Using Graph Neural Networks to Learn Fire and Smoke Behaviour in a Physics- Based Simulator

dc.contributor.authorLam, Edvin
dc.contributor.departmentChalmers tekniska högskola / Institutionen för fysiksv
dc.contributor.examinerEkström, Andreas
dc.contributor.supervisorMogren, Olof
dc.date.accessioned2021-06-14T13:46:09Z
dc.date.available2021-06-14T13:46:09Z
dc.date.issued2021sv
dc.date.submitted2020
dc.description.abstractDeep learning is prominent in computer vision as a means of learning spatial features and processing them in useful ways, such as for image classification and image segmentation. An application of this in physics is to use videos of fire to predict how the flames and smoke evolve over time. This thesis explores a simplified version of this in an attempt to lay the groundwork for future studies. In particular, simulations of fire and smoke were made using the open source software Fire Dynamics Simulator by NIST. From these simulations, frame by frame states of the physical system could be extracted. A graph neural network using the MeshGraphNets framework was trained to predict future states of the fire given two past states as input. Some of the resulting neural networks were able to reasonably predict over 50 frames into the future and also showed some competence when faced with test sets with a different physical geometry. The performances of the trained models varied greatly depending on the loss functions used in training, suggesting that more hyperparameter optimisation could be done in this regard.sv
dc.identifier.coursecodeTIFX05sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/302506
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectgraph neural networksv
dc.subjectfire dynamics simulatorsv
dc.subjectdeep learningsv
dc.subjectphysics simulationsv
dc.titleUsing Graph Neural Networks to Learn Fire and Smoke Behaviour in a Physics- Based Simulatorsv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
Master_Thesis_Edvin.pdf
Storlek:
3.29 MB
Format:
Adobe Portable Document Format
Beskrivning:
License bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: