A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
DOI: | 10.3390/w15061126 |
Texto Completo: | http://dx.doi.org/10.3390/w15061126 http://hdl.handle.net/11449/247162 |
Resumo: | Coagulation is the most sensitive step in drinking water treatment. Underdosing may not yield the required water quality, whereas overdosing may result in higher costs and excess sludge. Traditionally, the coagulant dosage is set based on bath experiments performed manually, known as jar tests. Therefore, this test does not allow real-time dosing control, and its accuracy is subject to operator experience. Alternatively, solutions based on machine learning (ML) have been evaluated as computer-aided alternatives. Despite these advances, there is open debate on the most suitable ML method applied to the coagulation process, capable of the most highly accurate prediction. This study addresses this gap, where a comparative analysis between ML methods was performed. As a research hypothesis, a data-driven (D2) fuzzy inference system (FIS) should provide the best performance due to its ability to deal with uncertainties inherent to complex processes. Although ML methods have been widely investigated, only a few studies report hybrid neuro-fuzzy systems applied to coagulation. Thus, to the best of our knowledge, this is the first study thus far to address the accuracy of this non-hybrid data-driven FIS (D2FIS) for such an application. The D2FIS provided the smallest error (0.69 mg/L), overcoming the adaptive neuro-fuzzy inference system (1.09), cascade-correlation network (1.18), gene expression programming (1.15), polynomial neural network (1.20), probabilistic network (1.17), random forest (1.26), radial basis function network (1.28), stochastic gradient tree boost (1.25), and support vector machine (1.17). This finding points to the D2FIS as a promising alternative tool for accurate real-time coagulant dosage in drinking water treatment. In conclusion, the D2FIS can help WTPs to reduce operating costs, prevent errors associated with manual processes and operator experience, and standardize the efficacy with real-time and highly accurate predictions, and enhance safety for the water industry. Moreover, the evidence from this study can assist in filling the gap with the most suitable ML method and identifying a promising alternative for computer-aided coagulant dosing. For further advances, future studies should address the potential of the D2FIS for the control and optimization of other unit operations in drinking water treatment. |
id |
UNSP_57c3e083928f43da564b1269be61129c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/247162 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Predictioncoagulant dosagefuzzymachine learningwater treatmentCoagulation is the most sensitive step in drinking water treatment. Underdosing may not yield the required water quality, whereas overdosing may result in higher costs and excess sludge. Traditionally, the coagulant dosage is set based on bath experiments performed manually, known as jar tests. Therefore, this test does not allow real-time dosing control, and its accuracy is subject to operator experience. Alternatively, solutions based on machine learning (ML) have been evaluated as computer-aided alternatives. Despite these advances, there is open debate on the most suitable ML method applied to the coagulation process, capable of the most highly accurate prediction. This study addresses this gap, where a comparative analysis between ML methods was performed. As a research hypothesis, a data-driven (D2) fuzzy inference system (FIS) should provide the best performance due to its ability to deal with uncertainties inherent to complex processes. Although ML methods have been widely investigated, only a few studies report hybrid neuro-fuzzy systems applied to coagulation. Thus, to the best of our knowledge, this is the first study thus far to address the accuracy of this non-hybrid data-driven FIS (D2FIS) for such an application. The D2FIS provided the smallest error (0.69 mg/L), overcoming the adaptive neuro-fuzzy inference system (1.09), cascade-correlation network (1.18), gene expression programming (1.15), polynomial neural network (1.20), probabilistic network (1.17), random forest (1.26), radial basis function network (1.28), stochastic gradient tree boost (1.25), and support vector machine (1.17). This finding points to the D2FIS as a promising alternative tool for accurate real-time coagulant dosage in drinking water treatment. In conclusion, the D2FIS can help WTPs to reduce operating costs, prevent errors associated with manual processes and operator experience, and standardize the efficacy with real-time and highly accurate predictions, and enhance safety for the water industry. Moreover, the evidence from this study can assist in filling the gap with the most suitable ML method and identifying a promising alternative for computer-aided coagulant dosing. For further advances, future studies should address the potential of the D2FIS for the control and optimization of other unit operations in drinking water treatment.Civil and Environmental Engineering Graduate Program College of Engineering São Paulo State University, 14-01 Eng. Luiz E.C. Coube AvenueEnvironmental Engineering Department Institute of Science and Technology São Paulo State University, 500 Altino Bondensan RoadNatural Disasters Graduate Program Brazilian Center for Early Warning and Monitoring for Natural Disasters, 500 Altino Bondensan RoadCivil and Environmental Engineering Graduate Program College of Engineering São Paulo State University, 14-01 Eng. Luiz E.C. Coube AvenueEnvironmental Engineering Department Institute of Science and Technology São Paulo State University, 500 Altino Bondensan RoadUniversidade Estadual Paulista (UNESP)Brazilian Center for Early Warning and Monitoring for Natural DisastersBressane, Adriano [UNESP]Goulart, Ana Paula Garcia [UNESP]Melo, Carrie Peres [UNESP]Gomes, Isadora Gurjon [UNESP]Loureiro, Anna Isabel Silva [UNESP]Negri, Rogério Galante [UNESP]Moruzzi, Rodrigo [UNESP]Reis, Adriano Gonçalves dos [UNESP]Formiga, Jorge Kennety Silva [UNESP]da Silva, Gustavo Henrique Ribeiro [UNESP]Thomé, Ricardo Fernandes [UNESP]2023-07-29T13:08:01Z2023-07-29T13:08:01Z2023-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/w15061126Water (Switzerland), v. 15, n. 6, 2023.2073-4441http://hdl.handle.net/11449/24716210.3390/w150611262-s2.0-85152418495Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengWater (Switzerland)info:eu-repo/semantics/openAccess2023-07-29T13:08:01Zoai:repositorio.unesp.br:11449/247162Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T19:52:13.170056Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
title |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
spellingShingle |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction Bressane, Adriano [UNESP] coagulant dosage fuzzy machine learning water treatment Bressane, Adriano [UNESP] coagulant dosage fuzzy machine learning water treatment |
title_short |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
title_full |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
title_fullStr |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
title_full_unstemmed |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
title_sort |
A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction |
author |
Bressane, Adriano [UNESP] |
author_facet |
Bressane, Adriano [UNESP] Bressane, Adriano [UNESP] Goulart, Ana Paula Garcia [UNESP] Melo, Carrie Peres [UNESP] Gomes, Isadora Gurjon [UNESP] Loureiro, Anna Isabel Silva [UNESP] Negri, Rogério Galante [UNESP] Moruzzi, Rodrigo [UNESP] Reis, Adriano Gonçalves dos [UNESP] Formiga, Jorge Kennety Silva [UNESP] da Silva, Gustavo Henrique Ribeiro [UNESP] Thomé, Ricardo Fernandes [UNESP] Goulart, Ana Paula Garcia [UNESP] Melo, Carrie Peres [UNESP] Gomes, Isadora Gurjon [UNESP] Loureiro, Anna Isabel Silva [UNESP] Negri, Rogério Galante [UNESP] Moruzzi, Rodrigo [UNESP] Reis, Adriano Gonçalves dos [UNESP] Formiga, Jorge Kennety Silva [UNESP] da Silva, Gustavo Henrique Ribeiro [UNESP] Thomé, Ricardo Fernandes [UNESP] |
author_role |
author |
author2 |
Goulart, Ana Paula Garcia [UNESP] Melo, Carrie Peres [UNESP] Gomes, Isadora Gurjon [UNESP] Loureiro, Anna Isabel Silva [UNESP] Negri, Rogério Galante [UNESP] Moruzzi, Rodrigo [UNESP] Reis, Adriano Gonçalves dos [UNESP] Formiga, Jorge Kennety Silva [UNESP] da Silva, Gustavo Henrique Ribeiro [UNESP] Thomé, Ricardo Fernandes [UNESP] |
author2_role |
author author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Brazilian Center for Early Warning and Monitoring for Natural Disasters |
dc.contributor.author.fl_str_mv |
Bressane, Adriano [UNESP] Goulart, Ana Paula Garcia [UNESP] Melo, Carrie Peres [UNESP] Gomes, Isadora Gurjon [UNESP] Loureiro, Anna Isabel Silva [UNESP] Negri, Rogério Galante [UNESP] Moruzzi, Rodrigo [UNESP] Reis, Adriano Gonçalves dos [UNESP] Formiga, Jorge Kennety Silva [UNESP] da Silva, Gustavo Henrique Ribeiro [UNESP] Thomé, Ricardo Fernandes [UNESP] |
dc.subject.por.fl_str_mv |
coagulant dosage fuzzy machine learning water treatment |
topic |
coagulant dosage fuzzy machine learning water treatment |
description |
Coagulation is the most sensitive step in drinking water treatment. Underdosing may not yield the required water quality, whereas overdosing may result in higher costs and excess sludge. Traditionally, the coagulant dosage is set based on bath experiments performed manually, known as jar tests. Therefore, this test does not allow real-time dosing control, and its accuracy is subject to operator experience. Alternatively, solutions based on machine learning (ML) have been evaluated as computer-aided alternatives. Despite these advances, there is open debate on the most suitable ML method applied to the coagulation process, capable of the most highly accurate prediction. This study addresses this gap, where a comparative analysis between ML methods was performed. As a research hypothesis, a data-driven (D2) fuzzy inference system (FIS) should provide the best performance due to its ability to deal with uncertainties inherent to complex processes. Although ML methods have been widely investigated, only a few studies report hybrid neuro-fuzzy systems applied to coagulation. Thus, to the best of our knowledge, this is the first study thus far to address the accuracy of this non-hybrid data-driven FIS (D2FIS) for such an application. The D2FIS provided the smallest error (0.69 mg/L), overcoming the adaptive neuro-fuzzy inference system (1.09), cascade-correlation network (1.18), gene expression programming (1.15), polynomial neural network (1.20), probabilistic network (1.17), random forest (1.26), radial basis function network (1.28), stochastic gradient tree boost (1.25), and support vector machine (1.17). This finding points to the D2FIS as a promising alternative tool for accurate real-time coagulant dosage in drinking water treatment. In conclusion, the D2FIS can help WTPs to reduce operating costs, prevent errors associated with manual processes and operator experience, and standardize the efficacy with real-time and highly accurate predictions, and enhance safety for the water industry. Moreover, the evidence from this study can assist in filling the gap with the most suitable ML method and identifying a promising alternative for computer-aided coagulant dosing. For further advances, future studies should address the potential of the D2FIS for the control and optimization of other unit operations in drinking water treatment. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T13:08:01Z 2023-07-29T13:08:01Z 2023-03-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3390/w15061126 Water (Switzerland), v. 15, n. 6, 2023. 2073-4441 http://hdl.handle.net/11449/247162 10.3390/w15061126 2-s2.0-85152418495 |
url |
http://dx.doi.org/10.3390/w15061126 http://hdl.handle.net/11449/247162 |
identifier_str_mv |
Water (Switzerland), v. 15, n. 6, 2023. 2073-4441 10.3390/w15061126 2-s2.0-85152418495 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Water (Switzerland) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1822182365509713920 |
dc.identifier.doi.none.fl_str_mv |
10.3390/w15061126 |