The problem of emission control in chemical fiber industry and construction of multifactor model of pollution index prediction is studied. A neural network method that makes it possible to derive regularities of a unidimensional series for PM 2.5 and simultaneously determine the influence of a set of factors of weather conditions is described. To reduce the complexity of the model, instead of the range of factors of influence, its main components are used. The interconnection of the number of factors of influence, depth of retrospective sampling, type and scale of neural network, and accuracy of prediction is studied.
Similar content being viewed by others
References
Environment and Environmental Safety [in Russian], [electronic resource], Access mode: https://ekolog.org/books/16/5_5.htm.
O.I. Sedlyarov, A.P. Polieftova, and V.Y. Aleinikov, Fibre Chemistry, 51, No. 4, 312-317 (2019). https://doi.org/10.1007/s10692-020-10104-x.
W.-C. Chen, Y.-W. Hou, e. a., J. Zhejiang University (Engineering Science). No. 51(1), 145-152 (January 2017). https://doi.org/10.3785/j.issn.1008-973X.2017.01.018.
Pavitrakumar Sarang, Himanshu P. Kohli, et al., Chemical Data Collections, 40 (2022). https://doi.org/10.1016/j.cdc.2022.100890.
Bin Liu and Yingwei Liu, Inorg. Chem. Commun., 144 (2022). https://doi.org/10.1016/j.inoche.2022.109846.
Nawaf N. Hamadneh, Waseem S. Khan, and Waqar A. Khan, J. King Saud University, 31, No. 4, 618-627 (Sci 2019). https://doi.org/10.1016/j.jksus.2018.03.013.
Nikhil Sharma, Santosh Kumar, and K.K. Singh, Tribology Intern., 172 (2022). https://doi.org/10.1016/j.triboint.2022.107580
Jiachen Zhao, Fang Deng, Yeyun Cai, Chemosphere, 220, 486-492 (2019). https://doi.org/10.1016/j.chemosphere.2018.12.128.
Jacopo De Stefani, Ph. D Thesis, Advisor: Prof. Gianluca Bontempi, Universite Libre De Bruxelles. February 2022, 199 p.
Malek Youssef Nait, Najib Mehdi, et al., Big Data Mining and Analytics, 4, No. 1, 56-64 (2021). https://doi.org/10.26599/BDMA.2020.9020027.
Arij Omrane, AI to the rescue: Multivariate Time Series Forecasting [electronic resource]. Access mode: https://www.business-and-ai.com/ai-to-the-rescue-multivariatetime-series-forecasting.
Raza Muhammad Qamar, Mithulananthan Nadarajah, et al., IEEE Transactions on Sustainable Energy, 11, No. 1, 27-36 (2020). https://doi.org/10.1109/TSTE.2018.2883393.
Jason Brownlee, Multivariate Time Series Forecasting with LSTMs in Keras [electronic resource]. Access mode: https://machinelearningmastery.com/multivariate-timeseries-forecasting-lstms-keras.
Machine Learning and Neural Network [in Russian], Access code: https://yandex.ru/q/machine-learning/10401405953.
Li Shen, Yuning Wei, Yangzhu Wang, IEEE Transactions On Knowledge And Data Engineering, 1-28 (July 2022). https://doi.org/10.48550/arXiv.2207.10941.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Khimicheskie Volokna, No. 3, pp. 50-55, May-June 2023
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Pimenov, V.I., Pimenov, I.V. Multifactor Prediction of Ecological Indicators of Production of Chemical Fibers Based on Neural Networks. Fibre Chem 55, 187–192 (2023). https://doi.org/10.1007/s10692-023-10458-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10692-023-10458-y