Application of sparse identification of nonlinear dynamics for physics-informed learning
Advances in machine learning and deep neural networks have enabled complex engineering tasks like image recognition, anomaly detection, regression, and multi-objective optimization, to name but a few. The complexity of the algorithm architecture, e.g., the number of hidden layers in a deep neural ne...
Uloženo v:
| Vydáno v: | 2020 IEEE Aerospace Conference s. 1 - 8 |
|---|---|
| Hlavní autor: | |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.03.2020
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Advances in machine learning and deep neural networks have enabled complex engineering tasks like image recognition, anomaly detection, regression, and multi-objective optimization, to name but a few. The complexity of the algorithm architecture, e.g., the number of hidden layers in a deep neural network, typically grows with the complexity of the problems they are required to solve, leaving little room for interpreting (or explaining) the path that results in a specific solution. This drawback is particularly relevant for autonomous aerospace and aviation systems, where certifications require a complete understanding of the algorithm behavior in all possible scenarios. Including physics knowledge in such data-driven tools may improve the interpretability of the algorithms, thus enhancing model validation against events with low probability but relevant for system certification. Such events include, for example, spacecraft or aircraft sub-system failures, for which data may not be available in the training phase. This paper investigates a recent physics-informed learning algorithm for identification of system dynamics, and shows how the governing equations of a system can be extracted from data using sparse regression. The learned relationships can be utilized as a surrogate model which, unlike typical data-driven surrogate models, relies on the learned underlying dynamics of the system rather than large number of fitting parameters. The work shows that the algorithm can reconstruct the differential equations underlying the observed dynamics using a single trajectory when no uncertainty is involved. However, the training set size must increase when dealing with stochastic systems, e.g., nonlinear dynamics with random initial conditions. |
|---|---|
| AbstractList | Advances in machine learning and deep neural networks have enabled complex engineering tasks like image recognition, anomaly detection, regression, and multi-objective optimization, to name but a few. The complexity of the algorithm architecture, e.g., the number of hidden layers in a deep neural network, typically grows with the complexity of the problems they are required to solve, leaving little room for interpreting (or explaining) the path that results in a specific solution. This drawback is particularly relevant for autonomous aerospace and aviation systems, where certifications require a complete understanding of the algorithm behavior in all possible scenarios. Including physics knowledge in such data-driven tools may improve the interpretability of the algorithms, thus enhancing model validation against events with low probability but relevant for system certification. Such events include, for example, spacecraft or aircraft sub-system failures, for which data may not be available in the training phase. This paper investigates a recent physics-informed learning algorithm for identification of system dynamics, and shows how the governing equations of a system can be extracted from data using sparse regression. The learned relationships can be utilized as a surrogate model which, unlike typical data-driven surrogate models, relies on the learned underlying dynamics of the system rather than large number of fitting parameters. The work shows that the algorithm can reconstruct the differential equations underlying the observed dynamics using a single trajectory when no uncertainty is involved. However, the training set size must increase when dealing with stochastic systems, e.g., nonlinear dynamics with random initial conditions. |
| Author | Corbetta, Matteo |
| Author_xml | – sequence: 1 givenname: Matteo surname: Corbetta fullname: Corbetta, Matteo organization: SGT Inc., NASA Ames Research Center,Moffett Field,CA,94035 |
| BookMark | eNpNT7tqwzAUVaEZ2jRfECj6AbtX15ZljSakDwgESoZuQdajvWDLxvbiv6-gGTqdJwfOI7uPQ_SMPQvIhQD90hw_z6VClDkCQq6FwqKu7thOqzrxWqAqSvXAvppx7MiahYbIh8Dn0Uyz5-R8XCj8C9J-R9Gbibs1mp7szMMw8fFnnRPPKCbVe8e7VIkUv5_YJphu9rsbbtnl9Xg5vGen89vHoTllhFAsmW0DCG0lBqjqUgdQLWqXHN_aUDrphFStqBUIqa11lZJWWYPKIFSgsdiy_d8see-v40S9mdbr7W7xC7joUR0 |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/AERO47225.2020.9172386 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9781728127347 1728127343 |
| EndPage | 8 |
| ExternalDocumentID | 9172386 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i203t-cbf019c52f06849f07b29d19cebcf4d5d157b1870159ccd675c7ca27a2060923 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 15 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000681699101058&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 06 17:59:30 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i203t-cbf019c52f06849f07b29d19cebcf4d5d157b1870159ccd675c7ca27a2060923 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_9172386 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-March |
| PublicationDateYYYYMMDD | 2020-03-01 |
| PublicationDate_xml | – month: 03 year: 2020 text: 2020-March |
| PublicationDecade | 2020 |
| PublicationTitle | 2020 IEEE Aerospace Conference |
| PublicationTitleAbbrev | AERO |
| PublicationYear | 2020 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 2.238922 |
| Snippet | Advances in machine learning and deep neural networks have enabled complex engineering tasks like image recognition, anomaly detection, regression, and... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Aerodynamics Bayes methods Heuristic algorithms Libraries Machine learning Machine learning algorithms Mathematical models Nonlinear dynamical systems System dynamics Trajectory |
| Title | Application of sparse identification of nonlinear dynamics for physics-informed learning |
| URI | https://ieeexplore.ieee.org/document/9172386 |
| WOSCitedRecordID | wos000681699101058&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07a8MwED6S0KFTW5LSNxo6VomsWJI9hpLQKQ0lg7egZ8mSFDvp7-_ZMg6FLt2EJJA4cbrvpLv7AJ6llkEFLqlwQtNUe1QpZgKdChPEVCZB2Eg2oZbLrCjyVQ9eulwY730TfObHdbP5y3d7e6yfyiboWqCFkX3oKyVjrlab9JuwfDKbf7zXpQ8Fen2cjdvJv1hTGqOxuPjfcpcwOmXfkVVnV66g53dDKGann2ayDwQvgrLyZOvaaJ9uYBdrX-iSuEg2XxHEpSS-YFQ0Fkr1jrR0EZ8jWC_m69c32rIi0C1n0wO1JiAss4IHJrM0D0wZnjvs8caG1AmXCGUSVEMEKtY6dAissporzZlkCOeuYYA78TdAGGIR7WqiIi1SZ3zGjXN55nnQPE84u4VhLZTNV6x7sWnlcfd39z2c13KP8VkPMDiUR_8IZ_b7sK3Kp-awfgC5bJlP |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmuhJDRjf9uDRQrdsu7tHYiAYEYnhwI30abiA2QV_v7PbDcTEi7embdJmmna-6Tw-gEeppE88l1RYoWisHF4ppj3tCe1FT0ZemEA2kUwm6XyeTRvwtMuFcc5VwWeuUzYrX75dm235VdZF0wI1jDyAQxHHnIVsrTrtN2JZtz_4eC-LHwq0-zjr1NN_8aZUamN4-r8Fz6C9z78j051mOYeGW7Vg3t_7msnaE3wK8sKRpa3jfXYDq1D9QuXEBrr5giAyJeEPo6ChVKqzpCaM-GzDbDiYPY9ozYtAl5z1NtRoj8DMCO6ZTOPMs0TzzGKP08bHVthIJDrCi4hQxRiLJoFJjOKJ4kwyBHQX0MSduEsgDNGIsiVVkRKx1S7l2tosddwrnkWcXUGrFMriK1S-WNTyuP67-wGOR7O38WL8Mnm9gZPyDEK01i00N_nW3cGR-d4si_y-Orgf4GOclg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2020+IEEE+Aerospace+Conference&rft.atitle=Application+of+sparse+identification+of+nonlinear+dynamics+for+physics-informed+learning&rft.au=Corbetta%2C+Matteo&rft.date=2020-03-01&rft.pub=IEEE&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FAERO47225.2020.9172386&rft.externalDocID=9172386 |