Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series. Silva, L., Marques, M., Gomes, M., Escovedo, T., & Kalinowski, M. In Proceedings of the XIX Brazilian Symposium on Information Systems, of SBSI '23, pages 102–111, 2023. Association for Computing Machinery. ![Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Author version doi abstract bibtex 5 downloads Context: Virtual analyzers or inferences are mathematical models widely used in the chemical process industry, as they allow real-time prediction of properties of interest from measurements of basic properties available at the appropriate frequency. Problem: Therefore, they are a key component of chemical process control and optimization structures. Inferences with superior prediction capabilities provide a better process control reducing losses and improving profits. Solution: This work seeks to establish whether Machine Learning (ML) algorithms and techniques could be used to generate inferences for the ethane content in Liquefied Petroleum Gas (LPG) produced in a Natural Gas Processing Unit (NGPU) with advantages over the inferences traditionally used. IS Theory: This work is associated with the Theory of the knowledge-based company, assisting in decision-making and efficiency in the application of resources. Method: In order to accomplish this, a dataset with five years of real data from a Petrobras UPGN has been obtained, and models with different types of algorithms were generated. The machine learning models are compared between them and against models similar to the inferences currently used in the plant, in order to verify whether the ML tools have real potential to provide better results. Summary of Results: The obtained results showed that the machine learning models have a much better representation capability when compared to the traditional inference models. Contributions and Impact in the IS area: The paper contributes to the use of machine learning techniques to generate better inferences for the ethane content in LGP produced in a NGPU, making the analytical process more agile and assertive to increase the generation of value for Petrobras.
@inproceedings{SilvaMGEK23,
author = {Silva, Luciana and Marques, Marcelo and Gomes, Marcos and Escovedo, Tatiana and Kalinowski, Marcos},
title = {Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series},
year = {2023},
isbn = {9798400707599},
publisher = {Association for Computing Machinery},
urlAuthor_version = {http://www.inf.puc-rio.br/~kalinowski/publications/SilvaMGEK23.pdf},
doi = {10.1145/3592813.3592894},
abstract = {Context: Virtual analyzers or inferences are mathematical models widely used in the chemical process industry, as they allow real-time prediction of properties of interest from measurements of basic properties available at the appropriate frequency. Problem: Therefore, they are a key component of chemical process control and optimization structures. Inferences with superior prediction capabilities provide a better process control reducing losses and improving profits. Solution: This work seeks to establish whether Machine Learning (ML) algorithms and techniques could be used to generate inferences for the ethane content in Liquefied Petroleum Gas (LPG) produced in a Natural Gas Processing Unit (NGPU) with advantages over the inferences traditionally used. IS Theory: This work is associated with the Theory of the knowledge-based company, assisting in decision-making and efficiency in the application of resources. Method: In order to accomplish this, a dataset with five years of real data from a Petrobras UPGN has been obtained, and models with different types of algorithms were generated. The machine learning models are compared between them and against models similar to the inferences currently used in the plant, in order to verify whether the ML tools have real potential to provide better results. Summary of Results: The obtained results showed that the machine learning models have a much better representation capability when compared to the traditional inference models. Contributions and Impact in the IS area: The paper contributes to the use of machine learning techniques to generate better inferences for the ethane content in LGP produced in a NGPU, making the analytical process more agile and assertive to increase the generation of value for Petrobras.},
booktitle = {Proceedings of the XIX Brazilian Symposium on Information Systems},
pages = {102–111},
numpages = {10},
location = {Macei\'{o}, Brazil},
series = {SBSI '23}
}
Downloads: 5
{"_id":"SYMNXmhKmdK7NYMFD","bibbaseid":"silva-marques-gomes-escovedo-kalinowski-inferenceofpropertiesofanaturalgasprocessingplantthroughtheapplicationofmachinelearningtotimeseries-2023","author_short":["Silva, L.","Marques, M.","Gomes, M.","Escovedo, T.","Kalinowski, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Silva"],"firstnames":["Luciana"],"suffixes":[]},{"propositions":[],"lastnames":["Marques"],"firstnames":["Marcelo"],"suffixes":[]},{"propositions":[],"lastnames":["Gomes"],"firstnames":["Marcos"],"suffixes":[]},{"propositions":[],"lastnames":["Escovedo"],"firstnames":["Tatiana"],"suffixes":[]},{"propositions":[],"lastnames":["Kalinowski"],"firstnames":["Marcos"],"suffixes":[]}],"title":"Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series","year":"2023","isbn":"9798400707599","publisher":"Association for Computing Machinery","urlauthor_version":"http://www.inf.puc-rio.br/~kalinowski/publications/SilvaMGEK23.pdf","doi":"10.1145/3592813.3592894","abstract":"Context: Virtual analyzers or inferences are mathematical models widely used in the chemical process industry, as they allow real-time prediction of properties of interest from measurements of basic properties available at the appropriate frequency. Problem: Therefore, they are a key component of chemical process control and optimization structures. Inferences with superior prediction capabilities provide a better process control reducing losses and improving profits. Solution: This work seeks to establish whether Machine Learning (ML) algorithms and techniques could be used to generate inferences for the ethane content in Liquefied Petroleum Gas (LPG) produced in a Natural Gas Processing Unit (NGPU) with advantages over the inferences traditionally used. IS Theory: This work is associated with the Theory of the knowledge-based company, assisting in decision-making and efficiency in the application of resources. Method: In order to accomplish this, a dataset with five years of real data from a Petrobras UPGN has been obtained, and models with different types of algorithms were generated. The machine learning models are compared between them and against models similar to the inferences currently used in the plant, in order to verify whether the ML tools have real potential to provide better results. Summary of Results: The obtained results showed that the machine learning models have a much better representation capability when compared to the traditional inference models. Contributions and Impact in the IS area: The paper contributes to the use of machine learning techniques to generate better inferences for the ethane content in LGP produced in a NGPU, making the analytical process more agile and assertive to increase the generation of value for Petrobras.","booktitle":"Proceedings of the XIX Brazilian Symposium on Information Systems","pages":"102–111","numpages":"10","location":"Maceió, Brazil","series":"SBSI '23","bibtex":"@inproceedings{SilvaMGEK23,\r\n author = {Silva, Luciana and Marques, Marcelo and Gomes, Marcos and Escovedo, Tatiana and Kalinowski, Marcos},\r\n title = {Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series},\r\n year = {2023},\r\n isbn = {9798400707599},\r\n publisher = {Association for Computing Machinery},\r\n urlAuthor_version = {http://www.inf.puc-rio.br/~kalinowski/publications/SilvaMGEK23.pdf},\r\n doi = {10.1145/3592813.3592894},\r\n abstract = {Context: Virtual analyzers or inferences are mathematical models widely used in the chemical process industry, as they allow real-time prediction of properties of interest from measurements of basic properties available at the appropriate frequency. Problem: Therefore, they are a key component of chemical process control and optimization structures. Inferences with superior prediction capabilities provide a better process control reducing losses and improving profits. Solution: This work seeks to establish whether Machine Learning (ML) algorithms and techniques could be used to generate inferences for the ethane content in Liquefied Petroleum Gas (LPG) produced in a Natural Gas Processing Unit (NGPU) with advantages over the inferences traditionally used. IS Theory: This work is associated with the Theory of the knowledge-based company, assisting in decision-making and efficiency in the application of resources. Method: In order to accomplish this, a dataset with five years of real data from a Petrobras UPGN has been obtained, and models with different types of algorithms were generated. The machine learning models are compared between them and against models similar to the inferences currently used in the plant, in order to verify whether the ML tools have real potential to provide better results. Summary of Results: The obtained results showed that the machine learning models have a much better representation capability when compared to the traditional inference models. Contributions and Impact in the IS area: The paper contributes to the use of machine learning techniques to generate better inferences for the ethane content in LGP produced in a NGPU, making the analytical process more agile and assertive to increase the generation of value for Petrobras.},\r\n booktitle = {Proceedings of the XIX Brazilian Symposium on Information Systems},\r\n pages = {102–111},\r\n numpages = {10},\r\n location = {Macei\\'{o}, Brazil},\r\n series = {SBSI '23}\r\n}\r\n\r\n","author_short":["Silva, L.","Marques, M.","Gomes, M.","Escovedo, T.","Kalinowski, M."],"key":"SilvaMGEK23","id":"SilvaMGEK23","bibbaseid":"silva-marques-gomes-escovedo-kalinowski-inferenceofpropertiesofanaturalgasprocessingplantthroughtheapplicationofmachinelearningtotimeseries-2023","role":"author","urls":{"Author version":"http://www.inf.puc-rio.br/~kalinowski/publications/SilvaMGEK23.pdf"},"metadata":{"authorlinks":{}},"downloads":5},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/KuRSiZJF8A6EZiujE","dataSources":["q7rgFjFgwoTSGkm3G","B8Jierr7smZsGa7Jb","tvqztEQv84agmtPEB","FGDKYBjH9upApdKoL","56kphca3KPjtFZJC6","JxJm4GfaRAd3NEw2w","iSfhee4nHcHz4F2WQ"],"keywords":[],"search_terms":["inference","properties","natural","gas","processing","plant","through","application","machine","learning","time","series","silva","marques","gomes","escovedo","kalinowski"],"title":"Inference of Properties of a Natural Gas Processing Plant Through the Application of Machine Learning to Time Series","year":2023,"downloads":5}