Method of model building for estimation of quality parameters of fractionation column products under conditions of small volume of analytical control data

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The problem of improving the accuracy of models for estimating the low-temperature properties, flammability and anti-wear properties of the target products of the fractionation column under conditions of a small amount of analytical control data is considered. For the solution of the considered problem the method of model building is proposed, which includes the algorithm of expansion of a small training sample on the data of fractional composition, differing in the way of selection of additional data, taking into account the sparsity indicator, which allowed to include the missing amount of data in the training sample, and as a result to ensure the improvement of the model quality. The use of the proposed method improved the accuracy of the models by 18% on average compared to the known methods and by 6% on average compared to the method based on the expansion of the training sample without taking into account the sparsity index. The results are presented on examples of model building of quality indicators of filterability limit temperature, flash point, kinematic toughness at 40°C and cetane number of middle distillate (diesel fuel fraction) and flash point of kerosene fraction of industrial fractionation column of hydrocracking process unit.

Full Text

Restricted Access

About the authors

A. A. Plotnikov

Institute of Automatics and Control Processes, Far East Branch, Russian Academy of Sciences

Email: torgashov@iacp.dvo.ru
Russian Federation, Vladivostok

D. V. Shtakin

Institute of Automatics and Control Processes, Far East Branch, Russian Academy of Sciences

Email: torgashov@iacp.dvo.ru
Russian Federation, Vladivostok

O. Yu. Snegirev

Institute of Automatics and Control Processes, Far East Branch, Russian Academy of Sciences

Email: torgashov@iacp.dvo.ru
Russian Federation, Vladivostok

A. Yu. Torgashov

Institute of Automatics and Control Processes, Far East Branch, Russian Academy of Sciences

Author for correspondence.
Email: torgashov@iacp.dvo.ru
Russian Federation, Vladivostok

References

  1. Logunov P.L., Shamanin M.V., Kneller D.V., Setin S.P., Shunderyuk M.M. Advanced process control: from a PID loop up to refinery-wide optimization // Autom. & Remote Control. 2020. V. 80. № 10. P. 1929.
  2. Iplik E., Aslanidou I., Kyprianidis L. Hydrocracking: a perspective towards digitalization // Sustainability. 2020. V. 12. № 17. P. 1.
  3. Fortuna L., Graziani S., Sicilia M.G. Comparison of soft-sensor design methods for industrial plants using small data sets // IEEE Transactions on Instr. And Meas. 2009. V. 58. № 8. P. 2444.
  4. Shaikhina T., Khovanova N.A. Handling limited datasets with neural networks in medical applications: a small-data approach // Artificial Intel. In Med. 2016. V. 75. № 1. P. 1.
  5. Napoli G., Xibilia M.G. Soft Sensor design for a Topping process in the case of small datasets // Comput. & Chem. Eng. 2010. V. 35. № 11. P. 2447.
  6. Дрейпер Н., Смит Г. Прикладной регрессионный анализ. М.: Финансы и статистика, 1986. С. 73.
  7. Гаскаров Д.В., Шаповалов В.И. Малая выборка. М.: Статистика, 1978. С. 19.
  8. Zhu Q.X., Hou K.R., Chen Z.S., Gao Z.S., Xu Y., He Y.L. Novel virtual sample generation using conditional GAN for developing soft sensor with small data // Eng. Appl. Artif. Intell. 2021. V. 106. № 2.
  9. Zhang X.H., Xu Y., He Y.L., Zhu Q.X. Novel manifold learning based virtual sample generation for optimizing soft sensor with small data // ISA Transactions. 2021. V. 109. № 1. P. 229.
  10. Li D.C., Lin L.S., Peng L.J. Improving learning accuracy by using synthetic samples for small datasets with non-linear attribute dependency // Decision Support Syst. 2014. V. 59. № 1. P. 286.
  11. Samotylova S.A., Torgashov A.Yu. Application of a first principles mathematical model of a mass-transfer technological process to improve the accuracy of the estimation of the end product quality // Theor. Found. Chem. Eng. 2022. V. 56. № 3. P. 371. [Самотылова С.А., Торгашов А.Ю. Применение физически обоснованной математической модели массообменного технологического процесса для повышения точности оценивания качества конечного продукта // Теорет. основы хим. технологии. 2022. Т. 56. № 3. С. 371.]
  12. Bai X., Li S. A virtual sample generation method based on manifold learning and a generative adversarial network for soft sensor models with limited data // J. of the Taiwan Inst. of Chem. Eng. 2023. V. 151. № 3.
  13. Liu Y., Xie M. Rebooting data-driven soft-sensors in process industries: a review of kernel methods // J. of Proc. Control. 2020. V. 89. № 4. P. 58.
  14. He Y.L., Hua Q., Zhu Q.H., Lu S. Enhanced virtual sample generation based on manifold features: applications to developing soft sensor using small data // ISA Transactions. 2021. V. 126. № 4. P. 1.
  15. Zhu Q.X., Chen Z.S., Zhang X.H., Rajabifard A., Xu Y., Chen Y.Q. Dealing with small sample size problems in process industry using virtual sample generation: a kriging-based approach // Soft Computing. 2020. V. 24. № 1. P. 6889.
  16. Dinkov R., Stratiev D. Investigation on diesel cold flow properties // Proc. 45th International Petroleum Conf. Bratislava, 2011. P. 1.
  17. Vrablik A., Velvarska R., Stepanek K., Psenicka M., Hidalgo J.M., Cerny R. Rapid models for predicting the low-temperature behavior of diesel // Chem. Eng. Technology. 2019. V. 42. № 7. P. 735.
  18. Aleme H.G., Barbeira P.J.S. Determination of flash point and cetane index in diesel using distillation curves and multivariate calibration // Fuel. 2019. V. 102. № 1. P. 129.
  19. Gorenkov A.F., Lifanova T.A., Klyuchko I.G. Influence of jet fuel distillation range on quality indexes // Chem. & Technology of Fuels & Oils. 1985. V. 21. № 8. P. 37. [Горенков А.Ф., Лифанова Т.А., Кличко И.Г. Влияние диапазона перегонки реактивного топлива на показатели качества // Химия и Техн. Топлив и Масел. 1985. Т. 21. № 8. С. 37.]
  20. Aleme H.G., Assuncao R.A., Carvalho M.M.O., Barbeira P.J.S. Determination of specific gravity and kinematic viscosity of diesel using distillation curves and multivariate calibration // Fuel Processing Techn. 2012. V. 102. № 1. P. 90.
  21. Shepherd J.E., Nyut C.D., Lee J.J. Flash point and chemical composition of aviation kerosene (Jet A) // Explosion Dynamics Laboratory Report FM99-4. 1999. P. 1.
  22. Штакин Д.В., Снегирев О.Ю., Торгашов А.Ю. Метод построения виртуальных анализаторов в условиях малой обучающей выборки для управления качеством целевых продуктов фракционатора установки гидрокрекинга // Автоматизация в пром. 2024. Т. 22. № 6. С. 7.
  23. Dumuochel W., O’Brien F. Integrating a robust option into a multiple regression computing environment // Comp. and graphics in statistics. 1992. P. 41.
  24. Cybenko G. Approximation by superpositions of a sigmoidal function // Math. of Control, Signals & Systems. 1989. V. 2. № 1. P. 303.
  25. Bylesjo M., Rantalainen M., Nicholson J.K., Holmes E., Trygg J. K-OPLS package: Kernel-based orthogonal projections to latent structures for prediction and interpretation in feature space // BioMed Central. 2008. V. 9. № 1. P. 1.
  26. Holland P.W., Welsch R.E. Robust regression using iteratively reweighted least-squares // Communic. in Statistics – Theory & Methods. 1977. V. 6. № 9. P. 813.
  27. Rantalainen M., Bylesjo M., Cloarec O., Nicholson J.K., Holmes E., Trygg J. Kernel-based orthogonal projections to latent structures (K-OPLS) // J. of Chemometrics. 2007. V. 21. № 7–9. P. 376.
  28. Hayrettin O. Bayesian regularized neural networks for small n big p data // Artif. Neural Net. – Models & Appl. 2016. P. 27.
  29. Prak D.L., Cooke J., Dickerson T., McDaniel A., Cowart J. Cetane number, derived cetane number, and cetane index: when correlations fail to predict combustibility // Fuel. 2021. V. 289. № 12. P. 1.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Fractionation process flow chart. K-1 – fractionation column, K-2 – stripping column KF, K-3 – middle distillate stripping column, K-4 – heavy diesel fuel stripping column, KF – kerosene fraction, SD – middle distillate, DF – diesel fraction, HDF – heavy diesel fraction, UCCI – upper circulation irrigation, BCCI – lower circulation irrigation.

Download (415KB)
Indexing metadata
3. Fig. 2. Histograms of data distribution in the OV: (a) PTF of middle distillate; (b) TF of middle distillate; (c) viscosity at 40ºC of middle distillate; (d) CN of middle distillate; (d) TF of kerosene fraction.

Download (591KB)
Indexing metadata
4. Fig. 3. The structure of the proposed method for constructing a model for assessing PC in conditions of a small sample.

Download (334KB)
Indexing metadata
5. Fig. 4. Graphs of the dependences of the SAO during testing on the OVISD on the value of the sparsity indicator of the training sample S: (a) PTF of the middle distillate; (b) TSVP of the middle distillate; (c) viscosity at 40ºC of the middle distillate; (d) CN of the middle distillate; (d) TSVP of the kerosene fraction.

Download (487KB)
Indexing metadata

Copyright (c) 2025 Russian Academy of Sciences