Abstract
As the vibration signal characteristics of hydraulic pump present non-stationary and the fault features is difficult to extract, a new feature extraction method was proposed .This approach combines wavelet packet analysis techniques, fuzzy entropy and LLTSA (liner local tangent space alignment) which is one of typical manifold learning methods to extracting fault feature. Firstly, the vibration signals were decomposed into eight signals in different scales, then the fuzzy entropies of signals were calculated to constitute eight dimensions feature vector. Secondly, LLTSA method was applied to compress the high-dimension features into low-dimension features which have a better classification performance. Finally, the SVM (support vector machine) was employed to distinguish different fault features. Experiment results of hydraulic pump feature extraction show that the proposed method can exactly classify different fault type of hydraulic pump and this method has a significant advantage compared with other feature extraction means mentioned in this paper.
Highlights
In fault diagnosis of hydraulic pump, the vibration signal contains abundant running status information, analyzing the vibration signal is the most commonly used method in fault diagnosis process [1]
As there are different types of hydraulic pump faults, the results of fault vibration signal with wavelet packet decomposition will be changed under different scales of structure characteristics, the complexity and irregularity degree, and its fuzzy entropy value can produce significant change, so the different scales of fuzzy entropy can be used as a feature vector for feature extraction [8,9,10]
It shows that the fuzzy entropy has a larger advantage in description of sample fault characteristics; Secondly, recognition rates of wavelet packet fuzzy entropy fault eigenvectors are higher after dimensionality reduction by the principal component analysis (PCA), Local tangent space alignment (LTSA), local tangent space alignment (LLTSA) methods and increased by 1.25%, 2.5% and 6.25%; the LLTSA method has higher identification accuracy than PCA and LTSA which testifies that as a kind of popular nonlinear learning method, the LLTSA keeps lowdimensional main characteristics of high-dimensional fault information in the process of dimensionality reduction, and can effectively distinguish between four kinds of fault state of hydraulic pump
Summary
In fault diagnosis of hydraulic pump, the vibration signal contains abundant running status information, analyzing the vibration signal is the most commonly used method in fault diagnosis process [1]. As there are different types of hydraulic pump faults, the results of fault vibration signal with wavelet packet decomposition will be changed under different scales of structure characteristics, the complexity and irregularity degree, and its fuzzy entropy value can produce significant change, so the different scales of fuzzy entropy can be used as a feature vector for feature extraction [8,9,10]. Multi-scale analysis ability of wavelet packet decomposition was used to obtain different scales of hydraulic pump fault information, the different scales of fuzzy entropy were extracted as the characteristics of the hydraulic pump under different fault states, and LLTSA was used to conduct feature dimension reduction which could get fault features with low dimension, high sensitivity and good clustering performance. The effectiveness and superiority of this proposed method have been proved through fault signal diagnosis experiments of hydraulic pump and comparison with other methods
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 callMore From: International Journal of Online and Biomedical Engineering (iJOE)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
