Learning hydrocracking reaction dynamics via neural ODEs: A data‐driven, gradient‐interpretable lumped modelling framework.
Saved in:
| Title: | Learning hydrocracking reaction dynamics via neural ODEs: A data‐driven, gradient‐interpretable lumped modelling framework. |
|---|---|
| Authors: | Ta, Souvik1 (AUTHOR), Samavedham, Lakshminarayanan2 (AUTHOR), Ray, Ajay K.1 (AUTHOR) araycbe@gmail.com |
| Source: | Canadian Journal of Chemical Engineering. Mar2026, Vol. 104 Issue 3, p1372-1386. 15p. |
| Subjects: | Hydrocracking, Differential equations, Machine learning, Chemical kinetics, Sensitivity analysis, Artificial neural networks |
| Abstract: | This study applies neural ordinary differential equations (neural ODEs) to model hydrocracking kinetics, a key process for converting heavy hydrocarbons into lighter products like gasoline and diesel. Neural ODEs provide a data‐driven approach, learning reaction dynamics directly from data without requiring explicit assumptions on kinetics, addressing limitations in traditional methods. Two neural ODE models were trained on synthetic hydrocracking data representing different kinetic assumptions: one based on a 2.5‐order reaction scheme (Model A) and the other on a first‐order scheme (Model B), across varying temperatures and feedstocks. The models demonstrated high predictive accuracy when predicting within the range of training data, with RMSE values remaining below 0.5 wt.% under most conditions. However, performance declined during high‐temperature extrapolation scenarios, particularly for the higher‐order model, revealing challenges in capturing nonlinear dynamics at extreme conditions. This work also enhanced the interpretability of neural ODEs by analyzing gradients within the model, which validated alignment with known kinetic principles, uncovering critical information about reaction pathways and temperature sensitivities. This analysis demonstrated the models' ability to capture temperature‐dependent behaviour and rate stabilization, as illustrated through heat maps, which further emphasized the potential of neural ODEs for both predictive accuracy and interpretative insights in hydrocracking modelling. Additionally, the extracted gradients present an exciting avenue for future advancements, such as leveraging symbolic regression techniques to uncover governing equations. [ABSTRACT FROM AUTHOR] |
| Copyright of Canadian Journal of Chemical Engineering is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191457642 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Learning hydrocracking reaction dynamics via neural ODEs: A data‐driven, gradient‐interpretable lumped modelling framework. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ta%2C+Souvik%22">Ta, Souvik</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Samavedham%2C+Lakshminarayanan%22">Samavedham, Lakshminarayanan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ray%2C+Ajay+K%2E%22">Ray, Ajay K.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> araycbe@gmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Canadian+Journal+of+Chemical+Engineering%22">Canadian Journal of Chemical Engineering</searchLink>. Mar2026, Vol. 104 Issue 3, p1372-1386. 15p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Hydrocracking%22">Hydrocracking</searchLink><br /><searchLink fieldCode="DE" term="%22Differential+equations%22">Differential equations</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Chemical+kinetics%22">Chemical kinetics</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+analysis%22">Sensitivity analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This study applies neural ordinary differential equations (neural ODEs) to model hydrocracking kinetics, a key process for converting heavy hydrocarbons into lighter products like gasoline and diesel. Neural ODEs provide a data‐driven approach, learning reaction dynamics directly from data without requiring explicit assumptions on kinetics, addressing limitations in traditional methods. Two neural ODE models were trained on synthetic hydrocracking data representing different kinetic assumptions: one based on a 2.5‐order reaction scheme (Model A) and the other on a first‐order scheme (Model B), across varying temperatures and feedstocks. The models demonstrated high predictive accuracy when predicting within the range of training data, with RMSE values remaining below 0.5 wt.% under most conditions. However, performance declined during high‐temperature extrapolation scenarios, particularly for the higher‐order model, revealing challenges in capturing nonlinear dynamics at extreme conditions. This work also enhanced the interpretability of neural ODEs by analyzing gradients within the model, which validated alignment with known kinetic principles, uncovering critical information about reaction pathways and temperature sensitivities. This analysis demonstrated the models' ability to capture temperature‐dependent behaviour and rate stabilization, as illustrated through heat maps, which further emphasized the potential of neural ODEs for both predictive accuracy and interpretative insights in hydrocracking modelling. Additionally, the extracted gradients present an exciting avenue for future advancements, such as leveraging symbolic regression techniques to uncover governing equations. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Canadian Journal of Chemical Engineering is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191457642 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1002/cjce.70080 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 1372 Subjects: – SubjectFull: Hydrocracking Type: general – SubjectFull: Differential equations Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Chemical kinetics Type: general – SubjectFull: Sensitivity analysis Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: Learning hydrocracking reaction dynamics via neural ODEs: A data‐driven, gradient‐interpretable lumped modelling framework. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ta, Souvik – PersonEntity: Name: NameFull: Samavedham, Lakshminarayanan – PersonEntity: Name: NameFull: Ray, Ajay K. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00084034 Numbering: – Type: volume Value: 104 – Type: issue Value: 3 Titles: – TitleFull: Canadian Journal of Chemical Engineering Type: main |
| ResultId | 1 |
