Submersible Screw Pump Fault Diagnosis Method Based on a Probabilistic Neural Network

Kangxing Dong; Qiaoer Li; Ziheng Zhang; Minzheng Jiang; Shufan Xu

doi:10.6180/jase.202212_25(6).0002

Submersible Screw Pump Fault Diagnosis Method Based on a Probabilistic Neural Network

Kangxing Dong¹, Qiaoer Li¹, Ziheng Zhang¹, Minzheng Jiang This email address is being protected from spambots. You need JavaScript enabled to view it.¹, and Shufan Xu²

¹School of Mechanical Science and Engineering, Northeast Petroleum University, Daqing 163318, China
²No.2 Oil Provide Factory of Daqing Oilfield Co., Ltd., Daqing 163001, China

Received: September 3, 2021
Accepted: December 28, 2021
Publication Date: January 26, 2022

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202212_25(6).0002

ABSTRACT

The core components of submersible screw pump are concentrated underground, so it is difficult to judge the fault timely and accurately. Based on this, this paper proposes a fault diagnosis method of submersible screw pump based on probabilistic neural network (PNN), and develops the corresponding fault diagnosis system. Wavelet packet theory is used to decompose and reconstruct the active power signal of submersible screw pump, extract the main fault information contained in the power signal, and construct the fault feature vector of submersible screw pump combined with the parameters such as output, oil pressure, casing pressure and dynamic liquid level. Based on the historical data of submersible screw pump, a probabilistic neural network model is constructed. The mapping relationship between fault feature vector and fault form is obtained through the historical data training model, so as to judge the fault form to be logged according to the fault feature vector to be logged. 142 groups of fault data are collected to train the model and verify the accuracy of the diagnosis model and the test shows that the accuracy of the diagnosis model is 90.5%. The test results show that the fault diagnosis method of submersible screw pump based on PNN can timely and accurately judge the fault type of submersible screw pump and reduce the economic loss of oilfield production.

Keywords: fault diagnosis; probabilistic neural network; submersible screw pump; wavelet packet

REFERENCES

[1] H. Liu, H. Hao, L. Wang, and G. Cao, (2015) “Current Situation and Development Trend of Artificial Lift Technology" Acta Petrolei Sinica 36(11): 1441–1448.
[2] S. Fakher, A. Khlaifat, M. E. Hossain, and H. Nameer, (2021) “A comprehensive review of sucker rod pumps’ components, diagnostics, mathematical models, and common failures and mitigations" Journal of Petroleum Exploration and Production Technology 11(10): 3815–3839. DOI: 10.1007/s13202-021-01270-7.
[3] Z. Hao, S. Zhu, X. Pei, P. Huang, Z. Tong, B. Wang, and L. I. Deyin, (2019) “Submersible direct drive progressing cavity pump rodless lifting technology" Petroleum Exploration and Development 46(3): 621–628. DOI: 10.1016/S1876-3804(19)60042-X.
[4] K. Peng, (2016) “Fault diagnosis of electric submersible pump based on BP neural network" Journal of Petrochemical Universities 29(1): 76–77. DOI: 10.3969/j.issn.1006-396X.2016.01.015.
[5] Closed Loop Speed Control System of ESPCP with Capillary Tube. Day 1 Tue, October 17, 2017. SPE Asia Pacific Oil and Gas Conference and Exhibition. 2017. DOI: 10.2118/186261-MS.
[6] Field Trial Analyzing of Rodless PCP Technology: Problems, Improvements and Results. All Days. SPE Asia Pacific Oil and Gas Conference and Exhibition. DOI: 10.2118/182251-MS.
[7] D. Worth, E. Al-Safran, A. Choudhuri, and A. Al-Jasmi, (2019) “Assessment of artificial lift methods for a heavy oil field in Kuwait" Journal of Petroleum Science and Engineering 180: 835–843. DOI: 10.1016/j.petrol.2019.06.012.
[8] G. Zhu, (2014) “Discussion on the Diagnosis Method of Screw Pump Well Pump Condition" Inner Mongolia Petrochemical Industry 40(14): 86–87.
[9] L. Zhang, Y. Zhong, Y. Yuan, J. Li, and X. Qin, (2019) “The Method of Transforming Customer Demand into Engineering CharacteristicWeight in Green Design Based on Data Mining" China Mechanical Engineering 32(2): 174–182.
[10] J. Zhu, Y. Gao, and X. Yan, (2008) “Fault Diagnosis Method of Screw Pump Well Based on BP Neural Network" China Petroleum Machinery 36(1): 42–44.
[11] M. Li, P. He, and C. Meng, (2010) “Intelligent Integrated Fault Diagnosis Expert System of Screw Pump Well" Journal of Harbin Institute of Technology 42(7): 1038–1041.
[12] J. Xue, M. Li, G. Zhang, G. Yue, and N. Jiang, (2013) “Research on Fault Diagnosis Technology of Screw Pump Well Based on BP Neural Network" Journal of Xi’an Shiyou University 28(3): 74–77.
[13] S. Zhu, Z. Hao, Q. Wang, L. Zhang, and Z. Shen, (2017) “Research on Monitoring System of Downhole Working Condition of Submersible Screw Pump" China Petroleum Machinery 45(9): 92–96.
[14] M. Jiang, T. Cheng, K. Dong, S. Xu, and Y. Geng, (2020) “Fault diagnosis method of submersible screw pump based on random forest" PLOS ONE 15: DOI: 10.1371/journal.pone.0242458.