Transactions on Control, Automation and Systems Engineering

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Modeling of Process Plasma Using a Radial Basis Function Network: A Cases Study

  • Kim, Byungwhan (Department of Electrical Engineering, Chonnam National University) ;
  • Sungjin Rark (Department of Electrical Engineering, Chonnam National University)
  • Published : 2000.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Plasma models are crucial to equipment design and process optimization. A radial basis function network(RBFN) in con-junction with statistical experimental design has been used to model a process plasma. A 2$^4$ full factorial experiment was employed to characterized a hemispherical inductively coupled plasma(HICP) in characterizing HICP, the factors that were varied in the design include source power, pressure, position of shuck holder, and Cl$_2$ flow rate. Using a Langmuir probe, plasma attributes were collected, which include typical electron density, electron temperature. and plasma potential as well as their spatial uniformity. Root mean-squared prediction errors of RBEN are 0.409(10(sup)12/㎤), 0.277(eV), and 0.699(V), for electron density, electron temperature, and Plasma potential, respectively. For spatial uniformity data, they are 2.623(10(sup)12/㎤), 5.704(eV) and 3.481(V), for electron density, electron temperature, and plasma potential, respectively. Comparisons with generalized regression neural network(GRNN) revealed an improved prediction accuracy of RBFN as well as a comparable performance between GRNN and statistical response surface model. Both RBEN and GRNN, however, experienced difficulties in generalizing training data with smaller standard deviation.

Keywords

References

  1. Appl. Phys. Lett. v.63 no.5 Two-dimensional hybrid model of inductively coupled plasma sources for etching P L. G. Ventzek;T. J. Sommerer;R. J. Hoekstra;M. J. Kushner
  2. J. Vac. Sci. Technol. v.B 12 no.1 Two-dimensional fluid model of high density inductively coupled plasma sources R. A. Stewart;P. Vitello;D. B. Graves
  3. IEEE Trans. Semicond. Manufact. v.6 Advantages of plasma etch modeling using neural networks over statistical techniques C. D. Himmel;G. S. May
  4. IEEE Trans. Semicond. Manufact, v.6 no.4 Use of neural networks in modeling semiconductor manufacturing processes: An example of plasma etch modeling E. A. Rietman;E. R. Lory
  5. IEEE Trans. Semicond. Manufact. v.7 no.1 An optimal neural network process model for plasma etching B. Kim,;G. S. May
  6. IEEE Trans. Comp. Pack.. Manufact. Technol. C v.19 no.1 Reactive ion etch modeling using neural networks and simulated annealing B. Kim;G. S. May
  7. IEEE Trans. Semicond. Manufact. v.11 no.4 Modeling a magnetically RIE of aluminum alloy films using neural networks B. Kim;K. H. Kwon
  8. J. Vac. Sci. and Technol., A v.17 no.5 Characterizing metal-masked silica etch process in a CHF$_3$/CF$_4$ inductively coupled plasma B. Kim;K. H. Kwon;S. H. Park
  9. J. Vac. Sci. and Technol., A v.18 no.2 Use of neural network to model low-temperature tungsten etch characteristics in high density $SF_6$ plasma B. Kim;J. H. Sun;C. J. Choi;D. D. Lee;Y. S. Seol
  10. Neural Networks J. Freeman;D. Skapura
  11. IEEE Trans. Neural Networks v.2 no.2 Orthogonal least squares learning algorithm for radial basis function networks S. Chen;C. F. N. Cowan;P. M. Grant
  12. Advanced Methods in Neural Computing P. D. Wasserman
  13. Empirical Model Building and Response Surfaces G. Box,;N. Draper