MODELING THE PROPERTIES OF GAS SENSOR MATERIALS BASED ON COBALT-CONTAINING POLYACRYLONITRILE USING REGRESSION ANALYSIS AND NEURAL NETWORKS
Abstract
A modeling approach has been developed for materials based on organic semiconductors
and their physicochemical and gas-sensitive properties. For modeling, such methods as multiple
linear and non-linear regression, neural networks were used. As an input vector for modeling the
properties of metal-containing polyacrylonitrile are the parameters of the technological process of
forming materials: the mass fraction of the alloying component (cobalt) in the film-forming solution,
technological modes of IR annealing: temperature, time of the first and second stages. Output
vector - functional characteristics and physical and chemical properties of materials (resistivity,
gas sensitivity coefficient, stability and selectivity). Abstract—Metal–carbon systems with Co metal
particles based on polyacrylonitrile have been synthesized by IR pyrolysis. The resistance values
were measured in the medium of the detected gas (chlorine). Modeling of the functional characteristics
and physicochemical properties of materials was carried out on the basis of data obtained
from the study of 200 samples of cobalt/polyacrylonitrile films. Multiple linear regression proved to be effective for predicting resistivity values. Neural networks are used to predict the gas
sensitivity coefficient, selectivity, and stability of cobalt-containing polyacrylonitrile films.
An artificial neural network in the form of a multilayer perceptron was built to predict the gas
sensitivity coefficient of gas sensor elements based on the data of technological processes for obtaining
material (mass fraction of the alloying component (cobalt) in the film-forming solution,
technological modes of IR annealing: temperature, time of the first and second stages). Compliance
of the synthesized model was checked: with experimental data: correlation coefficient
R=0.82, root-mean-square error st=0.017. The synthesized models satisfactorily describe the collected
data within the experimental error, which makes it possible to optimize the chemical composition
and heat treatment conditions.
References
Noses: From Advanced Materials to Sensors Aided with Data Processing // Advanced Materials
Technologies. – 2019. – Vol. 4 (2). – P. 1800488.
2. Narkhede P., Walambe R., Mandaokar S., Chandel P., Kotecha K., Ghinea G. Gas detection
and identification using multimodal artificial intelligence based sensor fusion // Applied System
Innovation. – 2021. – Vol. 4 (1), No. 3. – P. 1-14.
3. Дулов А.А., Слинкин А.А. Органические полупроводники. – М.: Наука, 1970. – 128 с.
4. Dultsev F.N., Fioroni M.T., Blackburn J.M., Abell C., Ostanin V.P., Klenerman D. Direct and
quant tat ve detect on of bacter ophage by «hear ng» surface detachment us ng a quartz crystal
microbalance // Anal. Chem. – 2001. – Vol. 73. – P. 3935-3939.
5. Zhang X., Yang D., Yang Z., Guo X., Liu B., Ren X., Liu S. Improved PEDOT:PSS/c-Si hybrid solar
cell using inverted structure and effective passivation // Scientific Reports. – 2016. – Vol. 6. – P. 1-8.
6. Tao F., Bernasek S.L. Functionalization of Semiconductor Surfaces. – Hoboken: John Wiley &
Sons, 2012. – 434 p.
7. Calio A., Cassinese A., Casalino M., Rea I., Barra M., Chiarella F., De Stefano L. Hybrid
organic – inorganic porous semiconductor transducer for multiparameters sensing // Interface.
– 2015. – Vol. 12. – P. 20141268.
8. Géczy-Víg P., Farkas I. Neural network modelling of thermal stratification in a solar DHW
storage // Solar Energy. – 2010. – Vol. 84. – P. 801-806.
9. Efimov M.N., Vasil'ev A.A., Muratov D.G., Zemtsov L.M., Karpacheva G.P. Metall-uglerodnye
nanokompozity C/Co na osnove aktivirovannogo pirolizovannogo poliakrilonitrila i chastits
kobal'ta [Metal-carbon C/Co nanocomposites based on activated pyrolyzed polyacrylonitrile
and cobalt particles], Zhurnal fizicheskoy khimii [Journal of Physical Chemistry], 2017, Vol.
91, No. 9, pp. 1559-1564.
10. Zaporotskova I.V., Kakorina O.A., Kozhitov L.V. [i dr.]. Metallopolimernye nanokompozity
na osnove pirolizovannogo poliakrilonitrila s metallicheskimi vklyucheniyami Fe-Ni-Co
[Metallopolymer nanocomposites based on pyrolyzed polyacrylonitrile with metallic inclusions
of Fe-Ni-Co], Izvestiya vysshikh uchebnykh zavedeniy. Fizika [zvestiya of higher educational
institutions. Physics], 2020, Vol. 63, No. 11, pp. 68-74.
11. Kostina J., Chernikova E., Bondarenko G., Poteryaeva Z., Cherevan A., Efimov M., Duflot V.,
Dubova E. Influence of synthesis conditions of polyacrylonitrile on their structure and thermal
behavior, Materials, Methods & Technologies, 2012, Vol. 6, Part 1, pp. 273-289.
12. Kobzar' A.I. Prikladnaya matematicheskaya statistika. Dlya inzhenerov i nauchnykh
rabotnikov [Applied mathematical statistics. For engineers and researchers]. Moscow:
Fizmatlit, 2006, 816 p.
13. Amosov A.A., Dubinskiy Yu.A., Kopchenova N.V. Vychislitel'nye metody [Computational
methods]. Saint Petersburg, 2014, 672 p.
14. Khaykin S. Neyronnye seti: polnyy kurs [Neural networks: a complete course]. Moscow:
Izdatel'skiy dom Vil'yams, 2008, 1103 p.
15. Boccaletti S., Latora V., Moreno Y., Chavez M., Hwang D.-U. Complex networks: Structure
and dynamics, Physics Reports, 2006, Vol. 424 (4-5), pp. 175-308.
16. Moriasi D.N., Arnold J.G., Van Liew M.W., Bingner R.L., Harmel R.D., Veith T.L. Model
evaluation guidelines for systematic quantification of accuracy in watershed simulations,
Transactions of the ASABE, 2007, Vol. 50, No. 3, pp. 885-900.
17. Dreiseitl S., Ohno-Machado L. Logistic regression and artificial neural network classification
models: A methodology review, Journal of Biomedical Informatics, 2002, Vol. 35 (5-6),
pp. 352-359.
18. Bednaya T.A., Konovalenko S.P., Semenistaya T.V., Petrov V.V., Korolev A.N. Izgotovlenie
gazochuvstvitel'nykh elementov sensora dioksid azota i khlora na osnove
kobal'tsoderzhashchego poliakrilonitrila [Manufacture of gas-sensitive elements of the nitrogen
dioxide and chlorine sensor based on cobalt-containing polyacrylonitrile], Izvestiya
vysshikh uchebnykh zavedeniy. Elektronika [News of higher educational institutions. Electronics],
2012, No. 4 (96), pp. 66-71.
19. Konovalenko S.P., Bednaya T.A., Semenistaya T.V., Petrov V.V., Maraeva E.V. Razrabotka
tekhnologii polucheniya nepodogrevnykh sensorov gaza na osnove poliakrilonitrila dlya gibridnykh
sensornykh sistem [Development of technology for obtaining non-heating gas sensors based on
polyacrylonitrile for hybrid sensor systems], Inzhenernyy vestnik Dona [Engineering Bulletin of the
Don], 2012, No. 4 (Part 2). Available at:ivdon.ru/magazine/archive/n4p2y2012/1356/ (accessed
26 November 2022).
20. Werbos P.J. Backpropagation Through Time: What It Does and How to Do It, Proceedings of
the IEEE, 1990, Vol. 78, No. 10, pp. 1550-1560.
21. Setiono R., Kwong Hui, L.C. Use of a Quasi-Newton Method in a Feedforward Neural Network
Construction Algorithm, IEEE Transactions on Neural Networks, 1995, Vol. 6, No. 1,
pp. 273-277.
22. Charalambous C. Conjugate gradient algorithm for efficient training of artificial neural networks
IEE Proceedings, Devices and Systems Part, 1992, Vol. 139 (3), pp. 301-310.
23. Raja M.A.Z., Shoaib M., Hussain S., Nisar K.S., Islam S. Computational intelligence of
Levenberg-Marquardt backpropagation neural networks to study thermal radiation and Hall effects
on boundary layer flow past a stretching sheet, International Communications in Heat
and Mass Transfer, 2022, 130, art. No. 105799.
