Real-Time Machine Learning Control of a Hall Thruster Discharge Plasma

Real-Time Machine Learning Control of a Hall Thruster Discharge Plasma | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Real-Time Machine Learning Control of a Hall Thruster Discharge Plasma Ajay Krishnan, Bogdan Vlahov, Jason Gibson, Dan Lev, Evangelos Theodorou, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9325578/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Facility effects are known to alter Hall thruster performance between ground and space.Furthermore, discharge current oscillations are linked to impacting both the lifetime andthrust of Hall thrusters. In this work, we present a machine learning–based control frameworkdesigned for nonlinear, time-varying systems with hysteresis that can mitigate breathing modeoscillations and adapt to environmental changes. Unlike reactive approaches such as PIDcontrol, our method is predictive and flexible across a range of control objectives. Specifically,we employ echo state networks (ESNs), a class of recurrent neural networks well-suited fortime-series prediction. To train and test the model, we apply a diverse set of discharge voltageperturbations—including sine, triangle, square, ramp, chirp, bandlimited gaussian noise,pseudorandom binary sequence, and PID—on a 6-kW H6 Hall thruster operated at 400 Vas well as 250 V at 4.3 A, and measure the resulting discharge current as a part of a processknown as system identification. Using extended convergent cross mapping, we confirm causalrelationships between the applied perturbations and discharge current response. The ESNachieves 90% prediction accuracy on previously unseen time-series data based on variance. Wethen integrate the ESN into a nonlinear model predictive control (NMPC) framework, creatinga machine learning controller, to compute optimal control trajectories that suppress dischargeoscillations. NMPC simulations indicate that discharge current oscillations can be reducedby over 90%. Finally, we employ a deployment strategy in which the learned control policy isembedded as a multilayer perceptron on a field-programmable gate array, enabling real-timeexperimental implementation. The machine learning controller reduces oscillations by 1.33%while PID increases oscillations by 4.17% at the 250 V operating point. The machine learning(ML) controller has the potential to be applicable to other operating points by following astandard procedure of system identification and control optimization. Online and adaptive MLcontrol can be used in the future to improve oscillation reduction. Full Text Additional Declarations No competing interests reported. Supplementary Files MachineLearningControlJEP2026Appendix.pdf Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 03 May, 2026 Reviewers agreed at journal 03 May, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers invited by journal 18 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Submission checks completed at journal 13 Apr, 2026 First submitted to journal 05 Apr, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9325578","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625554055,"identity":"7ad2e9eb-fb68-4238-81b7-380d207e7773","order_by":0,"name":"Ajay Krishnan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIiWNgGAWjYFCCAwyMDQwSDAYg9gewCA8QsxGphXEGA5BFWAsDSAsDWAszDzFa+BsPP5OcucfC3ly6+dljm192dfzsZw8wfCg7jFOLxIFjZpIbnkkk7pxzzNw4ty9ZQrInL4FxxjncWhgOHDCTfHBAIsHgRoKZdG4Ps4TBDR4DZt423FrkDxz/BtJib3Aj/Zu0ZU+9hD1Iy188WgwOnAE67IAE44YbOWbSDD8OSxhIALUw4tFieOBMseWMAxKJQC1lkr0NxyVnnMkxONhzLh2nFrkbxzfe7DlQB3LYNokff6r5+dvPGD74UWaN2/sSB1gk4BzGNmiY4FYPBPwNzB8QvD941Y6CUTAKRsEIBQBmxFzO36+Z/QAAAABJRU5ErkJggg==","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Ajay","middleName":"","lastName":"Krishnan","suffix":""},{"id":625554057,"identity":"e64e3ad7-8749-48a3-9492-70fb9eee83e1","order_by":1,"name":"Bogdan Vlahov","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bogdan","middleName":"","lastName":"Vlahov","suffix":""},{"id":625554058,"identity":"97a38df2-c6e7-4466-80f1-0b99c76e9017","order_by":2,"name":"Jason Gibson","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jason","middleName":"","lastName":"Gibson","suffix":""},{"id":625554059,"identity":"7587180e-a065-4fd3-ad88-627dcb070797","order_by":3,"name":"Dan Lev","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Lev","suffix":""},{"id":625554060,"identity":"6ff7392c-ffe0-402d-aa21-addb943f81c0","order_by":4,"name":"Evangelos Theodorou","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Evangelos","middleName":"","lastName":"Theodorou","suffix":""},{"id":625554065,"identity":"03ac4ad2-30fe-4d13-90d7-776cc0ac2c44","order_by":5,"name":"Mitchell Walker","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Mitchell","middleName":"","lastName":"Walker","suffix":""},{"id":625554066,"identity":"9a0f68e7-771d-4d7b-96a7-8bd929b248fd","order_by":6,"name":"Maryam Saeedifard","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Maryam","middleName":"","lastName":"Saeedifard","suffix":""}],"badges":[],"createdAt":"2026-04-05 10:24:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9325578/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9325578/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107869732,"identity":"593b0cf4-4906-4cfb-8450-4d7cc6fe58ad","added_by":"auto","created_at":"2026-04-27 07:37:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2084390,"visible":true,"origin":"","legend":"","description":"","filename":"MachineLearningControlJEP472026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9325578/v1_covered_d266ddb4-4e92-4406-9a68-89cc8e2f2605.pdf"},{"id":107837771,"identity":"7c7bd8f9-b551-418b-a14b-455c23394fe8","added_by":"auto","created_at":"2026-04-26 16:58:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":110604,"visible":true,"origin":"","legend":"","description":"","filename":"MachineLearningControlJEP2026Appendix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9325578/v1/ba7c8814bc79fcc60715c9e7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Real-Time Machine Learning Control of a Hall Thruster Discharge Plasma","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-electric-propulsion","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"joeprop","sideBox":"Learn more about [Journal of Electric Propulsion](https://www.springer.com/journal/44205)","snPcode":"44205","submissionUrl":"https://submission.nature.com/new-submission/44205/3","title":"Journal of Electric Propulsion","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9325578/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9325578/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Facility effects are known to alter Hall thruster performance between ground and space.Furthermore, discharge current oscillations are linked to impacting both the lifetime andthrust of Hall thrusters. In this work, we present a machine learning–based control frameworkdesigned for nonlinear, time-varying systems with hysteresis that can mitigate breathing modeoscillations and adapt to environmental changes. Unlike reactive approaches such as PIDcontrol, our method is predictive and flexible across a range of control objectives. Specifically,we employ echo state networks (ESNs), a class of recurrent neural networks well-suited fortime-series prediction. To train and test the model, we apply a diverse set of discharge voltageperturbations—including sine, triangle, square, ramp, chirp, bandlimited gaussian noise,pseudorandom binary sequence, and PID—on a 6-kW H6 Hall thruster operated at 400 Vas well as 250 V at 4.3 A, and measure the resulting discharge current as a part of a processknown as system identification. Using extended convergent cross mapping, we confirm causalrelationships between the applied perturbations and discharge current response. The ESNachieves 90% prediction accuracy on previously unseen time-series data based on variance. Wethen integrate the ESN into a nonlinear model predictive control (NMPC) framework, creatinga machine learning controller, to compute optimal control trajectories that suppress dischargeoscillations. NMPC simulations indicate that discharge current oscillations can be reducedby over 90%. Finally, we employ a deployment strategy in which the learned control policy isembedded as a multilayer perceptron on a field-programmable gate array, enabling real-timeexperimental implementation. The machine learning controller reduces oscillations by 1.33%while PID increases oscillations by 4.17% at the 250 V operating point. The machine learning(ML) controller has the potential to be applicable to other operating points by following astandard procedure of system identification and control optimization. Online and adaptive MLcontrol can be used in the future to improve oscillation reduction.","manuscriptTitle":"Real-Time Machine Learning Control of a Hall Thruster Discharge Plasma","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-26 16:58:52","doi":"10.21203/rs.3.rs-9325578/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-03T20:43:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14759833354685340462821513462433033297","date":"2026-05-03T17:07:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269155505943276017722226967576415493333","date":"2026-04-18T21:53:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-18T15:30:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T13:14:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-13T06:01:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Electric Propulsion","date":"2026-04-05T10:06:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-electric-propulsion","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"joeprop","sideBox":"Learn more about [Journal of Electric Propulsion](https://www.springer.com/journal/44205)","snPcode":"44205","submissionUrl":"https://submission.nature.com/new-submission/44205/3","title":"Journal of Electric Propulsion","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"dd4ddad5-6adf-4b0e-86a4-113d8e23a40b","owner":[],"postedDate":"April 26th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-03T20:43:53+00:00","index":13,"fulltext":""},{"type":"reviewerAgreed","content":"14759833354685340462821513462433033297","date":"2026-05-03T17:07:33+00:00","index":12,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-26T16:58:52+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-26 16:58:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9325578","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9325578","identity":"rs-9325578","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}