The anomaly detection of axial piston pumps is essential to ensure the reliable and safe operation of hydraulic systems. Discharge pressure ripple is an inherent property of axial piston pumps, which exhibits a periodic waveform over each cycle under normal conditions. This work proposes an unsupervised learning method to detect wear faults in axial piston pumps by the similarity of pressure ripple signals. Specifically, the healthy discharge pressure ripples are transformed into similarity matrices to train an unsupervised network comprising a convolutional encoder and a deconvolutional decoder. The reconstruction error of similarity matrix under normal conditions determines the anomaly threshold. The anomaly detection of axial piston pumps is performed by comparing the reconstruction errors of testing samples with the predefined anomaly threshold. A test rig was built to carry out experiments of an actual axial piston pump under eight operating conditions in both normal and abnormal scenarios. The experimental results show that the proposed method can effectively detect the anomaly behavior due to wear faults in the axial piston pump with an average accuracy rate of more than 90%.
ZhaoJFuJLiY, et al. Flow characteristics of integrated motor-pump assembly with phosphate ester medium for aerospace electro-hydrostatic actuators. Chin J Aeronaut2023; 36(9): 392–407.
2.
TongZWuSTongS, et al. Energy-saving technologies for construction machinery: a review of electro-hydraulic pump-valve coordinated system. J Zhejiang Univ Sci A2020; 21(5): 331–349.
3.
SkaareBHörnstenBNielsenFG. Modeling, simulation and control of a wind turbine with a hydraulic transmission system. Wind Energy2013; 16(8): 1259–1276.
4.
LuoSChengMDingR, et al. Human–robot shared control based on locally weighted intent prediction for a teleoperated hydraulic manipulator system. IEEE/ASME Trans Mechatron2022; 27(6): 4462–4474.
5.
ChaoQXuZTaoJ, et al. Capped piston: a promising design to reduce compressibility effects, pressure ripple and cavitation for high-speed and high-pressure axial piston pumps. Alex Eng J2023; 62: 509–521.
6.
SaracyakupogluT. A comprehensive fracture research of an aircraft swash-plate pump. Eng Fail Anal2022; 140: 106569.
7.
ChaoQZhangJXuB, et al. A review of high-speed electro-hydrostatic actuator pumps in aerospace applications: challenges and solutions. J Mech Des2019; 141(5): 050801.
8.
ChaoQXuZShaoY, et al. Hybrid model-driven and data-driven approach for the health assessment of axial piston pumps. Int J Hydromechatron2023; 6(1): 76–92.
9.
KoniecznyJStojekJ. Use of the k-nearest neighbour classifier in wear condition classification of a positive displacement pump. Sensors2021; 21(18): 6247.
10.
XiaSXiaYXiangJ. Piston wear detection and feature selection based on vibration signals using the improved spare support vector machine for axial piston pumps. Materials2022; 15(23): 8504.
11.
KellerNSciancaleporeAVaccaA. Demonstrating a condition monitoring process for axial piston pumps with damaged valve plates. Int J Fluid Power2022; 23(2): 205–236.
12.
LanYHuJHuangJ, et al. Fault diagnosis on slipper abrasion of axial piston pump based on extreme learning machine. Measurement2018; 124: 378–385.
13.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
14.
LiuDShiJLiaoZ, et al. Prognostics and health management for electromechanical system: a review. J Adv Manuf Sci Technol2022; 2(4): 2022015.
15.
WangSXiangJZhongY, et al. A data indicator-based deep belief networks to detect multiple faults in axial piston pumps. Mech Syst Signal Process2018; 112: 154–170.
16.
ChaoQTaoJWeiX, et al. Cavitation intensity recognition for high-speed axial piston pumps using 1-D convolutional neural networks with multi-channel inputs of vibration signals. Alex Eng J2020; 59(6): 4463–4473.
17.
JiangWLiZZhangS, et al. Hydraulic pump fault diagnosis method based on EWT decomposition denoising and deep learning on cloud platform. Shock Vib2021; 2021: 18.
18.
TangSZhuYYuanS. An improved convolutional neural network with an adaptable learning rate towards multi-signal fault diagnosis of hydraulic piston pump. Adv Eng Inform2021; 50: 101406.
19.
TangSZhuYYuanS. A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images. Adv Eng Inform2022; 52: 101554.
20.
ZhuYTangSYuanS. Multiple-signal defect identification of hydraulic pump using an adaptive normalized model and S transform. Eng Appl Artif Intell2023; 124: 106548.
21.
ChaoQGaoHTaoJ, et al. Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals. Sci China Technol Sci2022; 65(2): 470–480.
22.
HeYTangHRenY, et al. A deep multi-signal fusion adversarial model based transfer learning and residual network for axial piston pump fault diagnosis. Measurement2022; 192: 110889.
23.
JiangWWangCZouJ, et al. Application of deep learning in fault diagnosis of rotating machinery. Processes2021; 9(6): 919.
24.
ZhouYKumarAParkashC, et al. A novel entropy-based sparsity measure for prognosis of bearing defects and development of a sparsogram to select sensitive filtering band of an axial piston pump. Measurement2022; 203: 111997.
25.
TangHYangWWangZ. A model-based method for leakage detection of piston pump under variable load condition. IEEE Access2019; 7: 99771–99781.
26.
XiangJZhongY. A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Appl Sci2016; 6(12): 414.
27.
GaoYLiuXXiangJ. Fault detection in gears using fault samples enlarged by a combination of numerical simulation and a generative adversarial network. IEEE/ASME Trans Mechatron2022; 27(5): 3798–3805.
28.
LouYKumarAXiangJ. Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. IEEE Trans Instrum Meas2022; 71: 3514709.
29.
LiuCGrylliasK. Simulation-driven domain adaptation for rolling element bearing fault diagnosis. IEEE Trans Ind Inform2022; 18(9): 5760–5770.
30.
Maradey LázaroJGBorrás PinillaC. A methodology for detection of wear in hydraulic axial piston pumps. Int J Interact Des Manuf2020; 14: 1103–1119.
31.
CasoliPPastoriMScolariF, et al. A vibration signal-based method for fault identification and classification in hydraulic axial piston pumps. Energies2019; 12(5): 953.
32.
KellerNSciancaleporeAVaccaA. Condition monitoring of an axial piston pump on a mini excavator. Int J Fluid Power2023; 24(2): 171–206.
33.
LinJWangYZhouS, et al. Simulation and experimental analysis of pressure pulsation characteristics of pump source fluid. Appl Sci2021; 11(20): 9559.
34.
ZhaoCDongHWeiX, et al. Experimental study on the pressure distribution of piston/cylinder lubricating interface based on time domain location method. Measurement2024; 231: 114595.
35.
PetterssonMWeddfeltKPalmbergJ. Methods of reducing flow ripple from fluid power piston pumps–a theoretical approach. In: 1991 International Off-highway & Powerplant Congress & Exposition, Milwaukee, USA, 9–12 September 1991, pp.158–167. Warrendale, PA: SAE International.
36.
YuanXWangWZhuX, et al. Theoretical model of dynamic bulk modulus for aerated hydraulic fluid. Chin J Mech Eng2022; 35(1): 121.
37.
YangMEdgeKJohnstonD. Condition monitoring and fault diagnosis for vane pumps using flow ripple measurement. In: Bath/ASME Symposium on Fluid Power and Motion Control 2008, Bath, UK, 10–12 September 2008, pp.43–54. New York, NY: ASME.
38.
DanesLVaccaA. The influence of line and fluid parameters on pressure ripple in hydraulic transmissions. SN Appl Sci2020; 2: 1281.
39.
AudibertJMichiardiPGuyardF, et al. USAD: Unsupervised anomaly detection on multivariate time series. In: 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual, Online, 23–27 August 2020, pp.3395–3404. New York, NY: ACM.
40.
ChaoQShaoYLiuC, et al. Health evaluation of axial piston pumps based on density weighted support vector data description. Reliab Eng Syst Saf2023; 237: 109354.
