Wear Rate Prediction of Multi-Component WC/Co Cermets Using PSO-Optimized Random Forest and XGBoost Models

Wear Rate Prediction of Multi-Component WC/Co Cermets Using PSO-Optimized Random Forest and XGBoost Models | 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 Wear Rate Prediction of Multi-Component WC/Co Cermets Using PSO-Optimized Random Forest and XGBoost Models Riad Harouz, Khaled Khelil, Djamel Zelmati, Haithem Boumediri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9429192/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract The accurate prediction of wear rates of WC/Co-based cermets is essential for the development of high-performance industrial components. While machine learning (ML) offers a transformative approach to material design, the lack of specialized, high-fidelity data remains a significant challenge. In this study, an experimental dataset, comprising 116 wear tests WC/Co-based cermets materials with the addition elements, serves as the foundation for this investigation. A robust ML framework is developed to evaluate the performance transition from standard default models to optimized architectures. Specifically, baseline Random Forest (RF) and Xtreme Gradient Boosting (XGBoost) models are compared against variants optimized via the Particle Swarm Optimization (PSO) algorithm. The PSO algorithm was employed for dual-objective optimization, enabling simultaneous feature selection and hyperparameters tuning. Starting from an initial set of 12 input variables, the optimization process reduced the feature space to four predictors for the Random Forest model and nine predictors for the XGBoost model, corresponding to dimensionality reductions of 67% and 25%, respectively. This reduction improves model interpretability while preserving the most informative variables for accurate prediction. Significant performance enhancements were observed when comparing the PSO-optimized variants to the default baseline models. For instance, the PSO-RF model demonstrated an R 2 improvement from 0.8140 to 0.8406, and for the PSO-XGBoost model, the coefficient of determination (R 2 ) was increased from 0.8234 to 0.8886, representing a 7.92% improvement, while the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were reduced by 20.57% and 21.25%, respectively. WC/Co Cermets Friction tests Wear rate Machine learning (ML) Particle Swarm Optimization Full Text Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 27 Apr, 2026 Editor assigned by journal 24 Apr, 2026 First submitted to journal 23 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-9429192","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":630330988,"identity":"16983523-919a-4ca5-8f93-eadd147edab8","order_by":0,"name":"Riad Harouz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIie2RsUoDQRCGBxYuzXppb0B8hpGFDWKRV0mwSHNayhVybJrYBOv4Fqms9xhItSHtWQtWFgEhYBOcI6LNnaKVxX4w7PDDxzIzAJHIv0Qfnr6U/wiSQ+R/UND9WiH/FXyvDNxR9VoUPDT1ZcUayhMK/PxU3JSQbtqdY59eYAisbH01EoUNrWeD07BiQN+uZKAJpzNObJ1Tdb/34+UGLLrEA1WuSzFvomizEGUBpSi9Hbp9CcTts4him18yynLyW1Dj5XreJApo1aEobc9cmFAWXhqFjUx2jdM71hg6lN7cPLrifNi/zc12JBtLw+QB3U6ajo2Bao8/7xWJRCKRv/AO2Zxbozk9U50AAAAASUVORK5CYII=","orcid":"","institution":"Universite Mohamed Cherif Messaadia de Souk-Ahras","correspondingAuthor":true,"prefix":"","firstName":"Riad","middleName":"","lastName":"Harouz","suffix":""},{"id":630330989,"identity":"edd9709b-447e-4a10-b3f6-81821b7e7050","order_by":1,"name":"Khaled Khelil","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Khaled","middleName":"","lastName":"Khelil","suffix":""},{"id":630330990,"identity":"d98bb4b9-22d2-4576-bbda-24efa5c14e4e","order_by":2,"name":"Djamel Zelmati","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Djamel","middleName":"","lastName":"Zelmati","suffix":""},{"id":630330991,"identity":"ec17e30e-a3d0-40ab-bbd5-51b9bae1c958","order_by":3,"name":"Haithem Boumediri","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Haithem","middleName":"","lastName":"Boumediri","suffix":""}],"badges":[],"createdAt":"2026-04-15 15:49:43","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9429192/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9429192/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108805614,"identity":"2d11bc23-bf0a-4e7b-a70e-2b247ef08f4d","added_by":"auto","created_at":"2026-05-08 15:26:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1619157,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscriptcleanedversion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9429192/v1_covered_82c8cab5-edd4-4943-bfe2-fc4f5b9f6b96.pdf"}],"financialInterests":"","formattedTitle":"Wear Rate Prediction of Multi-Component WC/Co Cermets Using PSO-Optimized Random Forest and XGBoost Models","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":"the-international-journal-of-advanced-manufacturing-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jamt","sideBox":"Learn more about [The International Journal of Advanced Manufacturing Technology](https://www.springer.com/journal/170)","snPcode":"170","submissionUrl":"https://submission.nature.com/new-submission/170/3","title":"The International Journal of Advanced Manufacturing Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"WC/Co Cermets, Friction tests, Wear rate, Machine learning (ML), Particle Swarm Optimization","lastPublishedDoi":"10.21203/rs.3.rs-9429192/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9429192/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe accurate prediction of wear rates of WC/Co-based cermets is essential for the development of high-performance industrial components. While machine learning (ML) offers a transformative approach to material design, the lack of specialized, high-fidelity data remains a significant challenge. In this study, an experimental dataset, comprising 116 wear tests WC/Co-based cermets materials with the addition elements, serves as the foundation for this investigation. A robust ML framework is developed to evaluate the performance transition from standard default models to optimized architectures. Specifically, baseline Random Forest (RF) and Xtreme Gradient Boosting (XGBoost) models are compared against variants optimized via the Particle Swarm Optimization (PSO) algorithm. The PSO algorithm was employed for dual-objective optimization, enabling simultaneous feature selection and hyperparameters tuning. Starting from an initial set of 12 input variables, the optimization process reduced the feature space to four predictors for the Random Forest model and nine predictors for the XGBoost model, corresponding to dimensionality reductions of 67% and 25%, respectively. This reduction improves model interpretability while preserving the most informative variables for accurate prediction. Significant performance enhancements were observed when comparing the PSO-optimized variants to the default baseline models. For instance, the PSO-RF model demonstrated an R\u003csup\u003e2\u003c/sup\u003e improvement from 0.8140 to 0.8406, and for the PSO-XGBoost model, the coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e) was increased from 0.8234 to 0.8886, representing a 7.92% improvement, while the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were reduced by 20.57% and 21.25%, respectively.\u003c/p\u003e","manuscriptTitle":"Wear Rate Prediction of Multi-Component WC/Co Cermets Using PSO-Optimized Random Forest and XGBoost Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-06 06:20:34","doi":"10.21203/rs.3.rs-9429192/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2026-04-30T12:49:22+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-27T12:37:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-24T13:25:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"The International Journal of Advanced Manufacturing Technology","date":"2026-04-23T05:44:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-international-journal-of-advanced-manufacturing-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jamt","sideBox":"Learn more about [The International Journal of Advanced Manufacturing Technology](https://www.springer.com/journal/170)","snPcode":"170","submissionUrl":"https://submission.nature.com/new-submission/170/3","title":"The International Journal of Advanced Manufacturing Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"915c9f0e-48b6-4ce6-921a-344ef7639b54","owner":[],"postedDate":"May 6th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"","date":"2026-04-30T12:49:22+00:00","index":0,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-06T06:20:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-06 06:20:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9429192","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9429192","identity":"rs-9429192","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}