Development of a Mathematical model for polymer selection for drilling fluids using Python
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/164140 |
Resumo: | This dissertation addresses the growing interest in utilizing polymeric systems for foundation element excavation in the construction industry. It develops and applies a comprehensive model to drilling muds, providing a practical tool for predicting and understanding fluid rheology, potentially improving construction timelines. Several experiments were carried out considering the effect of shear stress on the polymer chain of anionic polyacrylamides by analyzing the viscosities before and after the application of shear stress and considering the effect of adding clay to polymer solutions by evaluating Marsh and Brookfield viscosities (initial and final) as well as density, electrical conductivity, pH, and temperature in for subsequent organization into a database and introduction into Python. A neural network was built in Python, using the Pandas, NumPy, Keras, and sklearn libraries. The purposed model used a deep neural network with multiple layers, where each layer is designed to capture important information about the polymers, including characteristics such as molecular weight, anionicity, and other properties. Furthermore, it was implemented an expert network approach to deal with scenarios, where some variables are unknown, allowing the model to provide robust predictions even when incomplete data is provided. At last, two different models were achieved for the two tests carried out experimentally. The drilling fluid behavior is possible to predict considering polymer concentration, initial Brookfield viscosity, temperature, and polymers with different anionicity degrees and molecular weight. When shear stress is applied to the solution as a function of time, the predictive model reached a R2 equal to 0.97, a root mean squared error of 11 s/quart, and a percentage error of 8% and 12% for the initial and final Marsh viscosity, respectively. As for adding clay to the solution, a predictive model with R2 of 0.988, a root mean square error equal to 103 cP and a percentage error equal to 16% for the Brookfield viscosity after clay addition, were achieved. The assessment of predictive model performance with new data has revealed varying percentage errors for distinct polymers. For one polymer, the errors in predicting initial and final Marsh viscosities were 0.4% and 16.3%, respectively, while the other exhibited errors of 14.9% and 22.7%. Additionally, for Brookfield viscosity after clay addition, one polymer displayed a 10% error, while the other exhibited a 5.5% error. |
id |
RCAP_5f1b4a6258c7604313ac7cc0f382b36c |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/164140 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Development of a Mathematical model for polymer selection for drilling fluids using PythonDrilling fluidsPolyacrylamideMarsh viscosityBrookfield viscosityPredictive modelPython, Neural NetworksDomínio/Área Científica::Engenharia e Tecnologia::Engenharia QuímicaThis dissertation addresses the growing interest in utilizing polymeric systems for foundation element excavation in the construction industry. It develops and applies a comprehensive model to drilling muds, providing a practical tool for predicting and understanding fluid rheology, potentially improving construction timelines. Several experiments were carried out considering the effect of shear stress on the polymer chain of anionic polyacrylamides by analyzing the viscosities before and after the application of shear stress and considering the effect of adding clay to polymer solutions by evaluating Marsh and Brookfield viscosities (initial and final) as well as density, electrical conductivity, pH, and temperature in for subsequent organization into a database and introduction into Python. A neural network was built in Python, using the Pandas, NumPy, Keras, and sklearn libraries. The purposed model used a deep neural network with multiple layers, where each layer is designed to capture important information about the polymers, including characteristics such as molecular weight, anionicity, and other properties. Furthermore, it was implemented an expert network approach to deal with scenarios, where some variables are unknown, allowing the model to provide robust predictions even when incomplete data is provided. At last, two different models were achieved for the two tests carried out experimentally. The drilling fluid behavior is possible to predict considering polymer concentration, initial Brookfield viscosity, temperature, and polymers with different anionicity degrees and molecular weight. When shear stress is applied to the solution as a function of time, the predictive model reached a R2 equal to 0.97, a root mean squared error of 11 s/quart, and a percentage error of 8% and 12% for the initial and final Marsh viscosity, respectively. As for adding clay to the solution, a predictive model with R2 of 0.988, a root mean square error equal to 103 cP and a percentage error equal to 16% for the Brookfield viscosity after clay addition, were achieved. The assessment of predictive model performance with new data has revealed varying percentage errors for distinct polymers. For one polymer, the errors in predicting initial and final Marsh viscosities were 0.4% and 16.3%, respectively, while the other exhibited errors of 14.9% and 22.7%. Additionally, for Brookfield viscosity after clay addition, one polymer displayed a 10% error, while the other exhibited a 5.5% error.Esta dissertação aborda o interesse crescente na utilização de sistemas poliméricos para a escavação de elementos de fundação na indústria da construção. Desenvolve e aplica um modelo abrangente aos fluidos de perfuração, fornecendo uma ferramenta prática para prever e compreender a reologia dos fluidos, melhorando potencialmente os prazos de construção. Foram realizadas várias experiências, considerando o efeito da tensão de cisalhamento na cadeia polimérica das poliacrilamidas aniónicas, analisando as viscosidades antes e depois da aplicação da tensão de cisalhamento e considerando o efeito da adição de argila às soluções poliméricas, avaliando as viscosidades de Marsh e Brookfield (inicial e final), bem como a densidade, a condutividade eléctrica, o pH e a temperatura, para posterior organização numa base de dados e introdução em Python. Desta forma, foi construída uma rede neural em Python, utilizando as bibliotecas Pandas, NumPy, Keras e sklearn. O modelo proposto utilizou uma rede neural com várias camadas, em que cada camada foi concebida para captar informações importantes sobre os polímeros, incluindo características como o peso molecular, a anionicidade e outras propriedades. Além disso, foi implementada uma abordagem de rede especializada para lidar com cenários em que algumas variáveis são desconhecidas, permitindo que o modelo forneça previsões robustas mesmo quando são fornecidos dados incompletos. Por fim, foram obtidos dois modelos diferentes para os dois testes efetuados experimentalmente. O comportamento do fluido de perfuração é possível de se prever considerando a concentração do polímero, a viscosidade Brookfield inicial, a temperatura e polímeros com diferentes graus de anionicidade e peso molecular. Quando a tensão de cisalhamento é aplicada à solução em função do tempo, o modelo preditivo alcançou um R2 igual a 0,97, um erro quadrático médio de 11 s/quartel e um erro percentual de 8% e 12% para a viscosidade de Marsh inicial e final, respetivamente. Quanto à adição de argila à solução, obteve-se um modelo preditivo com R2 de 0,988, um erro quadrático médio igual a 103 cP e um erro percentual igual a 16% para a viscosidade Brookfield após a adição de argila. A avaliação do desempenho do modelo preditivo com novos dados revelou erros percentuais variáveis para polímeros distintos. Para um polímero, os erros na previsão das viscosidades inicial e final de Marsh foram de 0,4% e 16,3%, respetivamente, enquanto o outro apresentou erros de 14,9% e 22,7%. Além disso, para a viscosidade de Brookfield após a adição de argila, um polímero apresentou um erro de 10%, enquanto o outro apresentou um erro de 5,5%.Parada, LeandroEusébio, MárioRUNMagalhães, Leonor Moutinho2023-11-272026-10-01T00:00:00Z2023-11-27T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/164140enginfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:50:50Zoai:run.unl.pt:10362/164140Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T04:00:03.317699Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
title |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
spellingShingle |
Development of a Mathematical model for polymer selection for drilling fluids using Python Magalhães, Leonor Moutinho Drilling fluids Polyacrylamide Marsh viscosity Brookfield viscosity Predictive model Python, Neural Networks Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Química |
title_short |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
title_full |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
title_fullStr |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
title_full_unstemmed |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
title_sort |
Development of a Mathematical model for polymer selection for drilling fluids using Python |
author |
Magalhães, Leonor Moutinho |
author_facet |
Magalhães, Leonor Moutinho |
author_role |
author |
dc.contributor.none.fl_str_mv |
Parada, Leandro Eusébio, Mário RUN |
dc.contributor.author.fl_str_mv |
Magalhães, Leonor Moutinho |
dc.subject.por.fl_str_mv |
Drilling fluids Polyacrylamide Marsh viscosity Brookfield viscosity Predictive model Python, Neural Networks Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Química |
topic |
Drilling fluids Polyacrylamide Marsh viscosity Brookfield viscosity Predictive model Python, Neural Networks Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Química |
description |
This dissertation addresses the growing interest in utilizing polymeric systems for foundation element excavation in the construction industry. It develops and applies a comprehensive model to drilling muds, providing a practical tool for predicting and understanding fluid rheology, potentially improving construction timelines. Several experiments were carried out considering the effect of shear stress on the polymer chain of anionic polyacrylamides by analyzing the viscosities before and after the application of shear stress and considering the effect of adding clay to polymer solutions by evaluating Marsh and Brookfield viscosities (initial and final) as well as density, electrical conductivity, pH, and temperature in for subsequent organization into a database and introduction into Python. A neural network was built in Python, using the Pandas, NumPy, Keras, and sklearn libraries. The purposed model used a deep neural network with multiple layers, where each layer is designed to capture important information about the polymers, including characteristics such as molecular weight, anionicity, and other properties. Furthermore, it was implemented an expert network approach to deal with scenarios, where some variables are unknown, allowing the model to provide robust predictions even when incomplete data is provided. At last, two different models were achieved for the two tests carried out experimentally. The drilling fluid behavior is possible to predict considering polymer concentration, initial Brookfield viscosity, temperature, and polymers with different anionicity degrees and molecular weight. When shear stress is applied to the solution as a function of time, the predictive model reached a R2 equal to 0.97, a root mean squared error of 11 s/quart, and a percentage error of 8% and 12% for the initial and final Marsh viscosity, respectively. As for adding clay to the solution, a predictive model with R2 of 0.988, a root mean square error equal to 103 cP and a percentage error equal to 16% for the Brookfield viscosity after clay addition, were achieved. The assessment of predictive model performance with new data has revealed varying percentage errors for distinct polymers. For one polymer, the errors in predicting initial and final Marsh viscosities were 0.4% and 16.3%, respectively, while the other exhibited errors of 14.9% and 22.7%. Additionally, for Brookfield viscosity after clay addition, one polymer displayed a 10% error, while the other exhibited a 5.5% error. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-11-27 2023-11-27T00:00:00Z 2026-10-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/164140 |
url |
http://hdl.handle.net/10362/164140 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
eu_rights_str_mv |
embargoedAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799138176512557056 |