Modelling of plasma etching process using radial basis function network and genetic algorithm
Source abstract
Abstract
Abstract Computer prediction models are crucial to control complex plasma processes. A new plasma model was constructed by using a radial basis function network (RBFN) and genetic algorithm (GA). The GA was used to search for an optimized set of training factors. This technique was evaluated with the plasma etching data. The etching of silica thin film was conducted in an inductively coupled plasma. The etch responses modelled include aluminum (Al) etch rate, silica etch rate, Al selectivity, silica profile angle, and silica sidewall roughness. For comparison, conventional RBFN models as well as four types of statistical regression models were constructed . Compared to conventional RBFN models, GA-RBFN models exhibited improved predictions of more than 20% for Al etch rate, Al selectivity, and silica sidewall roughness. For the remaining two etch responses, both GA-RBFN and RBFN models were almost comparable. Compared to statistical regression models, GA-RBFN demonstrated improved predictions for nearly all etch responses. The improvement was even more than 35% for the Al selectivity and silica sidewall roughness. The comparisons revealed that the presented method can be effectively used to construct improved prediction models for plasma control.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Non-Destructive Testing Techniques · Metal and Thin Film Mechanics · Copper Interconnects and Reliability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (30)
Show source-provided references
1. Himmel · Proceedings of 1992 IEEE/SEMI Interantional Semiconductor Manyfacturing Science Symposium · 1992 · 12410.1109/ISMSS.1992.197650 ↗
2. Himmel · IEEE Trans. Semicond. Manufact. · 1993 · 6 · 19310.1109/66.216928 ↗
3. Rietman · IEEE Trans. Semicond. Manufact. · 1993 · 6 · 34310.1109/66.267644 ↗
4. Huang · IEEE Trans. Semi. Manufact. · 1994 · 7 · 33310.1109/66.311337 ↗
5. Kim · IEEE Trans. Semicond. Manufact. · 1994 · 7 · 1210.1109/66.286829 ↗
6. Bushman · J. Electrochem. Soc. · 1997 · 144 · 137910.1149/1.1837600 ↗
7. Kim · IEEE Trans. Semicond. Manufact. · 1999 · 22 · 128
8. Kim · J. Vac. Sci. Technol. A · 2000 · 18 · 41710.1116/1.582203 ↗
9. Kim · J. Vac. Sci. Technol. A · 2002 · 20 · 14610.1116/1.1427882 ↗
10. Kim · J. Vac. Sci. Technol. B · 2002 · 20 · 211310.1116/1.1511212 ↗
11. Kim · Chemometrics Intell. Lab. Syst. · 2001 · 56 · 3910.1016/S0169-7439(01)00107-1 ↗
12. Kim · J. Appl. Phys. · 2003 · 93 · 7610.1063/1.1527216 ↗
13. Kim · J. Appl. Phys. · 2004 · 96 · 361210.1063/1.1789276 ↗
14. Kim · J. Vac. Sci. Technol. B · 2004 · 22 · 246710.1116/1.1798851 ↗
15. Kim · J. Vac. Sci. Technol. A · 2004 · 22 · 251710.1116/1.1810169 ↗
16. Han · IEEE Trans. Semicond. Manufact. · 1997 · 10 · 27910.1109/66.572083 ↗
17. Natale · IEEE Trans. Semicond. Manufact. · 1999 · 12 · 10910.1109/66.744532 ↗
18. Wang · J. Electrochem. Soc. · 1995 · 142 · 312310.1149/1.2048699 ↗
19. Venkateswaran · J. Electrochem. Soc. · 2002 · 149 · 13710.1149/1.1430721 ↗
20. Kim · Vacuum · 2004 · 72 · 38510.1016/j.vacuum.2003.08.012 ↗
21. Rummelhart · 1986
22. Specht · IEEE Trans. Neural Network · 1991 · 2 · 56810.1109/72.97934 ↗
23. Park · Neural Comput. · 1991 · 3 · 24610.1162/neco.1991.3.2.246 ↗
24. Kim · Vacuum · 2003 · 71 · 49710.1016/S0042-207X(03)00075-7 ↗
25. Kim · Vacuum · 2004 · 76 · 3710.1016/j.vacuum.2004.05.018 ↗
26. Kim · Appl. Surf. Sci. · 2004 · 222 · 1710.1016/S0169-4332(03)00963-2 ↗
27. Kim · Trans. Contr. Autom. Syst. Eng. · 2000 · 2 · 268
28. Kim · Microeletron. Eng. · 2005 · 77 · 15010.1016/j.mee.2004.09.009 ↗
29. Goldbeg · 1989
30. Montgomery, · 1991