The comparative analysis of the methods of constructing soft sensors for the quality estimation of fractionation column products with account to missing data in the training set

Abstract


This article presents a comparative analysis of methods of constructing statistical models based on robust regression, ridge regression, kernel-based orthogonal projections to latent structures (K-OPLS), alternating conditional expectations (ACE) and direct distribution neural networks. These models are used for estimating the values of the points of fractional composition of the kerosene fraction, the product of the fractionation column. During the construction of models, the issue of meaning the values of input variables over a certain period was considered to link them to the values of output variables. Unlike the existing works, in this article, training and testing of models is carried out on segments of the data array limited in the values of the output variable. The training segment is formed from the general array by excluding observations whose values are limited by upper and lower limits. The excluded observations constitute the test sample. This paper shows the influence of the width of the interval of meaning the values of the input variable on the estimating accuracy of the resulting models. It is also shown that the lowest value of the mean absolute error for estimating the points of fractional composition is provided by models based on neural networks and K-OPLS for various training and testing options.

Full Text

6

About the authors

A. A Plotnikov

Far Eastern Federal University

D. V Shtakin

Institute of Automation and Control Processes Far Eastern Branch of the Russian Academy of Sciences; Far Eastern Federal University

O. Yu Snegirev

Institute of Automation and Control Processes Far Eastern Branch of the Russian Academy of Sciences

A. Yu Torgashov

Institute of Automation and Control Processes Far Eastern Branch of the Russian Academy of Sciences; Far Eastern Federal University

References

  1. Kadlec, P. Data-driven soft sensors in the process industry / P. Kadlec, B. Gabrys, S. Strandt // Computers and Chemical Engineering. 2009. – Vol. 33, iss. 4. – P. 795–814. doi: 10.1016/j.compchemeng.2008.12.012
  2. Iplik, E. Hydrocracking: a perspective towards digitalization / E. Iplik, I. Aslanidou, K. Kyprianidis // Sustainability (Switzerland). 2020. – Vol. 12, iss. 17. – 26 p. DOI: 10.3390/ su12177058
  3. The role of artificial intelligence-driven soft sensors in advanced sustainable process industries: A critical review / Y.S. Perera, D.A.A.C. Ratnaweera, C.H. Dasanayaka, C. Abeykoon // Engineering Applications of Artificial Intelligence. 2023. – Vol. 121, iss. 105988. – 24 p. doi: 10.1016/j.engappai.2023.105988
  4. King, M. Process control. A practical approach / M. King // Wiley. – 2016. – 2 Ed. – 623 p.
  5. Data-driven prediction of product yields and control framework of hydrocracking unit / Z. Pang, P. Huang, C. Lian, C. Peng, X. Fang, H. Liu // Chemical Engineering Science. 2024. – Vol. 283, iss. 119386 – 10 p. doi: 10.1016/j.ces.2023.119386
  6. A layer-wise data augmentation strategy for deep learning networks and its soft sensor application in an industrial hydrocracking Process / X. Yuan, C. Ou, Y. Wang, C. Yang, W. Gui // IEEE Trans Neural Netw Learn Syst. 2021. – Vol. 32, iss. 8. – P. 3296–3305. DOI: 10.1109/ TNNLS.2019.2951708
  7. Rani, A. Development of soft sensor for neural network based control of distillation column / A. Rani, V. Singh, J.R.P. Gupta // ISA Transactions. 2013. – Vol. 52, iss. 3. – P. 438–449. doi: 10.1016/j.isatra.2012.12.009
  8. Wang, Y. A two-layer ensemble learning framework for data-driven soft sensor of the diesel attributes in an industrial hydrocracking process / Y. Wang, D. Wu, X. Yuan // Journal of Chemometrics. 2019. – Vol. 33, iss. 12. – 14 p. doi: 10.1002/cem.3185
  9. Popoola, L.T. A Review of an expert system design for crude oil distillation column using the neural networks model and process optimization and control using genetic algorithm framework / L.T. Popoola, G. Babagana, A.A. Susu // Advances in Chemical Engineering and Science. 2013. – Vol. 3, iss. 2. – P. 164–170. doi: 10.4236/aces.2013.32020
  10. Soft-sensor design for a crude distillation unit using statistical learning methods / A. Urhan, N.G. Ince, R. Bondy, B. Alakent // Computer Aided Chemical Engineering. 2018. – Vol. 44. – P. 2269–2274. doi: 10.1016/B978-0-444-64241-7.50373-6
  11. Kano, M. The state of the art in advanced chemical process control in Japan / M. Kano, M. Ogawa // IFAC Proceedings Volumes. 2009. – Vol. 7, iss. 1. – P. 10–25. DOI: 10.3182/ 20090712-4-TR-2008.00005
  12. Hinich, M.J. A simple method for robust regression / M.J. Hinich, P.P. Talwar // Journal of the American Statistical Association. 1975. – Vol. 70, iss. 349. – P. 113–119. DOI: 10.1080/ 01621459.1975.10480271
  13. Дрейпер, Н. Прикладной регрессионный анализ / Н. Дрейпер, Г. Смит. – М.: Финансы и статистика, 1986. – Кн. 2. – 351 с.
  14. Alheety, M.I. Choosing ridge parameters in the linear regression model with AR(1): A comparative simulation study / M.I. Alheety, B.M.G. Kibria // International Journal of Statistics and Economics. – 2011. – Vol. 7, iss. 11. – 18 p.
  15. Khalaf, G. Choosing ridge parameter for regression problems / G. Khalaf, G. Shukur // Communications in statistics – Theory and Methods. 2005. – Vol. 34, iss. 5. – P. 1177–1182. doi: 10.1081/STA-200056836
  16. K-OPLS package: kernel-based orthogonal projections to latent structures for prediction and interpretation in feature space / M. Bylesjo, M. Rantalainen, J. K. Nicholson, E. Holmes, J. Trygg // BMC Bioinformatics. 2008. – Vol. 9, iss. 106. – 7 p. doi: 10.1186/1471-2105-9-106
  17. Correlating Bacharach Opacity in Fuel Oil Exhaust. Prediction of the Operating Parameters that Reduce It / M. Blanco, J. Coello, S. Maspoch, A. Puigdomenech, X. Peralta, J.M. Gonzalez, J. Torres // Oil & Gas Science and Technology. – 2000. – Vol. 55, iss. 5. – P. 533–541. doi: 10.2516/ogst: 2000040
  18. Wang, D. Identifying nonlinear relationships in regression using the ACE Algorithm / D. Wang, M. Murphy // Journal of Applied Statistics. 2005. – Vol. 32, iss. 3. – P. 243–258. DOI: 10.1080=02664760500054517
  19. Li, Yang. On hyperparameter optimization of machine learning algorithms: theory and practice / Yang Li, Abdallah Shami. // Neurocomputing. 2020. – Vol. 415. – P. 295–316. doi: 10.1016/j.neucom.2020.07.061
  20. ASTM D86 – 23. Standard test method for distillation of petroleum products at atmos-pheric pressure // American National Standard. ASTM International. – 2023. – 22 p.

Statistics

Views

Abstract - 6

PDF (Russian) - 1

Refbacks

  • There are currently no refbacks.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies