An Integrated Machine Learning and AHP-Optimized Framework for Power Transformer Risk Ranking based on IEEE C57.104-2019 Standard

An Integrated Machine Learning and AHP-Optimized Framework for Power Transformer Risk Ranking based on IEEE C57.104-2019 Standard | 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 An Integrated Machine Learning and AHP-Optimized Framework for Power Transformer Risk Ranking based on IEEE C57.104-2019 Standard Pankaj Chawla, Dr. Ayyala Kishore Ajay Ayalla This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9213964/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Dissolved Gas Analysis (DGA) continues to be the foremost technique for identifying nascent faults in power transformers. Interpreting DGA results under contemporary standards such as IEEE C57.104 increasingly demands moving beyond fixed thresholds toward adaptive, risk-focused approaches. This paper presents a hybrid diagnostic methodology that fuses Decision Tree (DT) and Random Forest (RF) machine learning classifiers with the Analytic Hierarchy Process (AHP). Using 374 transformer oil samples, classifiers were trained to assign health states according to the IEEE C57.104-2019 thresholds. AHP was then used to derive priority vectors for key combustible gases to enhance diagnostic sensitivity, highlighting Acetylene (C 2 H 2 ) and Hydrogen (H 2 ) as principal risk contributors. Evaluation metrics showed the Decision Tree attained a Precision of 100% and a Recall of 73.33% in detecting abnormal cases. The AHP-weighted Health Index (HI) segmented the transformer samples into five categories and pinpointed 2.7% of units as requiring urgent action. This integrated approach offers a scalable predictive-maintenance solution for modern grid assets. Power Transformers Dissolved Gas Analysis (DGA) Decision Tree Random Forest Analytic Hierarchy Process (AHP) Health Index IEEE C57.104-2019 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-9213964","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":611491900,"identity":"c9d71af6-5bda-469b-89e6-006b0c4c9218","order_by":0,"name":"Pankaj Chawla","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYHACZgYGHiB1gPkAA2MDhE+sFrYEUrSAwAEeA4gWQsCc/exhgx8yNvl8x898k/i5w0aOgZ33AF4tlj15yYk9PGmWM8/kbpPsPZNmzMDMl4BXi8GBHOMDPDyHDQwO5G6T4G07nNjADHQhXi3n3xgf/MPz3wDIeCb5lygtN3KMk3l4DhgAGWzSRNliOeONsbEMT7KB5I1nxtaybWnGbIS0mPPnGEu+7bEz4Duf/PDm2zYbOX7+MwQcBiIYe8BsFgkQyYZXPUwLww8wyfyBkOpRMApGwSgYmQAAtGpDr33XD4gAAAAASUVORK5CYII=","orcid":"","institution":"K R Mangalam University","correspondingAuthor":true,"prefix":"","firstName":"Pankaj","middleName":"","lastName":"Chawla","suffix":""},{"id":611491901,"identity":"84d19ae3-aba0-4e83-b66b-1918fd900d47","order_by":1,"name":"Dr. Ayyala Kishore Ajay Ayalla","email":"","orcid":"","institution":"K R Mangalam University","correspondingAuthor":false,"prefix":"Dr.","firstName":"Ayyala","middleName":"Kishore Ajay","lastName":"Ayalla","suffix":""}],"badges":[],"createdAt":"2026-03-24 15:38:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9213964/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9213964/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105566465,"identity":"80bfd8ae-f909-41ea-a443-1baff826eb01","added_by":"auto","created_at":"2026-03-27 12:56:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":593551,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchpaperAHP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9213964/v1_covered_4bd0c6ff-4556-4382-a554-21fb2fd6a008.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Integrated Machine Learning and AHP-Optimized Framework for Power Transformer Risk Ranking based on IEEE C57.104-2019 Standard","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Power Transformers, Dissolved Gas Analysis (DGA), Decision Tree, Random Forest, Analytic Hierarchy Process (AHP), Health Index, IEEE C57.104-2019","lastPublishedDoi":"10.21203/rs.3.rs-9213964/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9213964/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDissolved Gas Analysis (DGA) continues to be the foremost technique for identifying nascent faults in power transformers. Interpreting DGA results under contemporary standards such as IEEE C57.104 increasingly demands moving beyond fixed thresholds toward adaptive, risk-focused approaches. This paper presents a hybrid diagnostic methodology that fuses Decision Tree (DT) and Random Forest (RF) machine learning classifiers with the Analytic Hierarchy Process (AHP). Using 374 transformer oil samples, classifiers were trained to assign health states according to the IEEE C57.104-2019 thresholds. AHP was then used to derive priority vectors for key combustible gases to enhance diagnostic sensitivity, highlighting Acetylene (C\u003csub\u003e2\u003c/sub\u003eH\u003csub\u003e2\u003c/sub\u003e) and Hydrogen (H\u003csub\u003e2\u003c/sub\u003e) as principal risk contributors. Evaluation metrics showed the Decision Tree attained a Precision of 100% and a Recall of 73.33% in detecting abnormal cases. The AHP-weighted Health Index (HI) segmented the transformer samples into five categories and pinpointed 2.7% of units as requiring urgent action. This integrated approach offers a scalable predictive-maintenance solution for modern grid assets.\u003c/p\u003e","manuscriptTitle":"An Integrated Machine Learning and AHP-Optimized Framework for Power Transformer Risk Ranking based on IEEE C57.104-2019 Standard","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-26 05:45:54","doi":"10.21203/rs.3.rs-9213964/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"31229309-30b2-48dc-a888-57d17f68ebe9","owner":[],"postedDate":"March 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-26T05:45:54+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-26 05:45:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9213964","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9213964","identity":"rs-9213964","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}