Exploring the application of neural networks for the prediction of vehicle emissions

In this project, data from the EPA's fuel efficiency and emissions tests was used to train neural networks so that they could predict vehicle emissions. Vehicle characteristics were taken directly from the database, driving cycles were analyzed using their velocity and acceleration profiles in...

Full description

Autores:
Rodríguez Llorente, Diego
Tipo de recurso:
Trabajo de grado de pregrado
Fecha de publicación:
2019
Institución:
Universidad de los Andes
Repositorio:
Séneca: repositorio Uniandes
Idioma:
eng
OAI Identifier:
oai:repositorio.uniandes.edu.co:1992/45206
Acceso en línea:
http://hdl.handle.net/1992/45206
Palabra clave:
Consumo de combustible
Gases de combustión
Gases de escape en automóviles
Redes neurales (Computadores)
Ingeniería
Rights
openAccess
License
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
id UNIANDES2_2ea557aea29da48b74a3bacb33449cbb
oai_identifier_str oai:repositorio.uniandes.edu.co:1992/45206
network_acronym_str UNIANDES2
network_name_str Séneca: repositorio Uniandes
repository_id_str
dc.title.es_CO.fl_str_mv Exploring the application of neural networks for the prediction of vehicle emissions
title Exploring the application of neural networks for the prediction of vehicle emissions
spellingShingle Exploring the application of neural networks for the prediction of vehicle emissions
Consumo de combustible
Gases de combustión
Gases de escape en automóviles
Redes neurales (Computadores)
Ingeniería
title_short Exploring the application of neural networks for the prediction of vehicle emissions
title_full Exploring the application of neural networks for the prediction of vehicle emissions
title_fullStr Exploring the application of neural networks for the prediction of vehicle emissions
title_full_unstemmed Exploring the application of neural networks for the prediction of vehicle emissions
title_sort Exploring the application of neural networks for the prediction of vehicle emissions
dc.creator.fl_str_mv Rodríguez Llorente, Diego
dc.contributor.advisor.none.fl_str_mv González Mancera, Andrés Leonardo
dc.contributor.author.none.fl_str_mv Rodríguez Llorente, Diego
dc.subject.armarc.es_CO.fl_str_mv Consumo de combustible
Gases de combustión
Gases de escape en automóviles
Redes neurales (Computadores)
topic Consumo de combustible
Gases de combustión
Gases de escape en automóviles
Redes neurales (Computadores)
Ingeniería
dc.subject.themes.none.fl_str_mv Ingeniería
description In this project, data from the EPA's fuel efficiency and emissions tests was used to train neural networks so that they could predict vehicle emissions. Vehicle characteristics were taken directly from the database, driving cycles were analyzed using their velocity and acceleration profiles in order to calculate some defining characteristics, and these two groups were used as inputs to predict HC, CO, CO2, and NOx. For most of the project only HC was predicted to simplify the process with the idea that if a model was successful, then the output changed to another gas until a different model was successful with the predictions and so on. By the end of the project Multi-Task learning was applied to predict all four emissions simultaneously hoping that information could be shared between those tasks to improve the predictions. Feature engineering was applied to analyze the input variables and understand if one or more were introducing significant errors into the data and ruining the predictions. The error for the predictions was calculated using Mean Squared Percentage Error (MSPE) to compare the performance of different models. This error was consistently above 10E7% and many predictions were negative, rendering this exploration of neural networks unsuccessful. At the end of the project a phenomenon known as Emissions Deterioration was analyzed based on three different studies to understand how emissions deteriorate with the age of the vehicles. It was found that this phenomenon is much more complex than initially thought.
publishDate 2019
dc.date.issued.none.fl_str_mv 2019
dc.date.accessioned.none.fl_str_mv 2020-09-03T15:52:19Z
dc.date.available.none.fl_str_mv 2020-09-03T15:52:19Z
dc.type.spa.fl_str_mv Trabajo de grado - Pregrado
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/bachelorThesis
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_7a1f
dc.type.content.spa.fl_str_mv Text
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/TP
format http://purl.org/coar/resource_type/c_7a1f
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/1992/45206
dc.identifier.pdf.none.fl_str_mv u827141.pdf
dc.identifier.instname.spa.fl_str_mv instname:Universidad de los Andes
dc.identifier.reponame.spa.fl_str_mv reponame:Repositorio Institucional Séneca
dc.identifier.repourl.spa.fl_str_mv repourl:https://repositorio.uniandes.edu.co/
url http://hdl.handle.net/1992/45206
identifier_str_mv u827141.pdf
instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.es_CO.fl_str_mv eng
language eng
dc.rights.uri.*.fl_str_mv https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.es_CO.fl_str_mv 74 hojas
dc.format.mimetype.es_CO.fl_str_mv application/pdf
dc.publisher.es_CO.fl_str_mv Universidad de los Andes
dc.publisher.program.es_CO.fl_str_mv Ingeniería Mecánica
dc.publisher.faculty.es_CO.fl_str_mv Facultad de Ingeniería
dc.publisher.department.es_CO.fl_str_mv Departamento de Ingeniería Mecánica
dc.source.es_CO.fl_str_mv instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
instname_str Universidad de los Andes
institution Universidad de los Andes
reponame_str Repositorio Institucional Séneca
collection Repositorio Institucional Séneca
bitstream.url.fl_str_mv https://repositorio.uniandes.edu.co/bitstreams/6817a11b-1856-4bd7-9805-679d3a357a1a/download
https://repositorio.uniandes.edu.co/bitstreams/2f5511fb-9b23-4bef-9f4d-61799f8c1607/download
https://repositorio.uniandes.edu.co/bitstreams/e80504a7-a251-485a-aedd-e407c2040bd7/download
bitstream.checksum.fl_str_mv b951b66c09647bd0eb73160bf153550d
af73dad3fa41d1c41bc1af9b2d8f4017
ee99ea40a7e3dc184235fe8f2f9aaa28
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional Séneca
repository.mail.fl_str_mv adminrepositorio@uniandes.edu.co
_version_ 1812133873942790144
spelling Al consultar y hacer uso de este recurso, está aceptando las condiciones de uso establecidas por los autores.https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2González Mancera, Andrés Leonardo1a96c006-a679-415f-870a-e3c375a5259a500Rodríguez Llorente, Diegob8dc25ce-4aaf-460b-84d4-72165fe73de15002020-09-03T15:52:19Z2020-09-03T15:52:19Z2019http://hdl.handle.net/1992/45206u827141.pdfinstname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/In this project, data from the EPA's fuel efficiency and emissions tests was used to train neural networks so that they could predict vehicle emissions. Vehicle characteristics were taken directly from the database, driving cycles were analyzed using their velocity and acceleration profiles in order to calculate some defining characteristics, and these two groups were used as inputs to predict HC, CO, CO2, and NOx. For most of the project only HC was predicted to simplify the process with the idea that if a model was successful, then the output changed to another gas until a different model was successful with the predictions and so on. By the end of the project Multi-Task learning was applied to predict all four emissions simultaneously hoping that information could be shared between those tasks to improve the predictions. Feature engineering was applied to analyze the input variables and understand if one or more were introducing significant errors into the data and ruining the predictions. The error for the predictions was calculated using Mean Squared Percentage Error (MSPE) to compare the performance of different models. This error was consistently above 10E7% and many predictions were negative, rendering this exploration of neural networks unsuccessful. At the end of the project a phenomenon known as Emissions Deterioration was analyzed based on three different studies to understand how emissions deteriorate with the age of the vehicles. It was found that this phenomenon is much more complex than initially thought."En este proyecto, los datos de las pruebas de eficiencia de combustible y emisiones de la EPA se utilizaron para entrenar redes neuronales para que pudieran predecir las emisiones de los vehículos. Las características del vehículo se tomaron directamente de la base de datos, los ciclos de conducción se analizaron utilizando sus perfiles de velocidad y aceleración para calcular algunas características definitorias, y estos dos grupos se usaron como entradas para predecir HC, CO, CO2 y NOx. Para la mayor parte del proyecto, solo se predijo que el HC simplificaría el proceso con la idea de que si un modelo era exitoso, la salida cambiaba a otro gas hasta que un modelo diferente tuviera éxito con las predicciones y así sucesivamente. Al final del proyecto, se aplicó el aprendizaje de tareas múltiples para predecir las cuatro emisiones simultáneamente, con la esperanza de que la información pudiera compartirse entre esas tareas para mejorar las predicciones. La ingeniería de características se aplicó para analizar las variables de entrada y comprender si uno o más estaban introduciendo errores significativos en los datos y arruinando las predicciones. El error para las predicciones se calculó utilizando el error de porcentaje cuadrático medio (MSPE) para comparar el rendimiento de diferentes modelos. Este error fue sistemáticamente superior al 10E7% y muchas predicciones fueron negativas, lo que hace que esta exploración de redes neuronales no tenga éxito. Al final del proyecto, se analizó un fenómeno conocido como Deterioro de Emisiones basado en tres estudios diferentes para comprender cómo se deterioran las emisiones con la edad de los vehículos. Se encontró que este fenómeno es mucho más complejo de lo que se pensaba inicialmente."--Tomado del Formato de Documento de Grado.Ingeniero MecánicoPregrado74 hojasapplication/pdfengUniversidad de los AndesIngeniería MecánicaFacultad de IngenieríaDepartamento de Ingeniería Mecánicainstname:Universidad de los Andesreponame:Repositorio Institucional SénecaExploring the application of neural networks for the prediction of vehicle emissionsTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesishttp://purl.org/coar/resource_type/c_7a1fhttp://purl.org/coar/version/c_970fb48d4fbd8a85Texthttp://purl.org/redcol/resource_type/TPConsumo de combustibleGases de combustiónGases de escape en automóvilesRedes neurales (Computadores)IngenieríaPublicationTEXTu827141.pdf.txtu827141.pdf.txtExtracted texttext/plain195060https://repositorio.uniandes.edu.co/bitstreams/6817a11b-1856-4bd7-9805-679d3a357a1a/downloadb951b66c09647bd0eb73160bf153550dMD54THUMBNAILu827141.pdf.jpgu827141.pdf.jpgIM Thumbnailimage/jpeg7078https://repositorio.uniandes.edu.co/bitstreams/2f5511fb-9b23-4bef-9f4d-61799f8c1607/downloadaf73dad3fa41d1c41bc1af9b2d8f4017MD55ORIGINALu827141.pdfapplication/pdf4017694https://repositorio.uniandes.edu.co/bitstreams/e80504a7-a251-485a-aedd-e407c2040bd7/downloadee99ea40a7e3dc184235fe8f2f9aaa28MD511992/45206oai:repositorio.uniandes.edu.co:1992/452062023-10-10 16:21:09.654https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.co