Physics-informed machine learning for grade prediction in froth flotation

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorNasiri Abarbekouh, Mahdi
dc.contributor.authorIqbal, Sahel
dc.contributor.authorSärkkä, Simo
dc.contributor.departmentDepartment of Electrical Engineering and Automationen
dc.contributor.groupauthorSensor Informatics and Medical Technologyen
dc.contributor.groupauthorHelsinki Institute for Information Technology (HIIT)en
dc.contributor.organizationSensor Informatics and Medical Technology
dc.date.accessioned2025-04-30T07:33:07Z
dc.date.available2025-04-30T07:33:07Z
dc.date.issued2025-07-15
dc.descriptionPublisher Copyright: © 2025 The Authors
dc.description.abstractIn this paper, physics-informed neural network models are developed to predict the concentrate gold grade in froth flotation cells. Accurate prediction of concentrate grades is important for the automatic control and optimization of mineral processing. Both first-principles and data-driven machine learning methods have been used to model the flotation process. The complexity of models based on first-principles restricts their direct use, while purely data-driven models often fail in dynamic industrial environments, leading to poor generalization. To address these limitations, this study integrates classical mathematical models of froth flotation processes with conventional deep learning methods to construct physics-informed neural networks. The models are trained, evaluated, and tested on datasets generated from a digital twin model of flotation cells that merges real-process data with physics-based simulations, with data collected over nearly half a year at a five-minute sampling rate. Compared to the best purely data-driven model, the top-performing physics-informed neural network reduced the mean squared error by 65% and the mean relative error by 34%, demonstrating superior generalization and predictive performance.en
dc.description.versionPeer revieweden
dc.format.extent12
dc.format.mimetypeapplication/pdf
dc.identifier.citationNasiri Abarbekouh, M, Iqbal, S & Särkkä, S 2025, 'Physics-informed machine learning for grade prediction in froth flotation', Minerals Engineering, vol. 227, 109297. https://doi.org/10.1016/j.mineng.2025.109297en
dc.identifier.doi10.1016/j.mineng.2025.109297
dc.identifier.issn0892-6875
dc.identifier.issn1872-9444
dc.identifier.otherPURE UUID: a8e922b9-2b5f-4892-abfd-64a165b5158c
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/a8e922b9-2b5f-4892-abfd-64a165b5158c
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=105002400833&partnerID=8YFLogxK
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/179870140/Physics-informed_machine_learning_for_grade_prediction_in_froth_flotation.pdf
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/135144
dc.identifier.urnURN:NBN:fi:aalto-202504303454
dc.language.isoenen
dc.publisherElsevier
dc.relation.ispartofseriesMinerals Engineeringen
dc.relation.ispartofseriesVolume 227en
dc.rightsopenAccessen
dc.rightsCC BY
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subject.keywordFroth flotation
dc.subject.keywordMachine learning
dc.subject.keywordPhysics-informed neural networks
dc.subject.keywordPredictive modeling
dc.titlePhysics-informed machine learning for grade prediction in froth flotationen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Physics-informed_machine_learning_for_grade_prediction_in_froth_flotation.pdf
Size:
3.52 MB
Format:
Adobe Portable Document Format