Neural network model for assessing the quality indicators of the paper industry

Studies of the dependence of the quality of the paper web on the production conditions and properties of raw materials give a significant statistical spread, as a result of which it is impossible to accurately predict the result. This fact became a prerequisite for the use of neural network modeling technology in the development of an intelligent system for monitoring the quality of the paper web. The methodology for determining the estimates of the heterogeneity of the structure of the paper web at the final stage of its production is considered. It is proposed to expand the classification of finished product samples through the use of neurofuzzy interpolation of the linguistic values of such indicators, which will improve the efficiency of the production process

Keywords: paper production, quality assessment, structural heterogeneity assessment, neural network model, neural network classifier

References

  1. M. S. Revunov. Improving the stabilization system of paper flow parameters using the cross-correlation algorithm//Measurement Monitoring Control. Control. 2018. № 4. P. 24-34.
  2. I. I. Osovskaya, V. S. Antonova. The influence of surface destrution on the hydrophilicity and ability to from connections of the cellulose fibers//Chemistry of plant raw materials. 2020. № 1. P. 315-320.
  3. S. M. Gerasyuta, A. S. Smolin, E. I. Ivanova, V. S. Kanevskaya. Investigation of the coefficient of variation and the average size of the heterogeneity for various types of paper on the AP-2 collet analyzer//Proceedings of the St. Petersburg Forestry Academy. 2016. № 217. P. 238-247.
  4. V. V. Abramova, A. V. Gur'ev. Evaluation of Macrostructure Forming Uniformity of Copy Paper//Higher Education News. Forest magazine. 2017. № 4. P. 172-186.
  5. D. A. Manoshin. Artificial Intelligence Programming//Colloquium-journal. 2019. № 12 (36).
  6. Y. Zhou, T. Murata. Fuzzy -timing Petri net model for distributed mul-timedia synchronization//Proc. of the 1998 IEEE Conference on Systems, Man and Cybernetics, October 11-14. Lolla, California, 1998. P. 244-249.
  7. X. Koutsoukos, P. J. Antsaklis, J. A. Stiver, M. D. Lemmon. Supervisory control of hybrid systems//Proc. of IEE. 2000. 88. № 5. Р. 1026-1049.
  8. Y. Qian, X. X. Li, Y. R. Jiang. An expert system for real-time fault diagnosis of complex chemical processes//Expert Systems with Applications Vol. 24. Issue 4. May 2003. P. 425-432.
  9. J. Kallrath, S. Rebennack, J. Kallrath, R. Kusche. Solving real-world cutting stock-problems in the paper industry: Mathematical approaches, experience and challenges// European Journal of Operational Research. 2014. Vol. 238. Issue 1. P. 374-389.
  10. H. Dyckhoff. A typology of cutting and packing problems//European Journal of Operational Research. 990. № 44. P. 145-159.
  11. I. Harjunkoski. Qualitaetsbasierte Schnittplanoptimierung in der Papierindustrie//Automatisierungstechnik. 2008. № 2. P. 31-44.
  12. M. H. Correia, J. F. Oliveira, J. S. Ferreira. Integrated resolution of assignment, sequencing and cutting problems in paper production planning//International Journal of Production Research. 2012. 50 (18). P. 5195-5212.
  13. S. C. Poltroniere, S. A. Araujo, K. C. Poldi. Optimization of an Integrated Lot Sizing and Cutting Stock Problem in the Paper Industry//TEMA (Sгo Carlos) [online]. 2016. Vol. 17. № 3. P. 305-320.
  14. E. Silva, F. Alvelos, J. M. Valґerio de Carvalho. Integrating two-dimensional cutting stock and lot-sizing problems//Journal of the OperationalResearch Society. 2014. 65. 1. 108-123.
  15. J. Sahno, Ed. Shevtshenko, T. Karaulova, Kh. Tahera. Framework for continuous improvement of production processes//Economics of engineering decisions. Vol. 26. № 2. 2015.
  16. R. Rajnoha, K. Gбlovб, Z. Rуzsa. Measurement of Impact of Selected Industrial Engineering Practices on Companies’ Economic Performance//Economics of engineering decisions. Vol. 29. № 2. 2018.
  17. M. M. Khapaev, A. A. Tsygankov. An algorithm for the constrained extremum problems//Computational Mathematics and Modeling. 1997. Vol. 8. № 4. P. 322-325.
  18. G. Scheithauer. Zuschnitt und Packungsoptimierung. Problemstellungen, Model-lierungs-techniken, Loesungsmethoden. Wiesbaden: Verlag: Vieweg+Taubner, 2008. 132 р.
  19. A. Chernikova, S. Kuzmina, G. Kondrashkova, I. Bondarenkova. Digitizaton and axiomatics in modern metrology//IOP Conference Series: Materials Science and Engineering.2019. P. 12-13.
  20. V. V. Okrepilov, S. N. Kuzmina, V. L. Makarov, A. R. Bakhtizin. Application of supercomputer technologies for modeling socio-economic systems /Economy of Region. 2015. № 2. P. 301-313.
  21. GOST R 53636-2009 GOST R 53636-2009. Cellyuloza, bumaga, karton. Terminy i opredeleniya http://docs.cntd.ru/document/gost-r-53636-2009.
  22. OST 13-299-87. Hlysty drevesnye. Metody poshtuchnogo izmereniya i tablicy ob»emov. http://docs.cntd.ru/search/intellectual/q/%D0%9E%D0%A1%D0%A2+13-232-87/r/4.
  23. Y. Zhou, J. Hahn, M. Sam Mannan. Fault detection and classification in chemical processes based on neural networks with feature extraction//ISA Transactions. 2003. Vol. 42. P. 651-664.

Authors