Model of predicting the readiness class of thermochemical gas alarm sensors for fire and explosion prevention

Introduction. The relevance of the problem considered in the paper is in the need to improve the automation and intellectualization of organizational management of fire and explosion safety at the facilities of the fuel and energy complex. Zero drift due to the influence of a number of parameters in thermochemical sensors reduces their sensitivity, which requires the development of new approaches in the implementation of their maintenance. The sensor readiness class prediction model, based on a convolutional neural network (CNN), allows to adjust the established decision-making process, preventing dangerous situations at early stages of development.

Objective. To increase the efficiency of decision makers (DM) in planning the work of teams performing diagnostics and maintenance of auxiliary equipment used, among other things, to ensure fire safety (FS).

Methods. To calculate the classification values when predicting the readiness class of gas alarm sensors, a strategic planning method based on the importance of features (dynamic strategic planning using mathematical programming) was used. According to it, the readiness class was defined as the sum of the binary values of the features multiplied by the normalized value of their importance.

Results and discussion. To carry out calculations and evaluate the results of the CNN application, the authors developed a programme in the Python programming language. It was used to generate a common data set from which training and test sets were selected in a ratio of 9:1. After their formation, the CNN was trained. Testing showed that the DM can predict the readiness class of gas alarm sensors with a probability of 89 %.

Conclusions. The CNN presented in the paper allows to increase the efficiency of the DM work when planning the work of teams performing diagnostics and technical maintenance of auxiliary equipment for FS. The principle of operation of this CNN can be used to solve other similar planning and management tasks.

1. Yusupova D.M. Aspects of the introduction of artificial intelligence into the digital transformation of the economy and into electronic government systems. Economics and Society. 2023; 4(107-2):801-815. URL: www.iupr.ru (rus).

2. Shkodyrev V.P. Evolution in cybernetics: knowledge-based management. System analysis in design and management. Collection of scientific papers of the XXVI International Scientific and Practical Conference. In 3 parts. Saint Petersburg, 2023; 51-58. DOI: 10.18720/SPBPU/2/id23-34 (rus).

3. Topolsky N.G. Fundamentals of automated fire and explosion safety systems for facilities. Moscow, MIPB of the Ministry of Internal Affairs of Russia, 1997; 164. (rus).

4. Abrosimov A.A., Topolsky N.G., Fedorov A.V. Automated fire and explosion safety systems for oil refineries. Moscow, MIPB of the Ministry of Internal Affairs of Russia, 1999; 244. (rus).

5. Fedorov A.V., Gaplaev A.A.-B., Topolsky N.G., Samarin I.V. Automation of control and testing of fire protection control systems for fuel and energy complex facilities / Ed. by A.V. Fedorov. Moscow, Gubkin Russian State University of Oil and Gas (NRU), Academy of GPS of the Ministry of Emergency Situations of Russia, 2019; 183. (rus).

6. Bykova V.N., Kim E., Gadzhialiev M.R., Musienko V.O., Orujev A.O., Turovskaya E.A. The use of a digital double in the oil and gas industry. Actual problems of oil and gas. 2020; 1(28):8. DOI: 10.29222/ipng.2078-5712.2020-28.art8 (rus).

7. Butuzov S.Yu., Pranov B.M., Prus Yu.V., Semikov V.L., Yakovlev O.V. A model for assessing the stability of automated fire and explosion safety systems. Pozharovzryvobezopasnost/Fire and explosion safety. 2017; 26(6):14-20. DOI: 10.18322/PVB.2017.26.11.14-20. EDN YMCOHG. (rus).

8. Ablaev R.R., Abramova L.S., Ablaev A.R. Import substitution and restructuring of export flows in the field of high-tech production. Moscow Economic Journal. 2023; 3:216-229. DOI: 10.55186/2413046X_2023_8_3_130 (rus).

9. Krylov A.A. Study of the instability of the zero drift of MEMS gyroscopes and ways of accounting for it during calibration. Proceedings of Tula State University. Technical Sciences. 2020; 1:64-69. (rus).

10. Abdullah Al-hammadi S.R.A., Liang Y. A Review Study on Methane Gas Sensors. North American Academic Research. 2021; 4(5):303-309. DOI: 10.5281/zenodo.4884736

11. Gubenko A.M. Approaches to the use of artificial intelligence technologies for solving automated control problems in complex organizational and technical systems. Technology of communication tools. 2023; 4(164):66-71. DOI: 10.24412/­2782-2141-2023-4-66-71 (rus).

12. Kharitonova Yu.S., Savina V.S., Pagnini F. Bias of artificial intelligence algorithms: issues of ethics and law. Bulletin of the Perm University. Legal sciences. 2021; 53:488-515. DOI: 10.17072/1995-4190-2021-53-488-515. EDN EUKCPY. (rus).

13. Ikram Ben Ahmed1, Wael Ouarda, Chokri Ben Amar, Khouloud Boukadi. DEES-breast: deep end-to-end system for an early breast cancer classification. Evolving Systems. 2024; 15:1845-1863. DOI: 10.1007/s12530-024-09582-9

14. Sourour Brahimi, Ibrahimi Soumaya, Chokri Ben Amar. An object recognition method based on deep BCNN with Reinforced Dense Blocks, Conference : 2023 International Conference on Cyberworlds (CW). October 2023. DOI: 10.1109/CW58918.2023.00044

15. Rim Fakhfakh, Anis Ben Ammar, Chokri Ben Amar. Deep Learning-Based Recommendation: Current Issues and Challenges. (IJACSA) International Journal of Advanced Computer Science and Applications. 2017; 8(12). DOI: 10.14569/IJACSA.2017.081209

16. Zeineb Daoud, Amal Ben Hamida, Chokri Ben Amar. Fire object detection and tracking based on deep learning model and Kalman filter. Arabian Journal for Science and Engineering. 2023; 49(6). DOI: 10.1007/s13369-023-08127-7

17. Velibor Božić. Machine learning vs deep learning. March 2024. DOI: 10.13140/RG.2.2.16632.21762

18. Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela et al. Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artificial Intelligence Review. 2023; 56(11):­­13521-13617. DOI: 10.1007/s10462-023-10466-8

19. Topolsky N.G., Samarin I.V., Strogonov A.Yu. Methodology for assessing the readiness for operation of first-level information security equipment at fuel and energy complex facilities in special conditions. Pozharovzryvobezopasnost/Fire and explosion safety. 2019; 28(1):35-46. DOI: 10.18322/PVB.2019.28.01.35-46. EDN QHUJWX. (rus).

20. Topolsky N.G., Samarin I.V., Stroganov A.Yu. A model for assessing integrated safety in automated process control systems using fire detectors diagnostics to build an automated fire and explosion safety management support system. Pozharovzryvobezopasnost/Fire and explosion safety. 2018; 27(11):15-22. DOI: 10.18322/PVB.2018.27.11.15-22 (rus).