Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion
A physics-informed machine learning (ML) model, which incorporates the conservation of carbon mass, was developed to predict the product gas yield and composition for indirect gasification of waste in a fluidized bed. A dataset was compiled from experimental data of an in-house reactor, encompassing...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Chemical Engineering Journal Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666821124001169 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557555597967360 |
|---|---|
| author | Surika van Wyk |
| author_facet | Surika van Wyk |
| author_sort | Surika van Wyk |
| collection | DOAJ |
| description | A physics-informed machine learning (ML) model, which incorporates the conservation of carbon mass, was developed to predict the product gas yield and composition for indirect gasification of waste in a fluidized bed. A dataset was compiled from experimental data of an in-house reactor, encompassing a wide range of feedstocks characteristics (biomass to plastics) and process conditions, which served as input for the model. Four data-driven models were trained and evaluated, with the XGBoost model having the best predictive accuracy (RMSE = 1.1 & R2 = 0.99) and being adapted for the physics-informed model. The optimum physics contribution was 30 % (70 % data contribution) to maintain predictive accuracy (RMSE = 2.7 & R2 = 0.95) and improve carbon closure. Feedstock properties were shown to have a higher feature importance compared to the operating conditions. The developed physics-informed model demonstrated the potential of ML models for the modelling of gasification of various waste streams. This is a promising first step towards improving data-driven ML models for application to thermochemical systems. |
| format | Article |
| id | doaj-art-ec6d46ced3ea4520ad55adb9ce76a883 |
| institution | Kabale University |
| issn | 2666-8211 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Chemical Engineering Journal Advances |
| spelling | doaj-art-ec6d46ced3ea4520ad55adb9ce76a8832025-02-03T04:17:03ZengElsevierChemical Engineering Journal Advances2666-82112025-03-0121100699Development of a novel physics-informed machine learning model for advanced thermochemical waste conversionSurika van Wyk0Biobased and Circular Technology Group, Energy & Materials Transition Unit, The Netherlands Organization for Applied Scientific Research (TNO), Petten, the NetherlandsA physics-informed machine learning (ML) model, which incorporates the conservation of carbon mass, was developed to predict the product gas yield and composition for indirect gasification of waste in a fluidized bed. A dataset was compiled from experimental data of an in-house reactor, encompassing a wide range of feedstocks characteristics (biomass to plastics) and process conditions, which served as input for the model. Four data-driven models were trained and evaluated, with the XGBoost model having the best predictive accuracy (RMSE = 1.1 & R2 = 0.99) and being adapted for the physics-informed model. The optimum physics contribution was 30 % (70 % data contribution) to maintain predictive accuracy (RMSE = 2.7 & R2 = 0.95) and improve carbon closure. Feedstock properties were shown to have a higher feature importance compared to the operating conditions. The developed physics-informed model demonstrated the potential of ML models for the modelling of gasification of various waste streams. This is a promising first step towards improving data-driven ML models for application to thermochemical systems.http://www.sciencedirect.com/science/article/pii/S2666821124001169Physics-informedMachine learningFluidized bedBiomassPlasticsWaste |
| spellingShingle | Surika van Wyk Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion Chemical Engineering Journal Advances Physics-informed Machine learning Fluidized bed Biomass Plastics Waste |
| title | Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion |
| title_full | Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion |
| title_fullStr | Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion |
| title_full_unstemmed | Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion |
| title_short | Development of a novel physics-informed machine learning model for advanced thermochemical waste conversion |
| title_sort | development of a novel physics informed machine learning model for advanced thermochemical waste conversion |
| topic | Physics-informed Machine learning Fluidized bed Biomass Plastics Waste |
| url | http://www.sciencedirect.com/science/article/pii/S2666821124001169 |
| work_keys_str_mv | AT surikavanwyk developmentofanovelphysicsinformedmachinelearningmodelforadvancedthermochemicalwasteconversion |