Show simple item record

dc.contributor.advisorCarvajal Barrera, Gonzalo Andrés (Profesor Guía)
dc.contributor.advisorFuentes Castillo, Andrés Hernán (Profesor Correferente)
dc.contributor.authorRodríguez Barreda, Alonso Antonio
dc.coverage.spatialCasa Central Valparaísoes_CL
dc.date.accessioned2022-08-29T13:40:27Z
dc.date.available2022-08-29T13:40:27Z
dc.date.issued2022
dc.identifier.urihttps://hdl.handle.net/11673/53970
dc.description.abstractTraditional non-invasive optical techniques for estimating soot volume fraction and soot temperature in coflow laminar axisymmetric diffusion flames require solving ill-posed inverse problems from convoluted signals. Applying these techniques using inversion and regularization makes them highly susceptible to experimental noise and the choice of adjustable regularization parameters, which can prevent obtaining consistent and accurate estimations. This thesis proposes replacing these techniques with a machine learning model that implements the inversion step in the estimation of these soot properties. We develop a framework to generate physically-grounded simulated signals of reference soot fields and their corresponding convoluted projections in the camera plane, thus enabling a supervised learning approach to train our machine learning model. We focus on line-of-sight attenuation measurements for the characterization of the soot volume fraction field and Broadband Emission measurements for the characterization of the soot temperature field, as these techniques represent a promising approach to low-cost characterization of their respective soot property in flames. Using our framework, we generate datasets for each of the two soot properties to train a model based on U-Net, a fully convolutional neural network previously used in similar inversion problems. We then compare the performance of our models over the synthetic dataset versus traditional techniques and perform a final validation over data obtained during experimental campaigns. These results show that our machine learning models outperform traditional inversion techniques when processing noisy measurements, especially in areas of interest for soot formation, such as the flame center and its path of maximum soot concentration along the flame. The resilience to noise shown by machine learning models makes them attractive for implementing low-cost techniques to characterize soot properties in flames using experimental equipment of different quality, representing a promising research avenue.es_CL
dc.format.extent60 H.es_CL
dc.format.mimetypeapplication/pdf
dc.subjectHOLLÍNes_CL
dc.subjectFRACCIÓN DE VOLUMEN DE HOLLÍNes_CL
dc.subjectPIROMETRÍA DE HOLLÍNes_CL
dc.titleCharacterization of soot properties in coflow laminar axisymmetric diffusion flames using image processing and machine learninges_CL
dc.typeTesis de Postgrado
dc.rights.accessRightsA. Internet abierta repositorio.usm.cl y otros repositorios a que la USM se adscriba.
dc.description.degreeMAGISTER EN CIENCIAS DE LA INGENIERIA ELECTRONICAes_CL
dc.contributor.departmentUniversidad Técnica Federico Santa María. Departamento de Electrónicaes_CL
dc.description.programDEPARTAMENTO DE ELECTRÓNICA. MAGÍSTER EN CIENCIAS DE LA INGENIERÍA ELECTRÓNICA (MS)es_CL
dc.identifier.barcode188992552UTFSMes_CL
usm.identifier.rut18899255-2es_CL


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record