«Equipment and technologies for oil and gas complex»

Parametric diagnostics of turbo-expanding assemblies at a gas cooling station

UDC: 622.691.4
DOI: -

Authors:

¹ Ufa State Petroleum Technological University, Ufa, Russia
² Gazprom Dobycha Urengoy, Novy Urengoy, Russia

Keywords: gas complex treatment assembly, gas cooling station, turbo-expanding assembly, active magnetic bearings, technical state assessment, machine-learning

Annotation:

The authors of the article consider the issues related to improving operational diagnostics efficiency of turbo-expanding assemblies technical state operating at gas cooling stations (GCS). The existing methods for assessing the turbo-expander assembly state are analyzed and their limitations of being used in GCS operational conditions are revealed. To enhance diagnostic accuracy, the use of machine learning methods based on the analysis of operational data is proposed. A Random Forest Regressor model was built and tested for forecasting rotor vibro-displacements and active magnetic bearings currents. A comprehensive exploratory data analysis was conducted and key correlation dependencies among technological parameters were identified. An algorithm for assemblies’ operational state assessment based on monitoring deviations of forecasted values from the baseline model was developed. Practical testing of the proposed approach allowed revealing some defect of a backup bearing, thus confirming the effectiveness of the methodology. A new indirect technique for diagnosing the state of backup bearings without disassembling the assembly was developed. The results of the study can be applied for improving technical fault detection systems of turbo-expanding assemblies.

Bibliography:

1. Yazik A.V. Sistemy i sredstva okhlazhdeniya prirodnogo gaza. – M.: Nedra, 1986. – 200 s.
2. Opyt i perspektivy primeneniya turbodetandernykh agregatov na promyslovykh tekhnologicheskikh ob"ektakh gazovoy promyshlennosti Rossii / V.A. Khetagurov, P.P. Slugin, M.A. Vorontsov, A.N. Kubanov // Gazovaya promyshlennost'. – 2018. – № 11(777). – S. 14–22.
3. Povyshenie kachestva remonta turbodetandernykh agregatov, ustanovlennykh na Bovanenkovskom NGKM / S.N. Men'shikov, S.S. Kil'diyarov, V.V. Moiseev [i dr.] // Gazovaya promyshlennost'. – 2018. – № S3(773). – S. 28–33.
4. Tekhnologicheskiy analiz raboty turbokholodil'noy tekhniki na nachal'nom etape ekspluatatsii UKPG-2 Bovanenkovskogo NGKM / A.N. Kubanov, M.A. Vorontsov, D.M. Fedulov, V.Yu. Glazunov // Nauchno-tekhnicheskiy sbornik Vesti gazovoy nauki. – 2013. – № 4(15). – S. 84–89.
5. Smol'nikov V.O., Godovskiy D.A. Metody otsenki effektivnosti raboty turbodetandernykh agregatov na stantsiyakh okhlazhdeniya gaza na ob"ektakh dobychi // Transport i khranenie nefteproduktov i uglevodorodnogo syr'ya. – 2024. – № 1-2. – S. 32–36. – DOI: 10.24412/0131-4270-2024-1-2-32-36
6. Hu Yefa, Taha O.W., Yang Kezhen. Fault Detection in Active Magnetic Bearings Using Digital Twin Technology // Applied Sciences. – 2024. – Vol. 14, Issue 4. – Article 1384. – DOI: 10.3390/app14041384
7. Convolutional Neural Network for Electrical Fault Recognition in Active Magnetic Bearing Systems / G. Donati, M. Basso, G.A. Manduzio [et al.] // Sensors. – 2023. – Vol. 23, Issue 16. – Article 7023. – DOI: 10.3390/s23167023
8. Yan Xunshi, Zhang Chen-an, Yang Liu. Multi-branch convolutional neural network with generalized shaft orbit for fault diagnosis of active magnetic bearing-rotor system // Measurement. – 2021. – Vol. 171, Issue 9. – Article 108778. – DOI: 10.1016/j.measurement.2020.108778
9. Multi-Domain Entropy-Random Forest Method for the Fusion Diagnosis of Inter-Shaft Bearing Faults with Acoustic Emission Signals / Tian Jing, Liu Lili, Zhang Fengling [et al.] // Entropy. – 2020. – Vol. 22, Issue 1. – Article 57. – DOI: 10.3390/e22010057
10. Prediction of Gas Turbine Trip: A Novel Methodology Based on Random Forest Models / E. Losi, M. Venturini, L. Manservigi [et al.] // Journal of Engineering for Gas Turbines and Power. – 2022. – Vol. 144, Issue 3. – Article 031025. – DOI: 10.1115/1.4053194
11. Identifikatsiya chastichnykh otkazov v gazotransportnoy sisteme s ispol'zovaniem neyrosetevogo algoritma / Yu.G. Golubev, M.G. Sukharev, R.V. Samoylov, I.A. Luzinov // Avtomatizatsiya i informatizatsiya TEK. – 2025. – № 4(621). – S. 32–41.
12. Postroenie prognoznykh modeley na osnove iskusstvennogo intellekta dlya resheniya zadachi predskazaniya poyavleniya defektov truboprovodov / A.V. Shibanov, D.S. Pochikeev, F.A. Kochubey [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 10(603). – S. 38–47. – DOI: 10.33285/2782-604X-2023-10(603)-38-47
13. Lyapichev D.M., Andreev D.I., Admakin M.M. Primenenie mashinnogo obucheniya v diagnosticheskoy modeli sistemy monitoringa tekhnologicheskikh truboprovodov // Trudy Rossiyskogo gosudarstvennogo universiteta nefti i gaza imeni I.M. Gubkina. – 2025. – № 1(318). – S. 140–151.
14. Algoritmy komp'yuternogo zreniya i iskusstvennogo intellekta dlya detektsii defektov na energeticheskom oborudovanii i ob"ektakh truboprovodnogo transporta / A.I. Velichko, V.A. Zubakin, M.D. Tregubenko, K.N. Yusupov // Oborudovanie i tekhnologii dlya neftegazovogo kompleksa. – 2024. – № 1(139). – S. 71–79.
15. Ivanov E.S. Obespechenie effektivnosti raboty kompressornykh stantsiy v usloviyakh snizhennoy zagruzki magistral'nykh gazoprovodov: dis. … kand. tekhn. nauk: 25.00.19. – Ufa, 2016. – 189 s.