Abstract
The article presents a method of mode control based on neural network fault diagnosis and evaluation of the technical condition of electrically driven gas pumping unit for subsystems for the diagnostic determination of the coefficient that takes into account the manifestation of the fault on the basis of the neural networks of the Kohonen type. The coefficients taking into account the manifestation of faults to specific subsystems allow us to identify and assess faults. The graphs of the results of the evaluation of the technical condition of electrically driven gas-pumping unit are provided with respect to the identified faults in sub-systems (lubrication system, supercharger, engine (stator winding), the motor (mechanical defects). The proposed system improves the accuracy and completeness of diagnosis for electrically driven gas-pumping unit by using neural networks of Kohonen type.
Keywords
Electrically driven gas pumping unit, control system modes, assessment of the technical condition, engine diagnostics, Kohonen neural network, factor existence of these faults.
1. Rasporyazhenie pravitelstva RF «Koncepciya federalnoj sistemy monitoringa kriticheski vazhnyh obyektov i (ili) potencialno opasnyh obyektov infrastruktury RF i opasnyh gruzov» [Order of RF Government “The concept of the federal monitoring system of critical objects or hazardous facilities of the Russian Federation and dangerous cargo” (signed on August 27, 2005, no. 1314-р.)]. Moscow, 2005. (In Russian)
2. PP RF «Ob utverzhdenii tekhnicheskogo reglamenta o bezopasnosti setej gazoraspredeleniya i gazopotrebleniya» ot 29.10.2010 N 870 (red. ot 20.01.2017) [PP of RF «Adoption of technical regulations about the safety of gas distribution and gas consumption networks» authorized on 29.10.2010 N 870 (as in the force on 20.01.2017)]. Moscow, 2017. (In Russian)
3. STO Gazprom 2-3.5-032-2005. Polozhenie po organizacii i provedeniyu kontrolya za soblyudeniem trebovanij promyshlennoj bezopasnosti i obespecheniem rabotosposobnosti obyektov edinoj sistemy gazosnabzheniya OAO «Gazprom» [The company standard concerning the process of monitoring of meeting the industrial safety requirements and the performance of objects included into the unified gas supply system of the OJSC “Gasprom” (authorized on May 27, 2005, no. 88)]. Moscow, 2005. (In Russian)
4. STO Gazprom 18000.1-001-2014. Edinaya sistema upravleniya ohranoj truda i promyshlennoj bezopasnostyu v OAO «Gazprom» [United system of labor safety and industrial safety management at the OJSC “Gazprom” (authorized on July 28, 2014, no. 358)]. Moscow, 2005.
5. Order of the government of the RF «Ob Energeticheskoj strategii Rossii na period do 2030 goda» [Energy Strategy of Russia up to 2030 (signed on 13.11.2009, no. 1715-r)]. Moscow, 2009. (In Russian)
6. Puzhajlo A.F. Diagnostika oborudovaniya kompressornyh stancij [Diagnostics of gas compressor station equipment]: monograph. N. Novgorod: Istok, 2013. 299 p. (In Russian)
7. Kryukov O.V., Serebryakov A.V. Analysis of forecasting results of the technical states of electrical gas compressor units. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes]. 2016, no. 1(30). pp. 39–44. https://doi.org/ 10.18503/2311-8318-2016-1(30)-39-44. (In Russian)
8. Rubcova I.E., Babichev S.A. Control and monitoring of electric drives of gas compressor units in terms of stochastic disturbances. Aktualnye voprosy avto-matizirovannogo ehlektroprivoda [Topical issues of automated electric drive]. 2014, no. 3(2), pp. 209–215. (In Russian)
9. Babanova I.S. Application of an artificial neural network to predict temperature at the exit of the air cooler unit of gas for a gas compressor station of the main gas pipeline. Mezhdunarodnyj nauchno-issledovatelskij zhurnal [International research journal]. 2016, no. 3(45), part 2, pp. 6–9. https://doi.org/10.18454/IRJ.2016.45.090. (In Russian)
10. Ustinov D.A., Babanova I.S. Justification of the choice of the electricity tariff for consumers taking into account controlled load consumers. Promyshlennaya ehnergetika [Industrial energy]. Moscow, 2016, no. 11, pp. 9–16. (In Russian)
11. Abramovich B.N., Babanova I.S. Forecasting system of energy consumption using an artificial neural network. Gornye nauki i tekhnologii [Mining science and technology]. Moscow, MISiS, 2016, no. 2, pp. 66–77. (In Russian)
12. Babanova I.S. Ustinov D.A. Development of model of an artificial neural network to control and forecast the power consumption modes of mining enterprises. Ehlektroehnergetika glazami molodezhi – 2016: materialy VII Mezhdunarodnoj nauchno-tekhnicheskoj konferencii, 19–23 sentyabrya 2016, Kazan' [Electrical engineering from the point of view of the youth – 2016: proceedings of the VII international scientific and technical conference, September 19–23, 2016, Kazan]. Kazan: Kazan state energy university, 2016, iss. 3, vol. 2, pp. 47–50. (In Russian)
13. Babanova I.S. Application of an artificial neural network to predict the temperature of exit temperature of the air-cooling gas unit for the gas compressor station of the main gas pipeline. Mezhdunarodnyj nauchno-issledovatel'skij zhurnal [International research journal]. 2016, no. 3(45), part 2, pp. 6–9. https://doi.org/10.18454/IRJ.2016.45.090. (In Russian)
14. Babanova I.S. Development of strategic planning of electrical power system on the basis of comparative analysis of different forecasting methods of electrical energy consumption. Operativnoe upravlenie v elektroehnergetike [Operational management in power industry]. 2017, vol. 3, pp. 48–57. (In Russian)
15. Abramovich B.N., Babanova I.S. Application of artificial neural networks in the teaching process of electrical engineering courses. Sovremennye obrazovatelnye tekhnologii v prepodavanii estestvenno-nauchnyh i gumanitarnyh disciplin: sbornik nauchnykh trudov II Mezhdunarodnoi nauchno-metodicheskoi konferentsii, 09–10 aprelya 2015 [Modern educational technologies in teaching of natural Sciences and the Humanities: collection of scientific papers of the II international scientific conference, April 09–10, 2015]. Sankt-Petersburg, 2015, pp. 229–234. (In Russian)
16. A. Blinov, Y. Zhukovsky. Integrated system of safety and performance efficiency assessment of electromechanical equipment. Journal of Fundamental and Applied Sciences, 2016, 8(2S), 2185–2196.
17. Y. Zhukovskiy and N. Koteleva. A method of definition of life-cycle resources of electromechanical equipment. IOP Conf. Series: Materials Science and Engineering. 124(2016) 012172.
18. Kozyaruk A.E., Zhukovskij Yu.L. Maintenance system of electromechanical equipment and machines by the actual state. Gornoe oborudovanie i ehlektromekhanika [Mining equipment and electrical engineering]. 2014, no. 10, pp. 8–14. (In Russian)
19. Y. Zhukovskiy and N. Koteleva. Automated system for definition of life-cycle resources of electromechanical equipment IOP Conf. Series: Materials Science and Engineering. 177(2017)012014.
20. Korolev N.A. Diagnostics system of an AC electric motor based on the complex parameter analysis. Aktual'nye problemy povysheniya ehffek-tivnosti i bezopasnosti ehkspluatacii gornoshahtnogo i neftepromyslovogo oborudovaniya [Urgent problems of improving the efficiency and safe operation of oil mining equipment]. 2016, no. 1, pp. 236–242. (In Russian)
21. N.A. Korolev and S.V. Solovev. AC motor diagnostics system based on complex parametric analysis IOP Conference Series: Materials Science and Engineering; Tomsk; 2016; Vol. 177. conference 1. Available at: http://iopscience.iop.org/1757-899X/177/1/012007.
22. Zarickij S.P. Diagnostika gazoperekachivayushchih agregatov [Diagnostics of gas compressor units]. Moscow, Gulibkin University of oil and gas, 2003. 598 p.
23. Antropov P.G., Dolinina O.N., Shvarc A.Yu. A method of fault diagnostics of gas compressor units using hybrid intelligent systems. Vestnik Samarskogo gosudarstvennogo aehrokosmi-cheskogo universiteta [Vestnik of Samara state air-space university]. 2014, no. 5(47), pp. 75–84. (In Russian)