Research on a CNN-CBAM-Based Method for Seal Fault Diagnosis of Flow Control Valves

Hongbin Liu; Bangyao Tang; Yi Zhang; Daqin Zhang; Zhen Wang

doi:10.54691/76cfkp46

Authors

Hongbin Liu
Bangyao Tang
Yi Zhang
Daqin Zhang
Zhen Wang

DOI:

https://doi.org/10.54691/76cfkp46

Keywords:

Reciprocating Seal; Fault Diagnosis; CBAM; S-transform; Convolutional Neural Network.

Abstract

The seal of a flow control valve is a critical component in hydraulic systems. Seal failure may cause leakage, reduced energy efficiency, and unplanned shutdowns, posing severe threats to safe system operation. Traditional seal fault diagnosis methods often suffer from strong hysteresis and excessive reliance on expert experience; hence an efficient, real-time online seal monitoring technique is urgently needed. This paper proposes a seal fault diagnosis method for flow control valves based on a Convolutional Neural Network with a Convolutional Block Attention Module (CNN-CBAM). First, a reciprocating seal test rig was established, and seal models with multiple fault modes—including abrasion, aging, scuffing, and poor lubrication—were constructed. Friction force–time series data were collected. Then, time–frequency analysis methods such as the S-transform, Short-Time Fourier Transform (STFT), and Continuous Wavelet Transform (CWT) were used to convert the signals into time–frequency maps, which served as input features to the CNN-CBAM network. On this basis, we analyzed how the three time–frequency methods affect the performance of the CNN-CBAM hybrid architecture. Experimental results show that the S-transform + CNN-CBAM model achieved a test accuracy of 99.33% on 3000 samples and better preserved the frequency-adaptive characteristics of the signal. The proposed method significantly improves diagnostic accuracy and robustness, demonstrating that the CNN-CBAM hybrid architecture can effectively identify reciprocating seal faults.

Downloads

Download data is not yet available.

References

[1] Guo Dong. Parametric Design and Analysis of Downhole Flow Controller for Intelligent Wells [D]. Southwest Petroleum University, 2018.

[2] Xia Xiong. Study on Condition Monitoring and Fault Diagnosis Technology of Gas Seal Face Operating State [D]. Beijing University of Chemical Technology, 2012.

[3] Mayer E. Mechanical Seals [M]. London: Newnes-Butterworth, 1977.

[4] Min Zou, I. Green. Clearance control of a mechanical face seal [J]. Tribology Transactions, 1999, 42 (3): 535–540.

[5] Digard J., Gentile M. Experimental study on lubrication condition of low-pressure mechanical seals [C]. Proceedings of the International Gas Seal Conference, Beijing: China Machine Press, 1991.

[6] W. Anderson, R. Salant, J. Jarzynski. Ultrasonic detection of lubricating film collapse in mechanical seals [J]. Tribology Transactions, 1999, 42(4): 801–806.

[7] W. Anderson, J. Jarzynski, R. Salant. Condition monitoring for liquid-lubricated mechanical seals [J]. Tribology Transactions, 2001, 44(3): 479–483.

[8] T. Reddyhoff, R.S. Dwyer-Joyce, P. Harper. A new approach for the measurement of film thickness in liquid face seals [J]. Tribology Transactions, 2008, 51(2): 140–149.

[9] Li Jihe (ed.). Mechanical Seal Technology [M]. Chemical Industry Press, 1988.

[10] Gu Yongquan. Practical Technology of Mechanical Seals [M]. China Machine Press, 2001.

[11] Zhou Jianfeng; Gu Boqin. Reliability evaluation method of mechanical seals based on Monte Carlo [J]. Lubrication Engineering & Sealing, 2006(02): 108–110+141.

[12] Wei Long, Sun Jianjun. Reliability analysis of mechanical seals [J]. Chemical Industry and Engineering Technology, 2002(03): 20–22+3.

[13] Qing Pan, Yunlong Zeng, Yibo Li, Xuepeng Jiang, Minghui Huang. Experimental investigation of friction behaviors for double-acting hydraulic actuators with different reciprocating seals [J]. Tribology International, Volume 153.

[14] Shen Min, Song Meili, Zhang Hua. Simulation analysis of sealing performance of ZHM pneumatic combined seals for reciprocating shafts [J]. Machinery Manufacturing & Automation, 2021, 50(4): 104–108.

[15] Chong Xiang. Elastohydrodynamic lubrication simulation of reciprocating rod seal with textured rod [J]. Tribology International, Volume 158.

[16] XIANG C., GUO F., LIU X., et al. Thermo-elastohydrodynamic lubrication simulation of reciprocating rod seals under transient condition [J]. Tribology International, 2021, 153: 106603.

[17] Nawab S., Quatieri T., Lim J. Signal reconstruction from short-time Fourier transform magnitude [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1983, 31(4): 986–998.

[18] Griffin D., Lim J. Signal estimation from modified short-time Fourier transform [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1984, 32(2): 236–243.

[19] Wang Jiangping, Sun Wenli. Analysis and fault diagnosis of gear vibration signals based on wavelet packet energy spectrum [J]. Journal of Mechanical Transmission, 2011, 35(01): 55–58.

[20] Wang Ling. Pattern recognition of surface EMG signals based on wavelet packet transform [J]. Modern Electronics Technique, 2011, 34(17): 122–124+128.

[21] Xu Pan, Su Guangwei. Steganalysis based on wavelet coefficient correlation [J]. Computer Engineering and Applications, 2012, 48(28): 178–182+213.

[22] Stockwell R.G., Mansinha L., Lowe R.P. Localization of the complex spectrum: The S-transform [J]. IEEE Transactions on Signal Processing, 1996, 44(4): 998–1001. DOI: 10.1109/78.492555.

[23] Boureau Y.-L., Roux N., Bach F., et al. Ask the locals: Multi-way local pooling for image recognition. Proceedings of ICCV 2011. Barcelona, Spain, 2011: 2651–2658.

[24] Zeiler M., Fergus R. Stochastic pooling for regularization of deep convolutional neural networks. arXiv, 2013:1301.3557v1.

[25] Nair V., Hinton G.E. Rectified linear units improve restricted Boltzmann machines [C] // Proceedings of ICML’10. Haifa: International Machine Learning Society, 2010: 807–814.