Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law

T. Poznyak, I. Chairez, A. Poznyak

Research output: Contribution to conferencePaper

Abstract

© 2018 IEEE. A discontinuous learning law is implemented here to adjust an adaptive non-parametric identifier, based on the differential neural networks (DNNs) approximations. The learning law for DNN uses the vector form of an extended super-twisting algorithm as the output injection term in the DNN structure. The learning laws with discontinuous dynamics have been obtained from the application of a special class of strong lower semi-continuous Lyapunov function. The developed observer was tested on both modelled and experimental input-output information on the specific the ozonation process of a contaminated solid phase. A numerical example illustrates the observer performance when the input-output information is free of the observation noise. The observer has been evaluated using real experimental data, obtained by the direct laboratory analysis. In both cases, modelling and real experiments, the coincidence between the ozonation variables and the estimated states shows a remarkable correspondence.
Original languageAmerican English
Pages291-296
Number of pages261
DOIs
StatePublished - 10 Sep 2018
EventProceedings of IEEE International Workshop on Variable Structure Systems -
Duration: 10 Sep 2018 → …

Conference

ConferenceProceedings of IEEE International Workshop on Variable Structure Systems
Period10/09/18 → …

Fingerprint

Ozone
Ozonization
Impurities
Neural networks
Decomposition
Lyapunov functions
Experiments

Cite this

Poznyak, T., Chairez, I., & Poznyak, A. (2018). Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law. 291-296. Paper presented at Proceedings of IEEE International Workshop on Variable Structure Systems, . https://doi.org/10.1109/VSS.2018.8460461
Poznyak, T. ; Chairez, I. ; Poznyak, A. / Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law. Paper presented at Proceedings of IEEE International Workshop on Variable Structure Systems, .261 p.
@conference{34ea522ed4d647529f6548c2972c2bbe,
title = "Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law",
abstract = "{\circledC} 2018 IEEE. A discontinuous learning law is implemented here to adjust an adaptive non-parametric identifier, based on the differential neural networks (DNNs) approximations. The learning law for DNN uses the vector form of an extended super-twisting algorithm as the output injection term in the DNN structure. The learning laws with discontinuous dynamics have been obtained from the application of a special class of strong lower semi-continuous Lyapunov function. The developed observer was tested on both modelled and experimental input-output information on the specific the ozonation process of a contaminated solid phase. A numerical example illustrates the observer performance when the input-output information is free of the observation noise. The observer has been evaluated using real experimental data, obtained by the direct laboratory analysis. In both cases, modelling and real experiments, the coincidence between the ozonation variables and the estimated states shows a remarkable correspondence.",
author = "T. Poznyak and I. Chairez and A. Poznyak",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/VSS.2018.8460461",
language = "American English",
pages = "291--296",
note = "Proceedings of IEEE International Workshop on Variable Structure Systems ; Conference date: 10-09-2018",

}

Poznyak, T, Chairez, I & Poznyak, A 2018, 'Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law', Paper presented at Proceedings of IEEE International Workshop on Variable Structure Systems, 10/09/18 pp. 291-296. https://doi.org/10.1109/VSS.2018.8460461

Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law. / Poznyak, T.; Chairez, I.; Poznyak, A.

2018. 291-296 Paper presented at Proceedings of IEEE International Workshop on Variable Structure Systems, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Estimation of Contaminants Decomposition in Solid Phase with Ozone by Differential Neural Networks with Discontinuous Learning Law

AU - Poznyak, T.

AU - Chairez, I.

AU - Poznyak, A.

PY - 2018/9/10

Y1 - 2018/9/10

N2 - © 2018 IEEE. A discontinuous learning law is implemented here to adjust an adaptive non-parametric identifier, based on the differential neural networks (DNNs) approximations. The learning law for DNN uses the vector form of an extended super-twisting algorithm as the output injection term in the DNN structure. The learning laws with discontinuous dynamics have been obtained from the application of a special class of strong lower semi-continuous Lyapunov function. The developed observer was tested on both modelled and experimental input-output information on the specific the ozonation process of a contaminated solid phase. A numerical example illustrates the observer performance when the input-output information is free of the observation noise. The observer has been evaluated using real experimental data, obtained by the direct laboratory analysis. In both cases, modelling and real experiments, the coincidence between the ozonation variables and the estimated states shows a remarkable correspondence.

AB - © 2018 IEEE. A discontinuous learning law is implemented here to adjust an adaptive non-parametric identifier, based on the differential neural networks (DNNs) approximations. The learning law for DNN uses the vector form of an extended super-twisting algorithm as the output injection term in the DNN structure. The learning laws with discontinuous dynamics have been obtained from the application of a special class of strong lower semi-continuous Lyapunov function. The developed observer was tested on both modelled and experimental input-output information on the specific the ozonation process of a contaminated solid phase. A numerical example illustrates the observer performance when the input-output information is free of the observation noise. The observer has been evaluated using real experimental data, obtained by the direct laboratory analysis. In both cases, modelling and real experiments, the coincidence between the ozonation variables and the estimated states shows a remarkable correspondence.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85054091437&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85054091437&origin=inward

U2 - 10.1109/VSS.2018.8460461

DO - 10.1109/VSS.2018.8460461

M3 - Paper

SP - 291

EP - 296

ER -