Skip to main content
SpringerLink
Log in

Determining adsorbent performance degradation in pressure swing adsorption using a deep learning algorithm and one-dimensional simulator

  • Process Systems Engineering, Process Safety
  • Published:
Korean Journal of Chemical Engineering Aims and scope Submit manuscript

Abstract

This study proposes a methodology for diagnosing the degree of performance degradation of the adsorbent in pressure swing adsorption (PSA) plants using a one-dimensional simulator and a time-series deep learning algorithm. First, a 1D PSA simulator was developed using mathematical models and validated with previously published experimental data. The behavior change of the PSA plant according to the performance degradation was trained using a deep learning algorithm based on the developed simulator. The model combines the 1D convolutional neural network and long-short-term memory (LSTM) network. The prediction of the degradation degree of the internal adsorbent was then presented using a pretrained neural network. The developed methodology demonstrates a mean squared error lower than 10−6 when predicting the degree of adsorbent degradation from the adsorption-bed-temperature time-series profiles with an example. The methodology can be used to predictive maintenance strategy by identifying PSA performance degradation in real time without stopping operation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

Aw :

wall cross-sectional area [m2]

C:

diffusion time constant [sec−1]

Cpg, Cps, Cpw :

heat capacity of gas, pellet and wall [J/kg K]

DL :

axial dispersion coefficient [m2/s]

hi :

internal heat transfer coefficient [J/m2 K s]

ho :

external heat transfer coefficient [J/m2 K s]

ΔH:

heat of adsorption [J/mol]

KL :

axial thermal conductivity [J/m K s]

kd :

adsorbent degradation factor [-]

L:

bed length [m]

P:

total pressure [Pa]

q, q*, \(\overline {\rm{q}} \) :

adsorption loading amount, adsorption isotherm, average concentration [mmol/g]

R:

gas constant [8.31447 J/mol K]

RP :

pellet radius [m]

RBi :

bed inner radius [m]

RBo :

bed outer radius [m]

t:

time [sec]

Tamb :

ambient temperature [K]

T:

bed temperature [K]

Tw :

wall temperature [K]

u:

interstitial velocity [m/s]

yi :

mole fraction of species i in gas phase [-]

z:

axial distance in bed from the feed gas inlet [m]

ADS:

adsorption step

BD:

blowdown step

DEQ:

depressurizing pressure equalization step

PEQ:

pressurizing pressure equalization step

PR:

pressurization step

PG:

purge step

LSTM:

long-short term memory

α :

particle porosity [-]

ε :

voidage of adsorbent bed [-]

ε t :

total void fraction [-]

μ :

viscosity [Pa sec]

ρ g, ρp, ρB, ρw :

density of gas, pellet, bulk and bed wall [kg/m3]

ω :

linear driving force (LDF) coefficient [sec−1]

References

  1. L. T. Biegler, L. Jiang and V. G. Fox, Sep. Purif. Rev., 33(1), 1 (2005).

    Article  Google Scholar 

  2. D. W. Siderius, V. K. Shen, R. D., III Johnson and R. D. van Zee, NIST/ARPA-E Database of Novel and Emerging Adsorbent Materials, NIST Standard Reference Database Number 205; National Institute of Standards and Technology: Gaithersburg, MD, http://adsorbents.nist.gov (retrieved July 07, 2023).

  3. C. W. Wu and S. Sircar, Adsorption, 25, 669 (2019).

    Article  CAS  Google Scholar 

  4. M. Luberti and H. Ahn, Int. J. Hydrogen Energy, 47(20), 10911 (2022).

    Article  CAS  Google Scholar 

  5. A. D. Wiheeb, Z. Helwani, J. Kim and M. R. Othman, Sep. Purif. Rev., 45(2), 108 (2016).

    Article  CAS  Google Scholar 

  6. M. D. Sees, T. Kirkes and C. C. Chen, Comput. Chem. Eng., 147, 107235 (2021).

    Article  CAS  Google Scholar 

  7. M. A. Makarem, M. Mofarahi, B. Jafarian and C. H. Lee, Comput. Chem. Eng., 121, 483 (2019).

    Article  CAS  Google Scholar 

  8. J. Uebbing, L. T. Biegler, L. Rihko-Struckmann, S. Sager and K. Sundmacher, Comput. Chem. Eng., 151, 107340 (2021).

    Article  CAS  Google Scholar 

  9. R. Rajasree and A. S. Moharir, Comput. Chem. Eng., 24(11), 2493 (2000).

    Article  CAS  Google Scholar 

  10. A. Streb and M. Mazzotti, Comput. Chem. Eng., 166, 107974 (2022).

    Article  CAS  Google Scholar 

  11. F. G. Wiessner, Gas Sep. Purif., 2(3), 115 (1988).

    Article  Google Scholar 

  12. C. J. Heard, L. Grajciar, F. Uhlík, M. Shamzhy, M. Opanasenko, J. Čejka and P. Nachtigall, Adv. Mater., 32(44), 2003264 (2020).

    Article  CAS  Google Scholar 

  13. R. Razzaq, C. Li and S. Zhang, Fuel, 113, 287 (2013).

    Article  CAS  Google Scholar 

  14. H. Ahn, J. Yang and C. H. Lee, Adsorption, 7, 339 (2001).

    Article  CAS  Google Scholar 

  15. K. O. Iwuozor, J. O. Ighalo, E. C. Emenike, L. A. Ogunfowora and C. A. Igwegbe, Curr. Res. Green Sust. Chem., 4, 100179 (2021).

    Article  CAS  Google Scholar 

  16. S. Kulkarni and J. Kaware, Int. J. Innov. Sci. Eng. Technol., 1(8), 61 (2014).

    Google Scholar 

  17. J. G. Jee, M. B. Kim and C. H. Lee, Chem. Eng. Sci., 60(3), 869 (2005).

    Article  CAS  Google Scholar 

  18. C. H. Lee, J. Yang and H. Ahn, AIChE J., 45(3), 535 (1999).

    Article  CAS  Google Scholar 

  19. J. P. Mota and A. J. Rodrigo, Ind. Eng. Chem. Res., 39(7), 2459 (2000).

    Article  CAS  Google Scholar 

  20. J. H. Yun, D. K. Choi and H. Moon, Chem. Eng. Sci., 55(23), 5857 (2000).

    Article  CAS  Google Scholar 

  21. M. B. Kim, J. H. Moon, C. H. Lee, H. Ahn and W. Cho, Korean J. Chem. Eng., 21, 703 (2004).

    Article  CAS  Google Scholar 

  22. I. F. Macdonald, M. S. El-Sayed, K. Mow and F. A. L. Dullien, Ind. Eng. Chem. Fundam., 18(3), 199 (1979).

    Article  CAS  Google Scholar 

  23. N. S. Raghavan, M. M. Hassan and D. M. Ruthven, Chem. Eng. Sci., 41(11), 2787 (1986).

    Article  CAS  Google Scholar 

  24. C. T. Choi and H. Wen-Chung, Chem. Eng. Sci., 49(1), 75 (1994).

    Article  Google Scholar 

  25. L. Guo, W. A. Jury, R. J. Wagenet and M. Flury, J. Contam. Hydrol., 43(1), 45 (2000).

    Article  CAS  Google Scholar 

  26. T. Paszko and M. Jankowska, Ecotox. Environ. Safe., 161, 584 (2018).

    Article  CAS  Google Scholar 

  27. G. Van Rossum and F. L. Drake, Python 3 reference manual, Scotts Valley, CA: CreateSpace (2009).

    Google Scholar 

  28. H. Ahn, C. Chun, M. Park, I. S. Ahn and C. H. Lee, Sep. Sci. Technol., 36(10), 2121 (2001).

    Article  CAS  Google Scholar 

  29. S. Ahn, Y. W. You, D. G. Lee, K. H. Kim, M. Oh and C. H. Lee, Chem. Eng. Sci., 68(1), 413 (2012).

    Article  CAS  Google Scholar 

  30. L. Barelli, G. Bidini, F. Gallorini and S. Servili, Energy, 33(4), 554 (2008).

    Article  CAS  Google Scholar 

  31. L. Riboldi and O. Bolland, Energy Procedia, 114, 2390 (2017).

    Article  CAS  Google Scholar 

  32. ISO/TC 197 (2019). Hydrogen Technologies. ISO 14687 Hydrogen Fuel—Product Specification—Part 2: Proton Exchange Membrane (PEM) Fuel Cell Applications for Road Vehicles. Available online: https://www.iso.org/obp/ui/fr/#iso:std:iso.14687-1:v1:en (retrieved July 07, 2023).

  33. S. Zhang, T. Zhang and Y. Liu, International Conference on Industrial Engineering and Engineering Management (IEEM), 1029 (2021).

  34. S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj and D. J. Inman, Mech. Syst. Signal Proc., 151, 107398 (2021).

    Article  Google Scholar 

  35. Y. Yu, X. Si, C. Hu and J. Zhang, Neural Comput., 31(7), 1235 (2019).

    Article  PubMed  Google Scholar 

  36. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai and S. Chintala, Adv. Neural Inf. Process. Syst., 32, 8024 (2019).

    Google Scholar 

Download references

Acknowledgement

This study was conducted with the support of the Kyungpook National University and Research Insititute of Industrial Science and Technology (RIST) individual project.

Author information

Authors and Affiliations

  1. Department of Smart Plant Engineering, Kyungpook National University, Sangju, 37224, South Korea

    Seongmin Son

  2. Department of Convergence & Fusion System Engineering, Kyungpook National University, Sangju, 37224, South Korea

    Seongmin Son

Authors
  1. Seongmin Son
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Seongmin Son.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Son, S. Determining adsorbent performance degradation in pressure swing adsorption using a deep learning algorithm and one-dimensional simulator. Korean J. Chem. Eng. 40, 2602–2611 (2023). https://doi.org/10.1007/s11814-023-1524-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11814-023-1524-x

Keywords

Search

Navigation