МОДЕЛИРОВАНИЯ СВОЙСТВ МАТЕРИАЛОВ СЕНСОРОВ ГАЗОВ НА ОСНОВЕ КОБАЛЬТСОДЕРЖАЩЕГО ПОЛИАКРИЛОНИТРИЛА С ИСПОЛЬЗОВАНИЕМ РЕГРЕССИОННОГО АНАЛИЗА И НЕЙРОННЫХ СЕТЕЙ

Abstract

A modeling approach has been developed for materials based on organic semiconductorsand their physicochemical and gas-sensitive properties. For modeling, such methods as multiplelinear and non-linear regression, neural networks were used. As an input vector for modeling theproperties of metal-containing polyacrylonitrile are the parameters of the technological process offorming 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. Outputvector - functional characteristics and physical and chemical properties of materials (resistivity,gas sensitivity coefficient, stability and selectivity). Abstract—Metal–carbon systems with Co metalparticles based on polyacrylonitrile have been synthesized by IR pyrolysis. The resistance valueswere measured in the medium of the detected gas (chlorine). Modeling of the functional characteristicsand physicochemical properties of materials was carried out on the basis of data obtainedfrom 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 gassensitivity 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 gassensitivity coefficient of gas sensor elements based on the data of technological processes for obtainingmaterial (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). Complianceof the synthesized model was checked: with experimental data: correlation coefficientR=0.82, root-mean-square error st=0.017. The synthesized models satisfactorily describe the collecteddata within the experimental error, which makes it possible to optimize the chemical compositionand heat treatment conditions.