{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:26:08Z","timestamp":1791393968402,"version":"4.3.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:00:00Z","timestamp":1768608000000},"content-version":"vor","delay-in-days":54,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Natural Science Foundation of Jiangsu Province Basic Research Program-Youth Fund Project","award":["BK20230171"],"award-info":[{"award-number":["BK20230171"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Steel mechanical properties such as yield strength (YS), tensile strength (TS), and elongation (EL) are critical indicators of product quality and safety in downstream applications. In industrial practice, these properties are commonly obtained through tensile testing, which is destructive, time-consuming, and costly, and thus provides limited support for rapid quality feedback in continuous production. This work explores a data-driven alternative that leverages historical production records to predict steel mechanical properties. Motivated by the strongly coupled chemical and physical evolution of steel during heating, rolling, cooling, and heat treatment, we propose an ensemble-learning framework with Bayesian optimization for robust multi-target prediction under real production conditions. Specifically, we construct predictive datasets covering all steel grades produced on the same production line and design a stacking ensemble that uses Random Forest (RF) and CatBoost (CATB) as base learners and Linear Regression (LR) as a meta-learner, with Bayesian optimization for automated hyperparameter tuning. Extensive experiments on independent test data and online production data demonstrate strong predictive performance and practical applicability. Under industrial tolerance bands, the proposed method achieves 92.62% hit rate for YS (\u00b130 MPa), 97.41% for TS (\u00b130 MPa), and 94.53% for EL (\u00b14%), outperforming conventional single-model baselines. These results indicate that the proposed approach can deliver accurate, stable, and generalizable predictions across steel grades, reducing reliance on frequent destructive testing and enabling timely process monitoring and quality control in steel manufacturing.<\/jats:p>","DOI":"10.1007\/s40747-025-02168-1","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T12:37:31Z","timestamp":1763987851000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Bayesian-Optimized Ensemble Models for Predicting Steel Mechanical Properties"],"prefix":"10.1007","volume":"12","author":[{"given":"Suyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingqi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangshan","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fucun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guizhou","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6770-326X","authenticated-orcid":false,"given":"Fang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"2168_CR1","doi-asserted-by":"publisher","first-page":"109201","DOI":"10.1016\/j.matdes.2020.109201","volume":"197","author":"Q Xie","year":"2021","unstructured":"Xie Q, Suvarna M, Li JL et al (2021) Online prediction of mechanical properties of hot rolled steel plate using machine learning. Mater Des 197:109201","journal-title":"Mater Des"},{"issue":"6","key":"2168_CR2","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1007\/s12613-022-2536-y","volume":"30","author":"FF Li","year":"2023","unstructured":"Li FF, He AR, Song Y et al (2023) Deep learning for predictive mechanical properties of hot-rolled strip in complex manufacturing systems. Int J Minerals Metall 30(6):1093\u20131103","journal-title":"Int J Minerals Metall"},{"issue":"8","key":"2168_CR3","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1007\/s12613-020-2168-z","volume":"28","author":"SW Wu","year":"2021","unstructured":"Wu SW, Yang J, Cao GM (2021) Prediction of the Charpy V-notch impact energy of low carbon steel using a shallow neural network and deep learning. Int J Minerals Metall Mater Des 28(8):1309\u20131320","journal-title":"Int J Minerals Metall Mater Des"},{"issue":"3\u20134","key":"2168_CR4","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/0924-0136(95)02089-6","volume":"57","author":"ZY Liu","year":"1996","unstructured":"Liu ZY, Wang WD, Gao W (1996) Prediction of the mechanical properties of hot-rolled C-Mn steels using artificial neural networks. J Mater Process Technol 57(3\u20134):332\u2013336","journal-title":"J Mater Process Technol"},{"key":"2168_CR5","doi-asserted-by":"crossref","unstructured":"Yang YY, Mahfouf M, Linkens DA et al (2009) Tensile strength prediction for hot rolled steels by Bayesian neural network model. In: IFAC Proceedings Volumes. pp 255\u2013260","DOI":"10.3182\/20091014-3-CL-4011.00046"},{"key":"2168_CR6","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.1016\/j.proeng.2012.06.395","volume":"38","author":"P Saravanakumar","year":"2012","unstructured":"Saravanakumar P, Jothimani V, Sureshbabu L et al (2012) Prediction of mechanical properties of low carbon steel in hot rolling process using artificial neural network model. Procedia Eng 38:3418\u20133425","journal-title":"Procedia Eng"},{"key":"2168_CR7","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1007\/s12666-019-01624-0","volume":"72","author":"SW Wu","year":"2019","unstructured":"Wu SW, Ren JK, Zhou XG et al (2019) Comparisons of different data-driven modeling techniques for predicting tensile strength of X70 pipeline steels. Trans Indian Inst Met 72:1277\u20131288","journal-title":"Trans Indian Inst Met"},{"issue":"4","key":"2168_CR8","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1504\/IJMIC.2019.107482","volume":"33","author":"JX Chen","year":"2019","unstructured":"Chen JX, Zhao F, Sun YG et al (2019) Prediction model based on XGBoost for mechanical properties of steel materials. Int J Modelling Identif Control 33(4):322\u2013330","journal-title":"Int J Modelling Identif Control"},{"key":"2168_CR9","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1007\/s12666-020-01928-6","volume":"73","author":"SDL Jagadish","year":"2020","unstructured":"Jagadish SDL, Barad S (2020) Prediction of mechanical properties of Fe 415 steel in hot rolling process using artificial neural network. Trans Indian Inst Met 73:1535\u20131542","journal-title":"Trans Indian Inst Met"},{"key":"2168_CR10","doi-asserted-by":"crossref","unstructured":"Cheng TQ, Chen GC (2021) Prediction of mechanical properties of hot-rolled strip steel based on PCA-GBDT method. In: Journal of Physics: Conference Series. pp 012002","DOI":"10.1088\/1742-6596\/1774\/1\/012002"},{"key":"2168_CR11","first-page":"87","volume":"29","author":"KY Hao","year":"2023","unstructured":"Hao KY, Jin ZY, Yuan CS et al (2023) Rolling process optimization and performance prediction of C-Mn steel based on intelligent algorithm. J Plast Eng 29:87\u201393","journal-title":"J Plast Eng"},{"issue":"05","key":"2168_CR12","first-page":"338","volume":"41","author":"SX Hu","year":"2018","unstructured":"Hu SX, Li WG, Yang W (2018) Mechanical property prediction of hot-rolled strip based on convolutional neural network. J Wuhan Univ Sci Technol 41(05):338\u2013344","journal-title":"J Wuhan Univ Sci Technol"},{"issue":"6","key":"2168_CR13","first-page":"2","volume":"44","author":"Y Song","year":"2020","unstructured":"Song Y, Li B, Liu C et al (2020) Prediction model of mechanical properties of hot rolled strip based on improved stacked self-encoder. Metall Ind Autom 44(6):2","journal-title":"Metall Ind Autom"},{"issue":"1","key":"2168_CR14","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/s12613-022-2547-8","volume":"30","author":"G Xu","year":"2023","unstructured":"Xu G, He JS, L\u00fc ZM et al (2023) Prediction of mechanical properties for deep drawing steel by deep learning. Int J Minerals Metall Mater Des 30(1):156\u2013165","journal-title":"Int J Minerals Metall Mater Des"},{"key":"2168_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.jes.2022.01.044","volume":"123","author":"TY Zhu","year":"2023","unstructured":"Zhu TY, Wang XD, Yu Y et al (2023) Multi-process and multi-pollutant control technology for ultra-low emissions in the iron and steel industry. J Environ Sci 123:83\u201395","journal-title":"J Environ Sci"},{"key":"2168_CR16","doi-asserted-by":"publisher","first-page":"114946","DOI":"10.1016\/j.apenergy.2020.114946","volume":"268","author":"WQ Sun","year":"2020","unstructured":"Sun WQ, Wang Q, Zhou Y et al (2020) Material and energy flows of the iron and steel industry: status quo, challenges and perspectives. Appl Energy 268:114946","journal-title":"Appl Energy"},{"issue":"3","key":"2168_CR17","doi-asserted-by":"publisher","first-page":"e43","DOI":"10.1002\/imt2.43","volume":"1","author":"ZG Gu","year":"2022","unstructured":"Gu ZG (2022) Complex heatmap visualization. Imeta 1(3):e43","journal-title":"Imeta"},{"key":"2168_CR18","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","volume":"14","author":"XB Dong","year":"2020","unstructured":"Dong XB, Yu ZW, Cao WM et al (2020) A survey on ensemble learning. Front Comput Sci 14:241\u2013258","journal-title":"Front Comput Sci"},{"key":"2168_CR19","doi-asserted-by":"crossref","unstructured":"Pavlyshenko B (2018) Using stacking approaches for machine learning models. In: 2018 IEEE second international conference on data stream mining & processing (DSMP). pp 255\u2013258","DOI":"10.1109\/DSMP.2018.8478522"},{"issue":"2","key":"2168_CR20","doi-asserted-by":"publisher","first-page":"140","DOI":"10.38094\/jastt1457","volume":"1","author":"D Maulud","year":"2020","unstructured":"Maulud D, Abdulazeez AM (2020) A review on linear regression comprehensive in machine learning. J Appl Sci Technol Trends 1(2):140\u2013147","journal-title":"J Appl Sci Technol Trends"},{"key":"2168_CR21","doi-asserted-by":"publisher","unstructured":"Shafiq M, Thakre K, Krishna KR et al (2023) Continuous quality control evaluation during manufacturing using supervised learning algorithm for industry 4.0. Int J Adv Manuf Technol. https:\/\/doi.org\/10.1007\/s00170-023-10847-x","DOI":"10.1007\/s00170-023-10847-x"},{"key":"2168_CR22","doi-asserted-by":"crossref","unstructured":"Parmar A, Katariya R, Patel V (2018) A review on random forest: An ensemble classifier; proceedings of the International conference on intelligent data communication technologies and internet of things. Springer. 758\u2013763","DOI":"10.1007\/978-3-030-03146-6_86"},{"issue":"1","key":"2168_CR23","doi-asserted-by":"publisher","first-page":"7791582","DOI":"10.1155\/2022\/7791582","volume":"2022","author":"K Upreti","year":"2022","unstructured":"Upreti K, Verma M, Agrawal M et al (2022) Prediction of mechanical strength by using an artificial neural network and random forest algorithm. J Nanomaterials 2022(1):7791582","journal-title":"J Nanomaterials"},{"key":"2168_CR24","unstructured":"Dorogush AV, Ershov V, Gulin A (2018) CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:11363"},{"key":"2168_CR25","unstructured":"Prokhorenkova L, Gusev G, Vorobev A et al (2018) CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems. 31"},{"key":"2168_CR26","unstructured":"Eriksson D, Pearce M, Gardner J et al (2019) Scalable global optimization via local Bayesian optimization. Advances in neural information processing systems. 32"},{"issue":"13s","key":"2168_CR27","first-page":"1","volume":"55","author":"XL Wang","year":"2023","unstructured":"Wang XL, Jin YC, Schmitt S et al (2023) Recent advances in Bayesian optimization. ACM-CSUR 55(13s):1\u201336","journal-title":"ACM-CSUR"},{"key":"2168_CR28","doi-asserted-by":"publisher","first-page":"103301","DOI":"10.1016\/j.mtcomm.2022.103301","volume":"31","author":"Q Lan","year":"2022","unstructured":"Lan Q, Wang XC, Sun JW et al (2022) Artificial neural network approach for mechanical properties prediction of as-cast A380 aluminum alloy. Mater Today Commun 31:103301","journal-title":"Mater Today Commun"},{"key":"2168_CR29","doi-asserted-by":"publisher","first-page":"103679","DOI":"10.1016\/j.mtcomm.2022.103679","volume":"32","author":"DW Li","year":"2022","unstructured":"Li DW, Huang WQ, Liu JX et al (2022) Prediction of mechanical properties of ZL702A based on neural network and regression analysis. Mater Today Commun 32:103679","journal-title":"Mater Today Commun"},{"key":"2168_CR30","doi-asserted-by":"crossref","unstructured":"Wu SW, Yang J, Cao GM et al (2020) Elevating prediction performance for mechanical properties of hot-rolled strips by using semi-supervised regression and deep learning. In: IEEE Access. pp 134124\u2013134136","DOI":"10.1109\/ACCESS.2020.3010506"},{"key":"2168_CR31","first-page":"1","volume":"71","author":"GZ Peng","year":"2022","unstructured":"Peng GZ, Cheng YL, Wang HW et al (2022) Industrial IoT-enabled prediction interval estimation of mechanical performances for hot-rolling steel. IEEE Trans Instrum Meas 71:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"key":"2168_CR32","unstructured":"l Ke G, Meng Q, Finley T et al (2017) Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 30"},{"issue":"5","key":"2168_CR33","doi-asserted-by":"publisher","first-page":"765","DOI":"10.3390\/math8050765","volume":"8","author":"WZ Liang","year":"2020","unstructured":"Liang WZ, Luo SZ, Zhao GY et al (2020) Predicting hard rock pillar stability using GBDT, XGBoost, and LightGBM algorithms. Mathematics 8(5):765","journal-title":"Mathematics"},{"key":"2168_CR34","unstructured":"Prettenhofer P, Louppe G (2014) Gradient boosted regression trees in scikit-learn. In: PyData"},{"issue":"4","key":"2168_CR35","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1109\/TNNLS.2015.2424995","volume":"27","author":"JX Tang","year":"2015","unstructured":"Tang JX, Deng CW, Huang GB (2015) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Networks Learn Syst 27(4):809\u2013821","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"issue":"29","key":"2168_CR36","doi-asserted-by":"publisher","first-page":"41611","DOI":"10.1007\/s11042-021-11007-7","volume":"81","author":"J Wang","year":"2022","unstructured":"Wang J, Lu SY, Wang SH et al (2022) A review on extreme learning machine. Multimedia Tools Appl 81(29):41611\u201341660","journal-title":"Multimedia Tools Appl"},{"key":"2168_CR37","doi-asserted-by":"publisher","first-page":"109067","DOI":"10.1016\/j.asoc.2022.109067","volume":"125","author":"JW Dong","year":"2022","unstructured":"Dong JW, Chen YM, Yao BY et al (2022) A neural network boosting regression model based on XGBoost. Appl Soft Comput 125:109067","journal-title":"Appl Soft Comput"},{"key":"2168_CR38","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1016\/j.jclepro.2018.08.207","volume":"203","author":"MW Ahmad","year":"2018","unstructured":"Ahmad MW, Reynolds J, Rezgui Y (2018) Predictive modelling for solar thermal energy systems: a comparison of support vector regression, random forest, extra trees and regression trees. J Clean Prod 203:810\u2013821","journal-title":"J Clean Prod"},{"issue":"3","key":"2168_CR39","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1109\/TR.2018.2847353","volume":"67","author":"XX Yang","year":"2018","unstructured":"Yang XX, Wen WS (2018) Ridge and Lasso regression models for cross-version defect prediction. IEEE Trans Reliab 67(3):885\u2013896","journal-title":"IEEE Trans Reliab"},{"issue":"232","key":"2168_CR40","first-page":"1","volume":"18","author":"BS Price","year":"2018","unstructured":"Price BS, Sherwood B (2018) A cluster elastic net for multivariate regression. J Mach Learn Res 18(232):1\u201339","journal-title":"J Mach Learn Res"},{"key":"2168_CR41","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.neucom.2017.04.018","volume":"251","author":"YS Song","year":"2017","unstructured":"Song YS, Liang JY, Lu J et al (2017) An efficient instance selection algorithm for k nearest neighbor regression. Neurocomputing 251:26\u201334","journal-title":"Neurocomputing"},{"key":"2168_CR42","doi-asserted-by":"crossref","unstructured":"Karim R, Alam MK, Hossain MR (2021) Stock market analysis using linear regression and decision tree regression. In: 2021 1st international conference on emerging smart technologies and applications (eSmarTA). pp 1\u20136","DOI":"10.1109\/eSmarTA52612.2021.9515762"},{"key":"2168_CR43","doi-asserted-by":"crossref","unstructured":"An K, Meng J (2010) Voting-averaged combination method for regressor ensemble. In: International Conference on Intelligent Computing. pp 540\u2013546","DOI":"10.1007\/978-3-642-14922-1_67"},{"key":"2168_CR44","unstructured":"Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02168-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02168-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02168-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:23:52Z","timestamp":1771230232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02168-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2168"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02168-1","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"30 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"81"}}