Abstract
In this paper, a fault diagnosis method based on symmetric polar coordinate image and Fuzzy C-Means clustering algorithm is proposed to solve the problem that the fault signal of axial piston pump is not intuitive under the time-domain waveform diagram. In this paper, the sampled vibration signals of axial piston pump were denoised firstly by the combination of ensemble empirical mode decomposition and Pearson correlation coefficient. Secondly, the data, after noise reduction, was converted into images, called snowflake images, according to symmetric polar coordinate method. Different fault types of axial piston pump can be identified by observing the snowflake images. After that, in order to evaluate the research results objectively, the obtained images were converted into Gray-Level Cooccurrence Matrixes. Their multiple eigenvalues were extracted, and the eigenvectors consisting of multiple eigenvalues were classified by Fuzzy C-Means clustering algorithm. Finally, according to the accuracy of classification results, the feasibility of applying the symmetric polar coordinate method to axial piston pump fault diagnosis has been validated.
Highlights
With their outstanding advantages, such as light weight, great power-mass ratio, flexible control, and fast response speed, hydraulic systems have received extremely high attention and extensive applications in industry, agriculture, and national defence [1]. e hydraulic pump, as the power component of the hydraulic system, converts the mechanical energy, provided by the prime mover, into the pressure energy of the working medium
A new algorithm based on symmetric polar coordinate method and Fuzzy C-Means (FCM) clustering was proposed for fault diagnosis of axial piston pump. e method can project the time-domain vibration signals into the polar coordinate through the symmetrical polar coordinate. en the snowflake images were generated according to the mirror symmetry plane rotation angle φ and angle magnification factor k
Four types of vibration signals of axial piston pumps have been sampled, such as swash plate wear, loose slipper, sliding shoe wear, and normal operation, through experiments. e diagnosis methods introduced in this paper are used to analyse these types of signals. e operation gets the FCM clustering result. e analysis results show that the method proposed in this paper has a high accuracy rate for the fault diagnosis of the axial piston pump
Summary
With their outstanding advantages, such as light weight, great power-mass ratio, flexible control, and fast response speed, hydraulic systems have received extremely high attention and extensive applications in industry, agriculture, and national defence [1]. e hydraulic pump, as the power component of the hydraulic system, converts the mechanical energy, provided by the prime mover, into the pressure energy of the working medium. Erefore, research on fault diagnosis technology for hydraulic pumps is important for equipment safety and intellectualization [6, 7]. A new algorithm based on symmetric polar coordinate method and Fuzzy C-Means (FCM) clustering was proposed for fault diagnosis of axial piston pump. The FCM algorithm was used to cluster the eigenvalues to achieve the purpose of fault diagnosis. Compared with the traditional methods that generate the time-domain waveform and frequency domain waveform, the image generated by the symmetric polar coordinate can reflect the tiny difference of the signals more clearly. E analysis results show that the method proposed in this paper has a high accuracy rate for the fault diagnosis of the axial piston pump Four types of vibration signals of axial piston pumps have been sampled, such as swash plate wear, loose slipper, sliding shoe wear, and normal operation, through experiments. e diagnosis methods introduced in this paper are used to analyse these types of signals. e operation gets the FCM clustering result. e analysis results show that the method proposed in this paper has a high accuracy rate for the fault diagnosis of the axial piston pump
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
