Optimization of Graded Arrays of Resonators for Energy Harvesting in Sensors as a Markov Decision Process Solved via Reinforcement Learning
The design optimization of the grading of a resonator array for energy harvesting in sensors is described. Attention is paid to set the resonator heights, possibly removing resonators whenever convenient. Instead of employing time-consuming heuristic approaches that require verifying the physical un...
Saved in:
Published in | Engineering proceedings Vol. 27; no. 1; p. 18 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
MDPI AG
01.11.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The design optimization of the grading of a resonator array for energy harvesting in sensors is described. Attention is paid to set the resonator heights, possibly removing resonators whenever convenient. Instead of employing time-consuming heuristic approaches that require verifying the physical understanding of the problem and tuning the design ruling parameters, the optimization task is treated as a Markov decision process, in which states describe specific system configurations, and actions represent the modifications to the current design. The physics-based understanding of the problem is exploited to constrain the set of possible modifications to the mechanical system. Finite elements simulations are exploited to evaluate the action effects and to inform the reinforcement learning agent. The proximal policy optimization algorithm is employed to solve the Markov decision problem. The procedure is demonstrated to be able to automatically produce configurations, enhancing the mechanical system performance. The proposed framework is generalizable to a large class of problems involving the design optimization of sensors. |
---|---|
AbstractList | The design optimization of the grading of a resonator array for energy harvesting in sensors is described. Attention is paid to set the resonator heights, possibly removing resonators whenever convenient. Instead of employing time-consuming heuristic approaches that require verifying the physical understanding of the problem and tuning the design ruling parameters, the optimization task is treated as a Markov decision process, in which states describe specific system configurations, and actions represent the modifications to the current design. The physics-based understanding of the problem is exploited to constrain the set of possible modifications to the mechanical system. Finite elements simulations are exploited to evaluate the action effects and to inform the reinforcement learning agent. The proximal policy optimization algorithm is employed to solve the Markov decision problem. The procedure is demonstrated to be able to automatically produce configurations, enhancing the mechanical system performance. The proposed framework is generalizable to a large class of problems involving the design optimization of sensors. |
Author | Jacopo Maria De Ponti Luca Iorio Raffaele Ardito Alberto Corigliano Luca Rosafalco |
Author_xml | – sequence: 1 fullname: Luca Rosafalco organization: Dipartimento di Ingegneria Civile ed Ambientale, Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Milano, Italy – sequence: 2 fullname: Jacopo Maria De Ponti organization: Dipartimento di Ingegneria Civile ed Ambientale, Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Milano, Italy – sequence: 3 fullname: Luca Iorio organization: Dipartimento di Ingegneria Civile ed Ambientale, Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Milano, Italy – sequence: 4 fullname: Raffaele Ardito organization: Dipartimento di Ingegneria Civile ed Ambientale, Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Milano, Italy – sequence: 5 fullname: Alberto Corigliano organization: Dipartimento di Ingegneria Civile ed Ambientale, Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Milano, Italy |
BookMark | eNotzN9KwzAYBfAgCs65Ox8gL1BN86_p5ZjTDSYTp9fla_p1ZG7JSEphvoIvbafCgQOHw--GXPrgkZC7nN0LUbIHtAmyMssFz_UFGXFdiEyqMr8mk5R2jDGuci6FGJHv9bFzB_cFnQuehpY-R2iwodMY4ZTOwxum4KELMdE2RDr3GLcnuoDYY-qc31Ln6QZ9Oh9gCH2B-Bl6-ojWpTP6GoPFlOgm7PtB7h0MpvMDZvGAvqMrhOgH6ZZctbBPOPnvMfl4mr_PFtlq_bycTVdZkxdSZ2CsqaVuGWeouUFE03DJlG2hbcDULAdtmMqLRiI3jSpLXhR1qRgWWgqFYkyWf24TYFcdoztAPFUBXPU7hLitIHbO7rFSUAMvlEJlrLS1NbLUFoQsmAYcXPEDokRz1w |
ContentType | Journal Article |
DBID | DOA |
DOI | 10.3390/ecsa-9-13216 |
DatabaseName | DOAJ Directory of Open Access Journals |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
EISSN | 2673-4591 |
ExternalDocumentID | oai_doaj_org_article_5aba2755e58c4cbc8496ca34706ae927 |
GroupedDBID | AADQD AFZYC ALMA_UNASSIGNED_HOLDINGS GROUPED_DOAJ OK1 |
ID | FETCH-LOGICAL-d1746-a8c8b46f020e628eee8d2405cfafda8b01a680517d4e28d599277b950e76435e3 |
IEDL.DBID | DOA |
IngestDate | Tue Oct 22 15:15:59 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-d1746-a8c8b46f020e628eee8d2405cfafda8b01a680517d4e28d599277b950e76435e3 |
OpenAccessLink | https://doaj.org/article/5aba2755e58c4cbc8496ca34706ae927 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_5aba2755e58c4cbc8496ca34706ae927 |
PublicationCentury | 2000 |
PublicationDate | 2022-11-01 |
PublicationDateYYYYMMDD | 2022-11-01 |
PublicationDate_xml | – month: 11 year: 2022 text: 2022-11-01 day: 01 |
PublicationDecade | 2020 |
PublicationTitle | Engineering proceedings |
PublicationYear | 2022 |
Publisher | MDPI AG |
Publisher_xml | – name: MDPI AG |
SSID | ssj0002512433 |
Score | 2.254909 |
Snippet | The design optimization of the grading of a resonator array for energy harvesting in sensors is described. Attention is paid to set the resonator heights,... |
SourceID | doaj |
SourceType | Open Website |
StartPage | 18 |
SubjectTerms | energy harvesting for sensors Markov decision process metamaterials reinforcement learning |
Title | Optimization of Graded Arrays of Resonators for Energy Harvesting in Sensors as a Markov Decision Process Solved via Reinforcement Learning |
URI | https://doaj.org/article/5aba2755e58c4cbc8496ca34706ae927 |
Volume | 27 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEF6kJy-iqPhmD16XJvvK5uijtQjqoRZ6C_uYlIKm0taCv8E_7ewmh3ryIuS0DBOY3WTmW-b7hpDrWuvgeZ2x4AUCFMygzHEnWSFk0IAFhUpcmKdnPZrIx6mabo36ij1hrTxwG7i-ss7yQilQxkvvvJGl9lbIItMWSt7yyHO1BabiPzhmbSlE2-kuENf3wa8sKxmCr_y3Pn9KJMN9stdVgPSmffMB2YHmkHy_4Kf73nEi6aKmD0sbIKDV0n6t4kK8Z28iQl5RrDPpIHH2aBztE3UymhmdN3SMmDQaWHxoZOEsNvS-G6JDO0oAHS_eNuh5M7foM-mm-nRFSDup1dkRmQwHr3cj1s1JYAHxhGbWeOOkrrHyA80NAJiAiVr52tbBGpflVpuoxRUkcBNUiWErXKkyKLAeUSCOSa9ZNHBCKAhTo0WuMbgSZG4t9yJLvVAiDyI_JbcxctVHK4VRRXHqtIBbVnVbVv21ZWf_4eSc7PLIREi0wAvSWy8_4RLrg7W7SkfhB_7uuyQ |
link.rule.ids | 315,786,790,870,2115,27955,27956 |
linkProvider | Directory of Open Access Journals |
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%3Ajournal&rft.genre=article&rft.atitle=Optimization+of+Graded+Arrays+of+Resonators+for+Energy+Harvesting+in+Sensors+as+a+Markov+Decision+Process+Solved+via+Reinforcement+Learning&rft.jtitle=Engineering+proceedings&rft.au=Luca+Rosafalco&rft.au=Jacopo+Maria+De+Ponti&rft.au=Luca+Iorio&rft.au=Raffaele+Ardito&rft.date=2022-11-01&rft.pub=MDPI+AG&rft.eissn=2673-4591&rft.volume=27&rft.issue=1&rft.spage=18&rft_id=info:doi/10.3390%2Fecsa-9-13216&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_5aba2755e58c4cbc8496ca34706ae927 |