A recognition method of valve plate wear states of piston pump based on optimized VMD-CWT-CNN

Abstract

It is difficult to fully mine the information from that one-dimensional vibration signal that expresses the state characteristics and then early recognize the wear of the valve plate of a piston pump. In view of the excellent image processing capabilities of the convolutional neural networks(CNN), we proposed an optimized VMD-CWT-CNN model to solve the above-mentioned problem. Firstly, continuous wavelet transform(CWT) was used to preprocess the signal to obtain a two-dimensional time-frequency diagram of the signal, which iwasused as one input of the CNN model to convert the state recognition problem into a CNN image recognition problem. Secondly, after optimizing variational mode decomposition(VMD) parameters based on correlation coefficient, the vibration signal was preprocessed by using the optimized VMD, and then based on the principle of maximizing the correlation coefficient and the kurtosis value, three groups of Intrinsic mode function(IMF) with fault characteristics were selected and reorganized into a three-channel one-dimensional signal as another input of the CNN model. Finally, in the CNN model, two paths were converged, and the results of the recognition and classification of the valve plate wear states of the piston pump were obtained. In the experiment, the proposed method we first use the optimized VMD and the CWT to preprocess the vibration signal, respectively, and then combined with the CNN to classify the wear states of valve plates. Experimental results show the recognition effect of the proposed method on the three states of valve plate wear is significantly better than that of the single-input CNN model, the typical deep learning method and the machine learning classifier. The optimized VMD-CWT-CNN method can more accurately recognize the valve plate wear states of the piston pump.

Keywords

piston pump valve plate wear / vibration signal / convolutional neural network(CNN) / variational mode decomposition(VMD) / continuous wavelet transform(CWT)

References

[1] LIU S, DING L, JIANG W. Study on application of Principal Component Analysis to fault detection in hydraulic pump//2011 International Conference on Fluid Power and Mechatronics, August 17-20, 2011, Beijing, China. Beijing: Acta Aeronautica et Astronautica Sinica, 2011: 173-178

[2] GU L, XU R, WANG N. A novel reduced order dynamic model of axial piston motors with compression flow losses and Coulomb friction losses. Industrial Lubrication and Tribology, 2020,72(5): 567-573.

[3] ZI H Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing, 2009, 23(4): 1327-1338.

[4] JAYASWALT P, WADHWANI A K. Application of artificial neural networks, fuzzy logic and wavelet transform in fault diagnosis via vibration signal analysis: A review. Australian Journal of Mechanical Engineering, 2009, 7(2): 157-172.

[5] TANG X, LIANG L, GAO H, et al. Fault feature extraction method combining continuous wavelet transform with multi-constraint nonnegative matrix factorization. Journal of Vibration and Shock, 2013, 32(19): 7-11.

[6] HONG L, WANG W, CHEN Q. State identification of draft tube vortex based on continuous wavelet transform and convolution neural network. Guangdong Electric Power, 2018,31(5): 1-6.

[7] WU S, FENG F, WU C, et al. Research on fault diagnosis method of tank planetary gearbox based on VMD-DE. Journal of Vibration and Shock, 2020, 39(10):176-185.

[8] ZHOU F, TANG J, HE Y. Unbalanced fault feature extraction for wind power gearbox based on improved VMD. Journal of Vibration and Shock, 2020, 39(5):170-176.

[9] FENG S, CHAI K, ZHU S, et al. Fault feature extraction of hydraulic system based on improved VMD. Journal of Naval University of Engineering, 2021,33(2): 6-13.

[10] ZHENG Y, BAO H, XU C. A method for improved pedestrian gesture recognition in self-driving cars. Australian Journal of Mechanical Engineering, 2018, 16(sup1): 78-85.

[11] ZHANG W, LI C, PENG G, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing, 2018,100: 439-453.

[12] WU C, JIANG P, DING C, et al. Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network. Computers in Industry, 2019, 108: 53-61.

[13] MONTEIRO R, BASTOS-FILHO C, CERRADA M, et al. Convolutional neural networks using fourier transform spectrogram to classify the severity of gear tooth breakage//International Conference on Sensing, Diagnostics, Prognostics, and Control, August 15-17, 2018, Xi'an, China. Piscataway, N. J.: IEEE, 2018: 490-496.

[14] SIMONYAN K, ZISSERMAN A. Two-stream convolutional networks for action recognition in videos. Advances in Neural Information Processing Systems.2022-05-09].

[15] DONG H, KONG C, SHI F, et al. Signal processing of ultrasonic phased array echo of borehole imaging testing. Nondestructive Testing, 2017, 39(5): 65-69.

[16] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition. IEEE Transactions on Signal Processing, 2014,62(3): 531-544.

[17] YANG S, GU L, SHI Y, et al. Monitoring method of gear teeth failure of hydraulic gear pump based on improved VMD and DBN-DNN of electrical signal. Journal of Measurement Science and Instrumentation, 2021,12(2):242-252.

[18] BING L, JING C, XIAO J, et al. Robotic impact-echo non-destructive evaluation based on FFT and SVM// 11th World Congress on Intelligent Control and Automation, June 2-4, 2014, Shenyang,China. Piscataway, N. J.: IEEE, 2014: 2854-2859.