Prediction of Radio Frequency Impedance Matching in Plasma Equipment Using Neural Network

  • Byungwhan Kim
  • Donghwan Kim
  • Seung Soo Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


Optimizing a plasma impedance match process requires construction of prediction model. In this study, generalized regression neural network (GRNN) combined with genetic algorithm (GA) was used to build a match prediction model. A real-time match monitor system was used to collect steady match positions according to a statistical experimental design. GA-GRNN models were compared to GRNN and statistical regression models. Compared to GRNN models, GA-GRNN models demonstrated improved predictions of about 81% and 77% for the impedance and phase positions, respectively. With respect to statistical regression models, GA-GRNN models yielded an improvement of about 80% and 78%, respectively. Moreover, for either model type, the improvements for the training errors were more than about 90% for both positions.


Impedance Match Generalize Regression Neural Network Match Network Pattern Layer Phase Position 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Specht, D.F.: A General Regression Neural Network. IEEE Trans. Neural Network 2(5), 568–576 (1991)CrossRefGoogle Scholar
  2. 2.
    Kim, B., Kim, S., Lee, B.T.: Modeling SiC Surface Roughness Using Neural Network and Atomic Force Microscopy. J. Vac. Sci. Technol. B 22(5), 2467–2472 (2004)CrossRefGoogle Scholar
  3. 3.
    Kim, B., Lee, B.T.: Prediction of SiC Etching in a NF3/CH4 Plasma Using Neural Network. J. Vac. Sci. Technol. A 22(6), 2517–2522 (2004)CrossRefGoogle Scholar
  4. 4.
    Kim, B., Lee, D., Kwon, K.H.: Prediction of Etch Microtrenching Using a Neural Network. J. Appl. Phys. 96(7), 3612–3616 (2004)CrossRefGoogle Scholar
  5. 5.
    Kim, B., Park, K., Lee, D.: Use of Neural Network to Model a Deposition Rate of PECVD-Silicon Nitride Films. Plasma Sources Sci. Technol. 14, 83–88 (2005)CrossRefGoogle Scholar
  6. 6.
    Kim, B., Lee, C.: Monitoring Plasma Impedance Match Characteristics in a Multipole In-ductively Coupled Plasma for Process Control. J. Vac. Sci. Technol. A 18(1), 58–62 (2000)CrossRefGoogle Scholar
  7. 7.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization & Machine Learning. Addison Wesley, Reading (1989)MATHGoogle Scholar
  8. 8.
    Montgomery, D.C.: Design and Analysis of Experiments. John Wiley & Sons, Singapore (1991)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Byungwhan Kim
    • 1
  • Donghwan Kim
    • 2
  • Seung Soo Han
    • 3
  1. 1.Department of Electronic EngineeringSejong UniversitySeoulKorea
  2. 2.School of Mechanical Design & Automation EngineeringSeoul National University of TechnologySeoulKorea
  3. 3.Department of Information EngineeringMyongji UniversityYonginKorea

Personalised recommendations