@article{ferreira_development_2022,
	title = {Development of a {Machine} {Learning}-based {Soft} {Sensor} for an {Oil} {Refinery}’s {Distillation} {Column}},
	issn = {0098-1354},
	url = {https://www.sciencedirect.com/science/article/pii/S0098135422000977},
	doi = {10.1016/j.compchemeng.2022.107756},
	abstract = {In this paper, a machine learning framework based on Kaizen Programming is proposed for building a soft-sensor using real historical data from an oil refinery. The soft-sensor estimates the composition of C4 hydrocarbons in the distillate stream of a splitter column. Kaizen Programming is a novel technique that has shown excellent results for symbolic regression problems without requiring a priori selection of the functional bases. The framework follows three different steps: pre-processing of the data, model building with the selected algorithm, and ensemble of different good-fitting models. The final ensemble model accurately predicts operation of the column at and between two steady states, outperforming the model based on Gaussian Process in both validation and soft-sensor degradation scenarios.},
	language = {en},
	urldate = {2022-03-16},
	journal = {Computers \& Chemical Engineering},
	author = {Ferreira, Jimena and Pedemonte, Martín and Torres, Ana Inés},
	month = mar,
	year = {2022},
	keywords = {Kaizen Programming, Machine Learning, Modeling from real data, Soft sensor, Surrogate models, mentions sympy},
	pages = {107756},
}

{"_id":"53DYpdjiL7C3gzafF","bibbaseid":"ferreira-pedemonte-torres-developmentofamachinelearningbasedsoftsensorforanoilrefinerysdistillationcolumn-2022","author_short":["Ferreira, J.","Pedemonte, M.","Torres, A. I."],"bibdata":{"bibtype":"article","type":"article","title":"Development of a Machine Learning-based Soft Sensor for an Oil Refinery’s Distillation Column","issn":"0098-1354","url":"https://www.sciencedirect.com/science/article/pii/S0098135422000977","doi":"10.1016/j.compchemeng.2022.107756","abstract":"In this paper, a machine learning framework based on Kaizen Programming is proposed for building a soft-sensor using real historical data from an oil refinery. The soft-sensor estimates the composition of C4 hydrocarbons in the distillate stream of a splitter column. Kaizen Programming is a novel technique that has shown excellent results for symbolic regression problems without requiring a priori selection of the functional bases. The framework follows three different steps: pre-processing of the data, model building with the selected algorithm, and ensemble of different good-fitting models. The final ensemble model accurately predicts operation of the column at and between two steady states, outperforming the model based on Gaussian Process in both validation and soft-sensor degradation scenarios.","language":"en","urldate":"2022-03-16","journal":"Computers & Chemical Engineering","author":[{"propositions":[],"lastnames":["Ferreira"],"firstnames":["Jimena"],"suffixes":[]},{"propositions":[],"lastnames":["Pedemonte"],"firstnames":["Martín"],"suffixes":[]},{"propositions":[],"lastnames":["Torres"],"firstnames":["Ana","Inés"],"suffixes":[]}],"month":"March","year":"2022","keywords":"Kaizen Programming, Machine Learning, Modeling from real data, Soft sensor, Surrogate models, mentions sympy","pages":"107756","bibtex":"@article{ferreira_development_2022,\n\ttitle = {Development of a {Machine} {Learning}-based {Soft} {Sensor} for an {Oil} {Refinery}’s {Distillation} {Column}},\n\tissn = {0098-1354},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0098135422000977},\n\tdoi = {10.1016/j.compchemeng.2022.107756},\n\tabstract = {In this paper, a machine learning framework based on Kaizen Programming is proposed for building a soft-sensor using real historical data from an oil refinery. The soft-sensor estimates the composition of C4 hydrocarbons in the distillate stream of a splitter column. Kaizen Programming is a novel technique that has shown excellent results for symbolic regression problems without requiring a priori selection of the functional bases. The framework follows three different steps: pre-processing of the data, model building with the selected algorithm, and ensemble of different good-fitting models. The final ensemble model accurately predicts operation of the column at and between two steady states, outperforming the model based on Gaussian Process in both validation and soft-sensor degradation scenarios.},\n\tlanguage = {en},\n\turldate = {2022-03-16},\n\tjournal = {Computers \\& Chemical Engineering},\n\tauthor = {Ferreira, Jimena and Pedemonte, Martín and Torres, Ana Inés},\n\tmonth = mar,\n\tyear = {2022},\n\tkeywords = {Kaizen Programming, Machine Learning, Modeling from real data, Soft sensor, Surrogate models, mentions sympy},\n\tpages = {107756},\n}\n\n\n\n","author_short":["Ferreira, J.","Pedemonte, M.","Torres, A. I."],"key":"ferreira_development_2022","id":"ferreira_development_2022","bibbaseid":"ferreira-pedemonte-torres-developmentofamachinelearningbasedsoftsensorforanoilrefinerysdistillationcolumn-2022","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0098135422000977"},"keyword":["Kaizen Programming","Machine Learning","Modeling from real data","Soft sensor","Surrogate models","mentions sympy"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/nicoguaro/525293","dataSources":["7XH2gw6L5iJQ9EppA","YtBDXPDiQEyhyEDZC","fhHfrQgj3AaGp7e9E","qzbMjEJf5d9Lk78vE","45tA9RFoXA9XeH4MM","MeSgs2KDKZo3bEbxH","nSXCrcahhCNfzvXEY","ecatNAsyr4f2iQyGq","tpWeaaCgFjPTYCjg3"],"keywords":["kaizen programming","machine learning","modeling from real data","soft sensor","surrogate models","mentions sympy"],"search_terms":["development","machine","learning","based","soft","sensor","oil","refinery","distillation","column","ferreira","pedemonte","torres"],"title":"Development of a Machine Learning-based Soft Sensor for an Oil Refinery’s Distillation Column","year":2022}