Research on the Identification of Structural Size Parameters in Beam Pumping Units Using an Enhanced Particle Swarm Optimization Algorithm

Zhang Liu; Zhewei Ye

doi:10.54691/yt1pn977

Authors

Zhang Liu
Zhewei Ye

DOI:

https://doi.org/10.54691/yt1pn977

Keywords:

Beam Pumping Unit; Structural Parameters; Particle Swarm Optimization Algorithm; Parameter Identification.

Abstract

The structural size parameters (SSP) of the beam pumping unit (BPU) are crucial for kinematic analysis and other related technologies. However, early equipment often lacked data, and measuring a large number of SSPs for the BPU is costly and inefficient. To enable the automatic recognition of SSPs and reduce labor and resource investments, this paper proposes a method for recognizing the SSPs of the BPU. A kinematic model for calculating the crank angle based on beam tilt angle and SSPs is established, along with an SSP recognition model. Based on the traditional particle swarm optimization (PSO) algorithm, a comprehensive enhanced particle swarm optimization (CEPSO) algorithm is designed to solve the model. Latin hypercube sampling (LHS) is used to obtain the initial values of the SSPs, which are then substituted into the kinematic model using the measured beam tilt angle. The algorithm aims to minimize the average absolute error between the measured and calculated crank angles. The CEPSO algorithm iteratively updates the SSP values, and when the error converges to a minimum, the SSPs are obtained. Experimental results demonstrate the effectiveness of the model and the algorithm. The parameter recognition error of the CEPSO algorithm is within 5%, significantly outperforming traditional PSO. This method provides a new technological approach for measuring SSPs.

Downloads

Download data is not yet available.

References

[1] Zhang C.; Wang L.; Wu X.; Gao X. Performance analysis and design of a new-type wind-motor hybrid power pumping unit. Electric Power Systems Research. 2022, 208, 107931. https:// doi.org/ 10. 1016/j.epsr.2022.107931.

[2] Wang Q.; Zhang K.; Zhao H.; Zhang H.; Zhang L.;Yan X.; Liu P.; Fan L.; Yang Y. Yao J. A novel method for trajectory recognition and working condition diagnosis of sucker rod pumping systems based on high-resolution representation learning. Journal of Petroleum Science and Engineering. 2022, 218, 110931. https://doi.org/10.1016/j.petrol.2022.110931.

[3] Feng, Z.; Tan J.; Li Q.; Fang X. A review of beam pumping energy-saving technologies. Journal of Petroleum Exploration & Pro-duction Technology.2018, 8, 299-311. https://doi.org/ 10.1007/ s1 3202-017-0383-6.

[4] Zou J.; Wu Y.; Wang Z.; Dong S. A Novel Hybrid Method for Indirect Measurement Dynamometer Card Using Measured Motor Power in Sucker Rod Pumping System. IEEE Sensors Journal. 2022, 22,13971-80. https://doi.org/10.1109/JSEN.2022.3181621.

[5] Hao D.; Gao X. Unsupervised Fault Diagnosis of Sucker Rod Pump Using Domain Adaptation with Generated Motor Power Curves. Mathematics. 2022, 10, 1224. https://doi.org/ 10.3390/ math 10081224.

[6] Tan C.; Feng Z.; Liu X.; Fan J.; Cui W.; Sun R.; Ma Q. Review of variable speed drive technology in beam pumping units for energy-saving. Energy Reports. 2020, 6, 2676-88.https://doi.org/ 10. 1016/j.egyr.2020.09.018

[7] Cen X.; Wu X.; Wang L.; Zhen L.; Ge L. A New Model for Calculatin the Ideal Beam Counterbalance Weight for aPumping Unit. Petroleum Drilling Techniques. 2016, 44, 82-86. https://doi. org/doi: 10. 11911/syztjs.201602014.

[8] Yin J.; Sun D.; Ma H. Identification of the Four-Bar Linkage Size in a Beam Pumping Unit Based on Cubature Kalman Filter. Machines. 2022, 10, 1133. https://doi.org/10.3390/machines10121133.

[9] Zhang, K.; Xia X.; Song Z.; Zhang L.; Yang Y.; Wang J.; Yao J.; Zhang H.; Zhang Y.; Feng G; Liu C. Trajectory Recognition and Working Condition Analysis of Rod Pumping Systems Based on Pose Estimation Method with Heatmap-Free Joint Detec-tion. SPE JOURNAL. 2024, 29, 5521-5537. https://doi.org/10.2118/223095-PA.

[10] Sun J.; Huang Z.; Zhu Y.; Zhang Y. Real-time kinematic analysis of beam pumping unit: a deep learning approach. Neural Computing and Applications. 2022, 34, 7157-71. https://doi.org/ 10. 1007/ s00521-021-06783-0.

[11] Yang L.; Wang H.; Yan M. Particle Swarm Optimization-Based Model Abstraction and Explanation Generation for a Recurrent Neural Network. Algorithms. 2024, 17, 210. https://doi.org/ 10.3390/ a17050210.

[12] Bai Z.; Yu P.; Liu P.; Guo J. Linear System Identification-Oriented Optimal Tampering Attack Strategy and Implementation Based on Information Entropy with Multiple Binary Observations. Algorithms. 2024, 17, 239. https://doi.org/10.3390/a17060239.

[13] Ishaq H.; Rached D. Identification of Mechanical Parameters in Flexible Drive Systems Using Hybrid Particle Swarm Opti-mization Based on the Quasi-Newton Method. Algorithms. 2023, 16, 371. https://doi.org/ 10.3390/a16080371.

[14] Zhang J.; Li X.; Shi H. Design calculation of beam pumping unit[M]. Beijing: Petroleum Industry Press. 2005: 9-11.

[15] Zhao H.; He K.; Hu D.; Lu M. Research on the soft-sensing method of polished rod load of beam pumping unit. Chinese Journal of Scientific Instrument. 2021, 42, 160-171. https://doi.org/ 10. 19650/ j.cnki.cjsi.J2107962.

[16] Wang H.; Zheng W.; Yan J.; Wang J. On-line test of polished rod displacement of pumping unit. Oil-Gasfield Surface Engineering. 2014, 33, 41-42. https://doi.org/doi:10.3969/j.issn.1006-6896.2014. 11. 020.

[17] Wang B.; He Y.; Liu J.; Luo B. Fast parameter identification of lithium-ion batteries via classification model-assisted Bayesian optimization. Energy. 2024, 288,129667. https://doi.org/ 10.1016/ j. energy. 2023.129667.

[18] Wang L.; Li Y.; Liang Q.; Dong S.; Tang L. Greenhouse environmental data collection based on improved Chauvenet’s criterion. Transactions of the Chinese Society of Agricultural Engineering. 2015, 31, 212-217. https://doi.org/ doi: 10.3969/j.issn.1002-6819.2015.05.030.

[19] Ali R.A.; Mohammad M. Probabilistic load flow in distribution networks: An updated and comprehensive review with a new classification proposal. Electric Power Systems Research. 2023, 222, 109497. https://doi.org/10.1016/j.epsr.2023.109497.

[20] Juan R.V.; Zhang M.; Seah W. A performance study on synchronicity and neighborhood size in particle swarm optimization. Soft Computing. 2013, 17, 1019-1030. https://doi.org/ 10.1007/ s00 500-013-1015-9.

[21] Jordehi A.R. Time varying acceleration coefficients particle swarm optimisation (TVACPSO): A new optimisation algorithm for estimating parameters of PV cells and modules. Energy Conversion and Management. 2016, 129, 262-74. https://doi.org/10.1016/j.enconman.2016.09.085.

[22] Wu Z.; Luo Y.; Hu S. Optimization of jamming formation of USV offboard active decoy clusters based on an improved PSO algorithm. Defence Technology. 2024, 32, 529-540. https://doi.org/ 10.1016/ j.dt. 2023.03.017.

[23] Mahdavi S.; Rahnamayan S.; Deb K. Opposition based learning: A literature review. Swarm and Evolutionary Computation. 2018, 39, 1-23. https://doi.org/ 10.1016/j.swevo.2017.09.010.

[24] Song M.; Gu G. Research on particle swarm optimization: a review. Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on 2004. https://doi.org/ 10.1109/ ICMLC.2004.1382171.