Estimating viscosities of semiconductor-manufacturing gases
Source abstract
Abstract
Semiconductor manufacturing demands an accurate delivery of gases to the process chamber. To achieve this, accurate gas viscosities are needed. Hence, this paper compares viscosity models applied to pure gases and operating conditions relevant to semiconductor manufacturing and develops a method to design neural-network/multilayer-perceptron models of viscosity. Overall, the perceptron models give the smallest root-mean-square errors in comparison with experimental data, followed closely by a simplified variation of well-known models. Based on these findings, this paper uses a perceptron model to give viscosities of several semiconductor-manufacturing gases that are unavailable and gives recommendations on how to estimate these viscosities.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Engineering and Technologies · Advanced ceramic materials synthesis · Field-Flow Fractionation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Horiba , Reno, Nevada 89509,
References (59)
Show source-provided references
1. 2006
2. Process control in semiconductor manufacturing10.1116/1.588109 ↗
3. Modular fluid delivery system architectures drive configurability options, enhance semiconductor manufacturing equipment productivity, and improve process performance10.1109/tsm.2023.3271286 ↗
4. Chamber-to-chamber discrepancy detection in semiconductor manufacturing10.1109/tsm.2020.2965288 ↗
5. Part-level fault classification of mass flow controller drift in plasma deposition equipment10.1109/tsm.2024.3396994 ↗
6. Gas-delivery fluid-mechanical timescales in semiconductor manufacturing10.1109/TSM.2023.3327067 ↗
7. 2005
8. Upgrading of the modified Knudsen equation and its verification for calculating the gas flow rate through cylindrical tubes10.1116/6.0003581 ↗
9. 2019
10. R. A. Svehla , “Estimated viscosities and thermal conductivities of gases at high temperatures,” Technical Report No. NASA-TR-R-132, 1963.
11. Viscosity of nonpolar gaseous mixtures at normal pressures10.1002/aic.690160225 ↗
12. The estimation of the viscosities of gases and gas mixtures
13. 1980
14. Applications of kinetic gas theories and multiparameter correlation for prediction of dilute gas viscosity and thermal conductivity10.1021/i100013a002 ↗
15. Generalized multiparameter correlation for nonpolar and polar fluid transport properties10.1021/ie00076a024 ↗
16. Viscosity prediction from a modified square well intermolecular potential model: Polar and associating compounds10.1016/s0378-3812(97)00090-3 ↗
17. The new simple extended corresponding-states principle: Complex molecular transport properties in dilute gas state10.1016/s0378-3812(01)00537-4 ↗
18. Viscosity: A critical review of practical predictive and correlative methods10.1002/cjce.5450730103 ↗
19. 2001
20. See www.molecularknowledge.com for Cranium.
21. An improved extended corresponding states method for estimation of viscosity of pure refrigerants and mixtures10.1016/s0140-7007(96)00073-4 ↗
22. Viscosity prediction by computational method and artificial neural network approach: The case of six refrigerants10.1016/j.supflu.2013.04.017 ↗
23. A novel correlation for prediction of gas viscosity10.1080/15567036.2011.601798 ↗
24. The application of supervised machine learning techniques for multivariate modelling of gas component viscosity: A comparative study10.1016/j.fuel.2020.119146 ↗
25. ThermoData engine (TDE): Software implementation of the dynamic data evaluation concept10.1021/ci050067b ↗
26. See trc.nist.gov/tde.html for ThermoDataEngine.
27. Enhancement of CO2 viscosity prediction using advanced intelligent methods: Application to carbon capture and storage10.1016/j.geoen.2023.211727 ↗
28. Y. Kwon , O.Kwon, Y.Kim, J.Ari, J.Jo, and T.Park, “SVRC model predicting gas viscosity of pure organic,” Korean Patent KR101313036B1 (01 October 2013).
29. Handling limited datasets with neural networks in medical applications: A small-data approach10.1016/j.artmed.2016.12.003 ↗
30. Ten deep learning techniques to address small data problems with remote sensing10.1016/j.jag.2023.103569 ↗
31. Reminder of the first paper on transfer learning in neural networks, 197610.31449/inf.v44i3.2828 ↗
32. 2002
33. Gas viscosities from a semiconductor-manufacturing mass-flow controller10.1088/1681-7575/ad435f ↗
34. See dortmunddatabank.com for Dortmund Data Bank.
35. Measurements of the viscosity of compressed gaseous and liquid fluorine10.1016/0031-8914(74)90079-2 ↗
36. E. W. Lemmon , I. H.Bell, M. L.Huber, and M. O.McLinden, NIST Standard Reference Database, Reference Fluid Thermodynamic and Transport Properties (REFPROP), 2018, www.nist.gov/srd/refprop.
37. See scikit-learn.org for scikit learn.
38. See pytorch.org for PyTorch.
39. 2023
40. 1980
41. UC Irvine Machine Learning Repository. Concrete compressive strength, archive.ics.uci.edu/dataset/165/concrete+compressive+strength (accessed 25 September 2024).
42. A data-driven statistical model for predicting the critical temperature of a superconductor10.1016/j.commatsci.2018.07.052 ↗
43. UC Irvine Machine Learning Repository. Superconductivty data, archive.ics.uci.edu/dataset/464/superconductivty+data (accessed 25 September 2024).
44. Modeling of strength of high-performance concrete using artificial neural networks10.1016/s0008-8846(98)00165-3 ↗
45. 1988
46. 2019
47. 2009
48. Viscosity prediction of nonpolar, polar, and associating fluids over a wide PρT range from a modified square well intermolecular potential model10.1021/ie970416u ↗
49. Dilute gases10.1039/9781782625254 ↗
50. Ab initio calculation of fluid properties for precision metrology10.1063/5.0156293 ↗
51. Recommended viscosities of 11 dilute gases at 25 °C10.1063/1.4765368 ↗
52. Calculation of the transport and relaxation properties of methane. I. Shear viscosity, viscomagnetic effects, and self-diffusion10.1063/1.2958279 ↗
53. Cross second virial coefficients and dilute gas transport properties of the (CH4 + C3H8) and (CO2 + C3H8) systems from accurate intermolecular potential energy surfaces10.1021/acs.jced.7b00886 ↗
54. Ab initio intermolecular potential energy surface and thermophysical properties of hydrogen sulfide10.1039/c1cp20873j ↗
55. State-of-the-art ab initio potential energy curve for the xenon atom pair and related spectroscopic and thermophysical properties10.1063/1.4994267 ↗
56. Kinematic viscosity and speed of sound in gaseous CO, CO2, SiF4, SF6, C4F8, and NH3 from 220 to 375 K and pressures up to 3.4 MPa10.1016/j.jct.2007.07.002 ↗
57. The viscosity of seven gases measured with a Greenspan viscometer10.1023/b:ijot.0000004088.04964.4c ↗
58. Reference viscosity of argon at low density in the temperature range from 290 to 680 K10.1007/s10765-010-0760-6 ↗
59. Reference viscosities of gaseous methane and hydrogen sulfide at low density in the temperature range from 292 to 682 K10.1021/je200371n ↗