{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T03:50:23Z","timestamp":1768449023500,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T00:00:00Z","timestamp":1692316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T00:00:00Z","timestamp":1692316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["CASE Award Studentship"],"award-info":[{"award-number":["CASE Award Studentship"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["CASE Award Studentship"],"award-info":[{"award-number":["CASE Award Studentship"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Engineering with Computers"],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The design of magnets for magnetic resonance imaging (MRI) scanners requires the numerical simulation of a coupled magneto-mechanical system where the effects that different material parameters and in-service loading conditions have on both imaging and MRI performance are key to aid with the design and the manufacturing process. To correctly capture the complex physics, and to obtain accurate solutions, finite element simulations with dense meshes and high order elements are needed. Reduced order model approaches, based on the established proper orthogonal decomposition (POD) approach, are attractive as they can rapidly predict the numerical simulations needed under changing parameters or conditions. However, the projected (PODP) approach has an invasive computational implementation, whilst the interpolated (PODI) approach presents challenges when the dimension of the space of parameters to be investigated becomes large. As an alternative, we investigate a POD technique based on using a neural network regression, which is not as invasive as PODP, but has superior approximation properties compared to PODI. We apply this to the coupled magneto-mechanical system to understand three pressing industrial problems: firstly, the accurate and rapid computation of the resonant frequencies associated with this coupled magneto-mechanical system, secondly, the effects of magnet motion on the Ohmic power and kinetic energy curves, and, thirdly, the prediction of the uncertainty in Ohmic power and kinetic energy curves as a function of exciting frequency for uncertain material parameters.<\/jats:p>","DOI":"10.1007\/s00366-023-01870-3","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T15:58:48Z","timestamp":1692374328000},"page":"4103-4127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Reduced order modelling using neural networks for predictive modelling of 3d-magneto-mechanical problems with application to magnetic resonance imaging scanners"],"prefix":"10.1007","volume":"39","author":[{"given":"S.","family":"Miah","sequence":"first","affiliation":[]},{"given":"Y.","family":"Sooriyakanthan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-7023","authenticated-orcid":false,"given":"P. D.","family":"Ledger","sequence":"additional","affiliation":[]},{"given":"A. J.","family":"Gil","sequence":"additional","affiliation":[]},{"given":"M.","family":"Mallett","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,18]]},"reference":[{"issue":"3","key":"1870_CR1","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/0730-725X(94)00124-L","volume":"13","author":"L Clarke","year":"1995","unstructured":"Clarke L, Velthuizen R, Camacho M, Heine J, Vaidyanathan M, Hall L, Thatcher R, Silbiger M (1995) MRI segmentation: methods and applications. Magn Reson Imaging 13(3):343\u2013368","journal-title":"Magn Reson Imaging"},{"issue":"3","key":"1870_CR2","first-page":"162","volume":"3","author":"SJ Matzat","year":"2013","unstructured":"Matzat SJ, van Tiel J, Gold GE, Oei EH (2013) Quantitative MRI techniques of cartilage composition. Quant Imaging Med Surg 3(3):162","journal-title":"Quant Imaging Med Surg"},{"issue":"5","key":"1870_CR3","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1007\/s003300101114","volume":"12","author":"A Savnik","year":"2002","unstructured":"Savnik A, Malmskov H, Thomsen HS, Graff LB, Nielsen H, Danneskiold-Sams\u00f8e B, Boesen J, Bliddal H (2002) MRI of the wrist and finger joints in inflammatory joint diseases at 1-year interval: MRI features to predict bone erosions. Eur Radiol 12(5):1203\u20131210","journal-title":"Eur Radiol"},{"issue":"1","key":"1870_CR4","first-page":"108","volume":"24","author":"P Kozlowski","year":"2006","unstructured":"Kozlowski P, Chang SD, Jones EC, Berean KW, Chen H, Goldenberg SL (2006) Combined diffusion-weighted and dynamic contrast-enhanced MRI for prostate cancer diagnosis: correlation with biopsy and histopathology. J Magn Reson Imaging Off J Int Soc Magn Reson Med 24(1):108\u2013113","journal-title":"J Magn Reson Imaging Off J Int Soc Magn Reson Med"},{"key":"1870_CR5","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1016\/j.apm.2015.09.030","volume":"40","author":"PD Ledger","year":"2016","unstructured":"Ledger PD, Gil AJ, Poya R, Kruip M, Wilkinson I, Bagwell S (2016) Solution of an industrially relevant coupled magneto-mechanical problem set on an axisymmetric domain. Appl Math Model 40:1959\u20131971","journal-title":"Appl Math Model"},{"key":"1870_CR6","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1002\/nme.5559","volume":"112","author":"S Bagwell","year":"2017","unstructured":"Bagwell S, Ledger PD, Gil AJ, Mallett M, Kruip M (2017) A linearised $$hp$$-finite element framework for acousto-magneto-mechanical coupling in axisymmetric MRI scanners. Int J Numer Methods Eng 112:1323\u20131352","journal-title":"Int J Numer Methods Eng"},{"key":"1870_CR7","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1002\/nme.5802","volume":"115","author":"S Bagwell","year":"2018","unstructured":"Bagwell S, Ledger PD, Gil AJ, Mallett M (2018) Transient solutions to nonlinear acousto-magneto-mechanical coupling for axisymmetric MRI scanner design. Int J Numer Methods Eng 115:209\u2013237","journal-title":"Int J Numer Methods Eng"},{"key":"1870_CR8","unstructured":"Szab\u00f3 B, Babu\u0161ka I (1991) Finite Element Analysis. Wiley, New York"},{"key":"1870_CR9","doi-asserted-by":"crossref","unstructured":"Karniadakis GE, Karniadakis G, Sherwin S (2005) Spectral\/hp Element Methods for Computational Fluid Dynamics. Oxford University Press on Demand, Oxford","DOI":"10.1093\/acprof:oso\/9780198528692.001.0001"},{"key":"1870_CR10","unstructured":"Demkowicz L (2006) Computing with hp-Adaptive Finite Elements: Volume 1 One and Two Dimensional Elliptic and Maxwell Problems. Chapman and Hall\/CRC, Boca Raton"},{"key":"1870_CR11","doi-asserted-by":"crossref","unstructured":"Demkowicz L, Kurtz J, Pardo D, Paszynski M, Rachowicz W, Zdunek A (2007) Computing with hp-Adaptive Finite Elements, vol. 2: Frontiers Three Dimensional elliptic and Maxwell problems with applications, 1st edn. Chapman & Hall\/CRC, Boca Raton","DOI":"10.1201\/9781420011692"},{"key":"1870_CR12","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1002\/nme.6088","volume":"119","author":"M Seoane","year":"2019","unstructured":"Seoane M, Ledger PD, Gil AJ, Mallett M (2019) An accurate and efficient three-dimensional high-order finite element methodology for the simulation of magneto-mechanical coupling in MRI scanners. Int J Numer Methods Eng 119:1185\u20131215","journal-title":"Int J Numer Methods Eng"},{"issue":"3","key":"1870_CR13","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1006\/jsvi.2001.4041","volume":"252","author":"Y Liang","year":"2002","unstructured":"Liang Y, Lee H, Lim S, Lin W, Lee K, Wu C (2002) Proper orthogonal decomposition and its applications-part i: theory. J Sound Vib 252(3):527\u2013544","journal-title":"J Sound Vib"},{"key":"1870_CR14","first-page":"808","volume":"78","author":"A Chatterjee","year":"2000","unstructured":"Chatterjee A (2000) An introduction to the proper orthogonal decomposition. Curr Sci 78:808\u2013817","journal-title":"Curr Sci"},{"key":"1870_CR15","doi-asserted-by":"crossref","unstructured":"Hesthaven JS, Rozza G, Stamm B et al (2016) Certified Reduced Basis Methods for Parametrized Partial Differential Equations, vol 590. Springer, Berlin","DOI":"10.1007\/978-3-319-22470-1"},{"issue":"7","key":"1870_CR16","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.2514\/1.35374","volume":"46","author":"D Amsallem","year":"2008","unstructured":"Amsallem D, Farhat C (2008) Interpolation method for adapting reduced-order models and application to aeroelasticity. AIAA J 46(7):1803\u20131813","journal-title":"AIAA J"},{"key":"1870_CR17","doi-asserted-by":"publisher","first-page":"3529","DOI":"10.1002\/nme.6369","volume":"121","author":"M Seoane","year":"2020","unstructured":"Seoane M, Ledger PD, Gil AJ, Zlotnik S, Mallett M (2020) A combined reduced order-full order methodology for the solution of 3D magneto-mechanical problems with application to magnetic resonance imaging scanners. Int J Numer Methods Eng 121:3529\u20133559","journal-title":"Int J Numer Methods Eng"},{"key":"1870_CR18","unstructured":"Seoane M (2020) 3D simulation of magneto-mechanical coupling in MRI scanners using high order FEM and POD. Ph.D. thesis, Swansea University, UK"},{"key":"1870_CR19","unstructured":"Bishop C (2006) Pattern Recognition and Machine Learning. Springer, Berlin"},{"key":"1870_CR20","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1137\/18M1165748","volume":"61","author":"CF Higham","year":"2019","unstructured":"Higham CF, Higham DJ (2019) Deep learning: an introduction for applied mathematicians. SIAM Rev 61:860\u2013891","journal-title":"SIAM Rev"},{"key":"1870_CR21","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jcp.2018.02.037","volume":"363","author":"JS Hesthaven","year":"2018","unstructured":"Hesthaven JS, Ubbiali S (2018) Non-intrusive reduced order modeling of nonlinear problems using neural networks. J Comput Phys 363:55\u201378","journal-title":"J Comput Phys"},{"key":"1870_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jweia.2017.07.021","volume":"170","author":"H Dongmei","year":"2017","unstructured":"Dongmei H, Shiqing H, Xuhui H, Xue Z (2017) Prediction of wind loads on high-rise building using a BP neural network combined with POD. J Wind Eng Ind Aerodyn 170:1\u201317","journal-title":"J Wind Eng Ind Aerodyn"},{"key":"1870_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109402","volume":"410","author":"Q Wang","year":"2020","unstructured":"Wang Q, Ripamonti N, Hesthaven JS (2020) Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori\u2013Zwanzig formalism. J Comput Phys 410:109402","journal-title":"J Comput Phys"},{"issue":"10 October","key":"1870_CR24","first-page":"1","volume":"15","author":"S Fresca","year":"2020","unstructured":"Fresca S, Manzoni A, Ded\u00e8 L, Quarteroni A (2020) Deep learning-based reduced order models in cardiac electrophysiology. PLoS One 15(10 October):1\u201332","journal-title":"PLoS One"},{"issue":"2","key":"1870_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10915-021-01462-7","volume":"87","author":"S Fresca","year":"2021","unstructured":"Fresca S, Dede\u2019 L, Manzoni A (2021) A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs. J Sci Comput 87(2):1\u201336","journal-title":"J Sci Comput"},{"key":"1870_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.114181","volume":"388","author":"S Fresca","year":"2022","unstructured":"Fresca S, Manzoni A (2022) POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition. Comput Methods Appl Mech Eng 388:114181","journal-title":"Comput Methods Appl Mech Eng"},{"key":"1870_CR27","unstructured":"Bagwell S (2018) A Numerical Multi-Physics Approach to Understanding MRI Scanners and their Complex Behaviour. Ph.D. thesis, Swansea University, UK"},{"key":"1870_CR28","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1108\/03321640510586015","volume":"24","author":"J Sch\u00f6berl","year":"2005","unstructured":"Sch\u00f6berl J, Zaglmayr S (2005) High order N\u00e9d\u00e9lec elements with local complete sequence properties. Int J Comput Math Electr Electron Eng (COMPEL) 24:374\u2013384","journal-title":"Int J Comput Math Electr Electron Eng (COMPEL)"},{"key":"1870_CR29","unstructured":"Zaglmayr S (2006) High Order Finite Element Methods for Electromagnetic Field Computation. Ph.D. thesis, Instit\u00fct f\u00fcr Numerische Mathematik, Johannes Kepler Univerit\u00e4t Linz, Austria"},{"key":"1870_CR30","unstructured":"Buljak V (2011) Inverse Analyses with Model Reduction: Proper Orthogonal Decomposition in Structural Mechanics. Springer Science & Business Media, Berlin"},{"issue":"17\u201318","key":"1870_CR31","doi-asserted-by":"publisher","first-page":"4827","DOI":"10.1016\/j.ijheatmasstransfer.2012.04.053","volume":"55","author":"Y Wang","year":"2012","unstructured":"Wang Y, Yu B, Cao Z, Zou W, Yu G (2012) A comparative study of POD interpolation and POD projection methods for fast and accurate prediction of heat transfer problems. Int J Heat Mass Transf 55(17\u201318):4827\u20134836","journal-title":"Int J Heat Mass Transf"},{"key":"1870_CR32","doi-asserted-by":"crossref","unstructured":"Rama R, Skatulla S, Sansour C (2015) Real-time modelling of the heart using the proper orthogonal decomposition with interpolation. In: VI international conference on computational bioengineering, ICCB, Barcelona, pp 1\u201312","DOI":"10.1201\/9781315641645-103"},{"key":"1870_CR33","doi-asserted-by":"crossref","unstructured":"Stabile G, Hijazi S, Mola A, Lorenzi S, Rozza G (2017) POD-galerkin reduced order methods for CFD using finite volume discretisation: vortex shedding around a circular cylinder. Commun Appl Ind Math 8(1):210\u2013236","DOI":"10.1515\/caim-2017-0011"},{"issue":"1","key":"1870_CR34","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/S1474-6670(17)67769-3","volume":"8","author":"J Mockus","year":"1975","unstructured":"Mockus J (1975) On the Bayes methods for seeking the extremal point. IFAC Proc Vol 8(1):428\u2013431","journal-title":"IFAC Proc Vol"},{"key":"1870_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113271","volume":"370","author":"G Barroso","year":"2020","unstructured":"Barroso G, Seoane M, Gil AJ, Ledger PD, Mallett M, Huerta A (2020) A staggered high-dimensional proper generalised decomposition for coupled magneto-mechanical problems with application to MRI scanners. Comput Methods Appl Mech Eng 370:113271","journal-title":"Comput Methods Appl Mech Eng"},{"key":"1870_CR36","unstructured":"Mathwork\u2019s deep learning toolbox. https:\/\/uk.mathworks.com\/products\/deep-learning.html. Accessed 10 Apr 2022"},{"key":"1870_CR37","unstructured":"Tensorflow. https:\/\/www.tensorflow.org\/. Accessed 10 Apr 2022"},{"key":"1870_CR38","unstructured":"scikit-learn. https:\/\/scikit-learn.org\/stable\/. Accessed 10 Apr 2022"},{"key":"1870_CR39","unstructured":"pytorch. https:\/\/pytorch.org. Accessed 10 Apr 2022"},{"key":"1870_CR40","unstructured":"Matlab. https:\/\/uk.mathworks.com\/products\/matlab.html. Accessed 10 Apr 2022"},{"key":"1870_CR41","unstructured":"Mathwork\u2019s statistics and machine learning toolbox. https:\/\/uk.mathworks.com\/products\/statistics.html. Accessed 15 June 2023"}],"container-title":["Engineering with Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-023-01870-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00366-023-01870-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-023-01870-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T03:09:05Z","timestamp":1703041745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00366-023-01870-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,18]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1870"],"URL":"https:\/\/doi.org\/10.1007\/s00366-023-01870-3","relation":{},"ISSN":["0177-0667","1435-5663"],"issn-type":[{"value":"0177-0667","type":"print"},{"value":"1435-5663","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,18]]},"assertion":[{"value":"27 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors are grateful for the financial support received from EPSRC CASE Award Studentships in partnership with Siemens Healthineers, which are supporting S. Miah and Y. Sooriyakanthan. The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}