Development of a Neural Model of a Semiconductor Gas Sensor

Purpose of research: Development of a neural model of a semiconductor gas sensor in order to generate data for training an information-processing device of gas analyzers based on artificial neural networks (ANN). Search and optimization of cleaning data composition and volume. The neural model of the sensor should take into account the influence of those factors on the signal, the fluctuations of which make the maximum contribution to the measurement errors. Testing of the model based on semiconductor carbon monoxide and hydrogen sensors.
Methods. Methods of computer modeling, numerical methods, theory of neural networks. To compare the simulation results and the responses of real sensors, the relative error and standard deviation were determined.
Results. Studies of various structures of the neural model of a semiconductor sensor have been carried out, the structure of a multilayer neural network of direct propagation for two semiconductor carbon monoxide and hydrogen sensors has been selected, modeling errors have been estimated, recommendations have been given for choosing the optimal structure and the amount of training data.
Conclusion. Neural models of semiconductor carbon monoxide and hydrogen sensors have been obtained, conclusions have been drawn about the possibility of using this ANN structure in solving typical problems. Based on the analysis of the errors obtained, the effectiveness of using neural models of sensors to generate training data has been shown. The maximum relative error of modeling the TGS2442 semiconductor carbon monoxide sensor did not exceed 5% for the main characteristic and 2% for additional ones. The maximum relative error of modeling of the TGS2442 semiconductor hydrogen sensor did not exceed 3% for the main characteristic and 1% for additional ones.

1. Tomakova R.A., Filist SA, Yaa Z.D. Tomakova R.A. Universal'nye setevye modeli dlya zadach klassifikatsii biomeditsinskikh dannykh [Universal network models for classification problems of biomedical data]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2012, no. 4-2 (43), pp. 44-50 (In Russ.).

2. Dashkovsky A. A., Primisskiy V. F. Matematicheskoe modelirovanie mnogokomponentnykh gazoanaliticheskikh izmerenii i analiz pogreshnostei [Mathematical modeling of multicomponent gatana-lytic measurements and error analysis]. Vostochno-Evropeiskii zhurnal peredovykh tekhnologii = Second-European Journal of Advanced Technologies, 2005, no. 6/2 (18), pp. 108-111 (In Russ.).

3. Sazonov S. Yu., Titenko E. A., Khanis N. A. Podkhod k prognozirovaniyu vozniknoveniya pozharoopasnoi situatsii v data-tsentre na osnove neironnykh sete [Approach to predicting the occurrence of a fire hazard in a data center based on neural networks]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2015, no. 4 (17), pp. 8-14 (In Russ.).

4. Swingler K. Applying neural networks: A practical guide. London, Academic Press, 1996, 345 р.

5. Foresee F.D., Hagan M.T. Gaus-Newton approximation to Bayesian regularization. Proceedings of the 1997 International Joint Conference on Neural Networks, 1997, pp. 1930-1935.

6. Dreizin V. E., Grima A. A. Izmeritel'nyi blok dlya neitronnogo spektrometra real'nogo vremeni s vychislitel'nym vosstanovleniem energeticheskikh spektrov s pomoshch'yu neironnykh setei [Measurement unit for a real-time neutron spectrometer with numerical recovery of energy spectra using neural networks]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2012, no. 2- 3, pp. 223-228 (In Russ.).

7. Mikhalchenko D. I., Ivin A. G., Shevchenko O. Yu., Aksamentov E. A. Primenenie neironnykh setei v zadache polucheniya karty glubiny iz dvumernogo izobrazheniya [Application of Deep Neural Networks in the Problem of Obtaining Depth Maps from TwoDimensional Images]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2019; 23(3): 113-134 (In Russ.) https://doi.org/10.21869/2223-1560-2019-23-3-113-134.

8. Dreizin V. E., Brezhneva E. O., Bondar O. G. Ustroistvo obrabotki signalov mnogokomponentnogo gazoanalizatora [Signal processing Device for multicomponent gas analysis.]. Pribory i Sistemy. Upravlenie, kontrol', diagnostika = Devices and Systems Management, Control, Diagnostics, 2011, no. 12, pp. 43-48 (In Russ.).

9. Bondar O. G., Brezhneva E. O., Chernyshov R. E. Primenenie neironnykh setei v zadache kolichestvennogo analiza sostava vozdushnoi sredy [Application of Neural Networks in the Problem of Quantitative Analysis of Air Composition]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2020, 24(1): 159-174 (In Russ.). https://doi.org/10.21869/2223-1560-2020-24-1-159-174

10. Bondar O. G., Brezhneva E. O., Pozdnyakov V. V. Methods and Algorithms for Con-trol of a Thermocatalytic Hydrogen Sensor. Measurement Techniques, August, 2018, vol.61, no. 5, pp.514-519.

11. George F., Cavanagh L. M., Afonja A., Binions R. Metal Oxide Semi-Conductor Gas Sensors in Environmental Monitoring. Sensors, 2010, pp. 5469-5502.

12. Dreizin V. E., Brezhnev E. O. [Modeling of gas-sensitive sensors]. Materialy 2-oi Mezhdunarodnoi nauch.-tekhn. konf. "Informatsionno-izmeritel'nye diagnosticheskie i upravlyayushchie sistemy. Diagnostika 2011" [Materials of the 2nd International scientific and technical conference "Information and measurement diagnostic and control systems. Diagnostics 2011"]. Kursk, 2011, pp. 53-59 (In Russ.).

13. Dreizin V. E., Brezhneva E. O. Sravnitel'nyi analiz kharakteristik promyshlennykh gazochuvstvitel'nykh datchikov [Comparative analysis of characteristics of industrial gassensitive sensors]. Datchiki i sistemy = Sensors and Systems, 2011, no. 3, pp. 68-78 (In Russ.).

14. Diakonov V. P., Kruglov V. V. MatLab 6.5 SP1/7/7 SP1/7 SP2. Moscow, SolonPress Publ., 2006. 456 p. (In Russ.).

15. Latypova Ramilya. Neironnye seti [Neural networks]. Moscow, LAP Lambert Academic Publishing, 2012. 572 p. (In Russ.).

16. Osnovy neirokibernetiki [Fundamentals of Neurocybernetics]. Moscow, Vysshaya shkola Publ., 2015. 372 p. (In Russ.).

17. Redko V. G. Podkhody k modelirovaniyu myshleniya [Approaches to modeling thinking]. Moscow, IL Publ., 2016. 392 p. (In Russ.).

18. Redko V. G. Evolyutsiya, neironnye seti, intellekt: Modeli i kontseptsii evolyutsionnoi kibernetiki [Evolution, neural networks, intelligence: Models and concepts of evolutionary Cybernetics]. Moscow, Vysshaya shkola Publ., 2017. 224 p. (In Russ.).

19. Tadeusevich Ryszard [et al.]. Elementarnoe vvedenie v tekhnologiyu neironnykh setei s primerami programm [Elementary introduction to neural network technology with examples of programs]. Moscow, Saint-Petersburg, Piter Publ., 2011. 408 p. (In Russ.).

20. Brezhneva E. O., Dreizin V. E. Vybor sensorov dlya razrabotki mnogosensornogo gazoanalizatora gazovykh smesei [Selection of sensors for the development of a multisensor gas analyzer for gas mixtures]. Bezopasnost' zhiznedeyatel'nosti = Life Safety, 2011, no. 4, pp. 5-11 (In Russ.).