{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T06:00:11Z","timestamp":1780466411978,"version":"3.54.1"},"reference-count":76,"publisher":"The Royal Society","issue":"2264","license":[{"start":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:00:00Z","timestamp":1700438400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/royalsociety.org\/journals\/ethics-policies\/data-sharing-mining\/"}],"content-domain":{"domain":["royalsocietypublishing.org"],"crossmark-restriction":true},"short-container-title":["Phil. Trans. R. Soc. A."],"published-print":{"date-parts":[[2024,1,8]]},"abstract":"\n A data-driven approach is developed to predict the fracture load of a notched component. To do so, more than 1500 fracture tests (507 unique experimental data points) on mixed-mode I\/II loading of notched brittle samples were collected from the literature. After pre-processing the raw data, six features of maximum tangential stress\n \n \n (<\/mml:mo>\n \n \u03c3<\/mml:mi>\n \n \u03b8<\/mml:mi>\n \u03b8<\/mml:mi>\n <\/mml:mrow>\n \n \n max<\/mml:mtext>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:msubsup>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n , maximum tangential stress angle\n \n \n (<\/mml:mo>\n \n \n \u03b8<\/mml:mi>\n \n \n \u03c3<\/mml:mi>\n \n \u03b8<\/mml:mi>\n \u03b8<\/mml:mi>\n <\/mml:mrow>\n \n \n max<\/mml:mtext>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:msubsup>\n <\/mml:mrow>\n <\/mml:msub>\n <\/mml:mrow>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n , ultimate tensile strength\n \n \n (<\/mml:mo>\n \n \n \u03c3<\/mml:mi>\n u<\/mml:mi>\n <\/mml:msub>\n <\/mml:mrow>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n , fracture toughness\n \n \n (<\/mml:mo>\n \n \n K<\/mml:mi>\n \n I<\/mml:mi>\n c<\/mml:mi>\n <\/mml:mrow>\n <\/mml:msub>\n <\/mml:mrow>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n , notch opening angle\n \n \n (<\/mml:mo>\n 2<\/mml:mn>\n \u03b1<\/mml:mi>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n and notch tip radius\n \n \n (<\/mml:mo>\n \u03c1<\/mml:mi>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n were selected by using the neighbourhood component analysis (NCA) technique. To predict the fracture load of various types of notched samples, several machine learning (ML) models were trained using the methods of Gaussian process regression (GPR), decision tree ensemble and artificial neural network (ANN). Then, the Bayesian optimization algorithm was applied to find the optimum hyperparameters for each model. Lastly, the performance of the models in predicting fracture load was evaluated against 124 unseen data points. The results revealed the high potential of data-driven methods for assessing the fracture load of notched brittle components with acceptable precisions of 92%, 89% and 88% accuracy, respectively, for GPR, decision tree ensemble and ANN models. The superior performance of the GPR method can be attributed to its ability to capture complex nonlinear relationships in the data while providing reliable uncertainty estimates. Furthermore, thanks to its interpolation capabilities, GPR is able to seamlessly fill the gaps between data points, resulting in more comprehensive and precise predictions across the entire range of input data. Additionally, the presented models were capable of predicting the fracture load of VO-shaped notched samples with acceptable accuracy, though this type of notch was not used in the model training process.\n <\/jats:p>\n This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.<\/jats:p>","DOI":"10.1098\/rsta.2022.0397","type":"journal-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:05:12Z","timestamp":1700438712000},"update-policy":"https:\/\/doi.org\/10.1098\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Data-driven based fracture prediction of notched components"],"prefix":"10.1098","volume":"382","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3830-3181","authenticated-orcid":true,"given":"Hossein","family":"Talebi","sequence":"first","affiliation":[{"name":"Fatigue and Fracture Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology,Narmak 16846, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6810-0214","authenticated-orcid":true,"given":"Bahador","family":"Bahrami","sequence":"additional","affiliation":[{"name":"Fatigue and Fracture Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology,Narmak 16846, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0209-5475","authenticated-orcid":true,"given":"Mohammad","family":"Daneshfar","sequence":"additional","affiliation":[{"name":"Fatigue and Fracture Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology,Narmak 16846, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Bagherifard","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majid R.","family":"Ayatollahi","sequence":"additional","affiliation":[{"name":"Fatigue and Fracture Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology,Narmak 16846, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2023,11,20]]},"reference":[{"key":"e_1_3_6_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2022.108914"},{"key":"e_1_3_6_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmecsci.2023.108214"},{"key":"e_1_3_6_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2021.110878"},{"key":"e_1_3_6_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2021.107890"},{"key":"e_1_3_6_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05035-x"},{"key":"e_1_3_6_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-021-01594-2"},{"key":"e_1_3_6_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijfatigue.2022.107342"},{"key":"e_1_3_6_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.114218"},{"key":"e_1_3_6_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2023.108325"},{"key":"e_1_3_6_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109377"},{"key":"e_1_3_6_12_2","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMM.782.170"},{"key":"e_1_3_6_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/ffe.13464"},{"key":"e_1_3_6_14_2","doi-asserted-by":"publisher","DOI":"10.1111\/ffe.12977"},{"key":"e_1_3_6_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/ma15248779"},{"key":"e_1_3_6_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11223-019-00126-0"},{"key":"e_1_3_6_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2010.12.034"},{"key":"e_1_3_6_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.prostr.2021.10.055"},{"key":"e_1_3_6_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2020.106990"},{"key":"e_1_3_6_20_2","doi-asserted-by":"publisher","DOI":"10.12989\/sem.2014.50.6.723"},{"key":"e_1_3_6_21_2","doi-asserted-by":"publisher","DOI":"10.5267\/j.esm.2020.3.004"},{"key":"e_1_3_6_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11223-016-9761-4"},{"key":"e_1_3_6_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.euromechsol.2014.06.009"},{"key":"e_1_3_6_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2020.102682"},{"key":"e_1_3_6_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00707-015-1323-5"},{"key":"e_1_3_6_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2017.05.009"},{"key":"e_1_3_6_27_2","doi-asserted-by":"publisher","DOI":"10.1520\/JTE20140496"},{"key":"e_1_3_6_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10704-022-00653-z"},{"key":"e_1_3_6_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijsolstr.2022.111798"},{"key":"e_1_3_6_30_2","first-page":"700","article-title":"Fracture propagation in Brazilian discs with multiple pre-existing notches by using a phase field method","volume":"62","author":"Zhou S","year":"2018","unstructured":"Zhou S. 2018 Fracture propagation in Brazilian discs with multiple pre-existing notches by using a phase field method. Period. Polytech. Civ. Eng. 62, 700-708. (doi:10.3311\/PPci.11916)","journal-title":"Period. Polytech. Civ. Eng."},{"key":"e_1_3_6_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2022.108628"},{"key":"e_1_3_6_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2017.01.005"},{"key":"e_1_3_6_33_2","doi-asserted-by":"publisher","DOI":"10.1051\/e3sconf\/202015605027"},{"key":"e_1_3_6_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00603-022-03134-w"},{"key":"e_1_3_6_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2018.06.010"},{"key":"e_1_3_6_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40870-021-00320-9"},{"key":"e_1_3_6_37_2","doi-asserted-by":"publisher","DOI":"10.1177\/1056789513514071"},{"key":"e_1_3_6_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijsolstr.2013.12.024"},{"key":"e_1_3_6_39_2","doi-asserted-by":"publisher","DOI":"10.1046\/j.1460-2695.2000.00264.x"},{"key":"e_1_3_6_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2004.09.005"},{"key":"e_1_3_6_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2008.10.001"},{"key":"e_1_3_6_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10704-007-9104-3"},{"key":"e_1_3_6_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2012.02.015"},{"key":"e_1_3_6_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2015.05.005"},{"key":"e_1_3_6_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2010.07.017"},{"key":"e_1_3_6_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00603-021-02365-7"},{"key":"e_1_3_6_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2017.05.025"},{"key":"e_1_3_6_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0272-8842(02)00230-4"},{"key":"e_1_3_6_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2005.11.005"},{"key":"e_1_3_6_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2015.12.020"},{"key":"e_1_3_6_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2012.05.022"},{"key":"e_1_3_6_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfailanal.2013.09.012"},{"key":"e_1_3_6_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12206-011-0614-6"},{"key":"e_1_3_6_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrmms.2019.104103"},{"key":"e_1_3_6_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.carbon.2010.02.041"},{"key":"e_1_3_6_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2020.102806"},{"key":"e_1_3_6_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1508-4"},{"key":"e_1_3_6_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2009.07.017"},{"key":"e_1_3_6_59_2","doi-asserted-by":"publisher","DOI":"10.1177\/0309324715570352"},{"key":"e_1_3_6_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engfracmech.2014.12.006"},{"key":"e_1_3_6_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.msea.2011.04.066"},{"key":"e_1_3_6_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00707-015-1404-5"},{"key":"e_1_3_6_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2014.10.010"},{"key":"e_1_3_6_64_2","doi-asserted-by":"publisher","DOI":"10.1111\/ffe.12057"},{"key":"e_1_3_6_65_2","volume-title":"Gaussian processes for machine learning","author":"Rasmussen CE","year":"2006","unstructured":"Rasmussen CE, Williams C. 2006 Gaussian processes for machine learning, vol. 1. Cambridge, MA: MIT press."},{"key":"e_1_3_6_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0"},{"key":"e_1_3_6_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmachtools.2007.07.011"},{"key":"e_1_3_6_68_2","doi-asserted-by":"publisher","DOI":"10.1201\/b12207"},{"key":"e_1_3_6_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"e_1_3_6_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_6_71_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_6_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"e_1_3_6_73_2","unstructured":"Vuji\u010di\u0107 T Matijevi\u0107 T \u0160evarac Z. 2016 Comparative analysis of methods for determining number of hidden neurons in artificial neural network. In Central European Conf. on information and intelligent systems Varazdin Croatia 21\u201323 September 2016 pp. 219-223. Varazdin Croatia: Faculty of Organization and Informatics Varazdin."},{"key":"e_1_3_6_74_2","first-page":"714","article-title":"Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture","volume":"31","author":"Karsoliya S","year":"2012","unstructured":"Karsoliya S. 2012 Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. Int. J. Eng. Trends Technol. 31, 714-717.","journal-title":"Int. J. Eng. Trends Technol."},{"key":"e_1_3_6_75_2","first-page":"117","article-title":"The application of Bayesian methods for seeking the extremum","volume":"2","author":"Mockus J","year":"1978","unstructured":"Mockus J, Tiesis V, Zilinskas A. 1978 The application of Bayesian methods for seeking the extremum. Towar. Glob. Optim 2, 117.","journal-title":"Towar. Glob. Optim"},{"key":"e_1_3_6_76_2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.4.954"},{"key":"e_1_3_6_77_2","doi-asserted-by":"publisher","DOI":"10.4304\/jcp.7.1.161-168"}],"container-title":["Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsta.2022.0397","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/full-xml\/10.1098\/rsta.2022.0397","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsta.2022.0397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:06:42Z","timestamp":1700438802000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/doi\/10.1098\/rsta.2022.0397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,20]]},"references-count":76,"journal-issue":{"issue":"2264","published-print":{"date-parts":[[2024,1,8]]}},"alternative-id":["10.1098\/rsta.2022.0397"],"URL":"https:\/\/doi.org\/10.1098\/rsta.2022.0397","relation":{},"ISSN":["1364-503X","1471-2962"],"issn-type":[{"value":"1364-503X","type":"print"},{"value":"1471-2962","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,20]]},"assertion":[{"value":"2023-06-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-17","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"20220397"}}