Rohatgi A, Nakano K, Hariharan A, Matthei K (2006) Development of a phosphorus spray diffusion system for low cost silicon solar cells. J Electrochem Soc 153:A1391–1396CrossRefGoogle Scholar
  14. Koza J (1992) Genetic programming: on the programming of computers by means of natural selection. The MIT Press, CambridgeMATHGoogle Scholar
  15. Koza J (1994) Genetic programming II. Automatic discovery of reusable programs. The MIT Press, CambridgeMATHGoogle Scholar
  16. Koza J, Bennett III, F, Andre D, Keane M (1999) Genetic programming III: Darwinian invention and problem solving. Morgan KaufmannGoogle Scholar
  17. Lee SJ, Pandey A, Kim DS, Rohatgi A, May G, Hong SJ, Han SS (2007) Characterization and optimization of the contact formation for high-performance silicon solar cells. Lecture Notes in Computer Science vol 4493, pp 246–251Google Scholar
  18. Marvin DC (1988) Solar cell modeling and simulation. NASA STI/Recon Technical Report NGoogle Scholar
  19. Michael S, Bates AD, Green MS (2005) Silvaco ATLAS as a solar cell modeling tool. In: 31st IEEE photovoltaic specialists conference, vol (3–7), pp 719–721Google Scholar
  20. Mottet S (1980) Solar cell modeling for computer-aided generator design and irradiation degradation computations. In: ESA photovoltaic generations in space, pp 177–186Google Scholar
  21. Nijs JF, Szlufcik J, Poortmans J, Sivoththaman S, Mertens RP (1999) Advanced manufacturing concepts for crystalline silicon solar cells. IEEE Trans Electron Devices 46:1948–1969CrossRefGoogle Scholar
  22. Rohatgi A, Chen Z, Doshi P, Pham T, Ruby D (1994) High-efficiency silicon solar cells by rapid thermal processing. Appl Phys Lett 65:2087–2089CrossRefGoogle Scholar
  23. Shi YH, Eberhart RC (1998) A Modified Particle Swarm Optimizer. In: IEEE international conference on evolutionary computation, pp 69–73Google Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  • Hyeon Bae
    • 1
  • Tae-Ryong Jeon
    • 2
  • Sungshin Kim
    • 2
  • Hyun-Soo Kim
    • 3
  • Dongseop Kim
    • 1
  • Seung-Soo Han
    • 3
  • Gary S. May
    • 1
  1. 1.School of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaUSA
  2. 2.School of Electrical EngineeringPusan National UniversityBusanKorea
  3. 3.Department of Information Engineering and NPTCMyongji UniversityKyunggiKorea

Personalised recommendations