Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 16;23(16):7211.
doi: 10.3390/s23167211.

Direct-Drive Electro-Hydraulic Servo Valve Performance Characteristics Prediction Based on Big Data and Neural Networks

Juncheng Mi  1 , Jin Yu  1 , Guoqin Huang  1
Affiliations

Direct-Drive Electro-Hydraulic Servo Valve Performance Characteristics Prediction Based on Big Data and Neural Networks

Juncheng Mi et al. Sensors (Basel). .

Abstract

Direct-drive electro-hydraulic servo valves play a key role in aerospace control systems, and their operational stability and safety reliability are crucial to the safety, stability, and efficiency of the entire control system. Based on the prediction of the performance change of the servo valve and the resulting judgement and prediction of its life, this can effectively avoid serious accidents and economic losses caused by failure due to performance degradation in the work. On the basis of existing research, factors such as opening, oil contamination, and pressure difference are used as prerequisites for the operation of direct-drive electro-hydraulic servo valves. In addition to the current research on pressure gain and leakage, the performance parameters of servo valves, such as overlap, threshold, and symmetry, are also expanded and selected as research objects, combined with pressure design servo valve performance degradation experiments for testing instruments such as flow and position sensors, and data are obtained on changes in various performance parameters. The experimental data are analyzed and a prediction model is built to predict the performance parameters of the servo valve by combining the existing popular neural networks, and the prediction error is calculated to verify the accuracy and validity of the model. The experimental results indicate that as the working time progresses, the degree of erosion and wear on the valve core and valve sleeve of the servo valve increases. Overall, it has been observed that the performance parameters of the servo valve show a slow trend of change under different working conditions, and the rate of change is generally higher under high pollution (level 9) conditions than under other conditions. The prediction results indicate that the predicted values of various performance parameters of the servo valve by the prediction model are lower than 0.2% compared to the experimental test set data. By comparing the two dimensions of the accuracy and prediction trend, this model meets industrial needs and outperforms deep learning algorithm models such as the exponential smoothing algorithm and ARIMA model. The experiments and results of this study provide theoretical support for the life prediction model of servo valves based on neural networks and machine learning in artificial intelligence, and provide a reference for the development of direct-drive electro-hydraulic servo valves in aerospace and other industrial fields for use and failure standards.

Keywords: direct-drive electrohydraulic servo valves; erosive wear; machine learning; neural networks; performance degradation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Schematic diagram of the servo valve performance degradation experiment: (1) tank; (2) hydraulic pump; (3) temperature gauge; (4) filter; (5) relief valve; (6) pressure gauge; (7) measured direct-drive electro-hydraulic flow servo valve; (8) throttle valve; (9) stop valve; (10) flowmeter.
Figure 2
Figure 2
Layout diagram of performance degradation experiment: (a) performance degradation test bench; (b) servo valves (DDV valves); (c) servo valves and pressure sensors; (d) flow sensors; (e) pressure gauge.
Figure 3
Figure 3
Particle counter.
Figure 4
Figure 4
Automated test equipment.
Figure 5
Figure 5
Data information missing map: (a) overlapping, (b) threshold, and (c) symmetry.
Figure 6
Figure 6
Experimental data trend chart: (a) overlap; (b) doorstill; (c) symmetry.
Figure 6
Figure 6
Experimental data trend chart: (a) overlap; (b) doorstill; (c) symmetry.
Figure 7
Figure 7
LSTM neural network structure diagram.
Figure 8
Figure 8
Framework diagram of LSTM model with overlap, threshold, and symmetry.
Figure 9
Figure 9
Framework diagram of the LSTM model for pressure gain and leakage.
Figure 10
Figure 10
Process framework diagram.
Figure 11
Figure 11
Training iteration log plots: (a) overlap; (b) thresholds; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 11
Figure 11
Training iteration log plots: (a) overlap; (b) thresholds; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 12
Figure 12
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 2: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 13
Figure 13
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 4: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 13
Figure 13
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 4: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 14
Figure 14
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 6: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 15
Figure 15
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 8: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 15
Figure 15
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 8: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 16
Figure 16
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 10: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 17
Figure 17
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 12: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 17
Figure 17
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 12: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 18
Figure 18
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 14: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 19
Figure 19
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 16: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
Figure 19
Figure 19
Prediction fitting diagram for overlap, threshold, symmetry, pressure gain, and leakage under condition 16: (a) overlap; (b) threshold; (c) symmetry; (d) pressure gain; (e) leakage.
See this image and copyright information in PMC

References

    1. Huang Y. Discussion on the Teaching Reform of <Sensor Technology and Application> in Local Application-oriented Undergraduate University. Off. Informatiz. 2022;27:44–46. (In Chinese)
    1. Chen Y. The Initial Design Concept and Applications for the Electrohydraulic Servovalve. Mach. Tool Hydraul. 2019;47:114–118. doi: 10.3969/j.issn.1001-3881.2019.09.024. (In Chinese) - DOI
    1. Wang H.-B., Huang Z., Liu Z., Gao B., Xv Y., Yu B. Life analysis of electro—Hydraulic servo valve based on FMMEA. J. Mech. Electr. Eng. 2022;39:1132–1137. doi: 10.3969/j.issn.1001-4551.2022.08.015. (In Chinese) - DOI
    1. Hu Q., He Q., Cao L. IHHO-LSSVM Rolling Bearing Life Prediction Model Treated by EEMD-KPCA. J. Huaqiao Univ. (Nat. Sci.) 2022;43:145–153. doi: 10.11830/ISSN.1000-5013.202012025. (In Chinese) - DOI
    1. Zhang Y., Tang B., Xiong P. Rolling element bearing life prediction based on multi-scale mutation particle swarm optimized multi-kernel least square support vector machine. Chin. J. Sci. Instrum. 2016;37:2489–2496. doi: 10.19650/j.cnki.cjsi.2016.11.011. (In Chinese) - DOI

LinkOut - more resources