Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator
Abstract This paper proposes a data‐driven sensor fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear predictor for a nonli...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | IET Control Theory & Applications |
| Online Access: | https://doi.org/10.1049/cth2.12366 |
| _version_ | 1797955350547136512 |
|---|---|
| author | Mohammadhosein Bakhtiaridoust Fatemeh Negar Irani Meysam Yadegar Nader Meskin |
| author_facet | Mohammadhosein Bakhtiaridoust Fatemeh Negar Irani Meysam Yadegar Nader Meskin |
| author_sort | Mohammadhosein Bakhtiaridoust |
| collection | DOAJ |
| description | Abstract This paper proposes a data‐driven sensor fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear predictor for a nonlinear system. Then, the obtained Koopman predictor has been used in a geometric framework for sensor fault detection and isolation purposes without relying on a priori knowledge about the underlying dynamics as well as requiring faulty data, leading to a data‐driven sensor fault detection and isolation framework for nonlinear systems. Finally, the approach's efficacy is demonstrated using simulation case study on a two‐degree of freedom robot arm. |
| first_indexed | 2024-04-10T23:32:51Z |
| format | Article |
| id | doaj.art-68e288ed57f84f00a061551d859e003d |
| institution | Directory Open Access Journal |
| issn | 1751-8644 1751-8652 |
| language | English |
| last_indexed | 2024-04-10T23:32:51Z |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Control Theory & Applications |
| spelling | doaj.art-68e288ed57f84f00a061551d859e003d2023-01-12T04:30:37ZengWileyIET Control Theory & Applications1751-86441751-86522023-01-0117212313210.1049/cth2.12366Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operatorMohammadhosein Bakhtiaridoust0Fatemeh Negar Irani1Meysam Yadegar2Nader Meskin3Department of Electrical and Computer Engineering Qom University of Technology Qom IranDepartment of Electrical and Computer Engineering Qom University of Technology Qom IranDepartment of Electrical and Computer Engineering Qom University of Technology Qom IranDepartment of Electrical Engineering Qatar University Doha QatarAbstract This paper proposes a data‐driven sensor fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear predictor for a nonlinear system. Then, the obtained Koopman predictor has been used in a geometric framework for sensor fault detection and isolation purposes without relying on a priori knowledge about the underlying dynamics as well as requiring faulty data, leading to a data‐driven sensor fault detection and isolation framework for nonlinear systems. Finally, the approach's efficacy is demonstrated using simulation case study on a two‐degree of freedom robot arm.https://doi.org/10.1049/cth2.12366 |
| spellingShingle | Mohammadhosein Bakhtiaridoust Fatemeh Negar Irani Meysam Yadegar Nader Meskin Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator IET Control Theory & Applications |
| title | Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator |
| title_full | Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator |
| title_fullStr | Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator |
| title_full_unstemmed | Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator |
| title_short | Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator |
| title_sort | data driven sensor fault detection and isolation of nonlinear systems deep neural network koopman operator |
| url | https://doi.org/10.1049/cth2.12366 |
| work_keys_str_mv | AT mohammadhoseinbakhtiaridoust datadrivensensorfaultdetectionandisolationofnonlinearsystemsdeepneuralnetworkkoopmanoperator AT fatemehnegarirani datadrivensensorfaultdetectionandisolationofnonlinearsystemsdeepneuralnetworkkoopmanoperator AT meysamyadegar datadrivensensorfaultdetectionandisolationofnonlinearsystemsdeepneuralnetworkkoopmanoperator AT nadermeskin datadrivensensorfaultdetectionandisolationofnonlinearsystemsdeepneuralnetworkkoopmanoperator |