Abstract
It is always a serious challenge to deal with the influence of noise for fault detection of rotating electrical machines under varying operating environments. To extract the most discriminative features for machine fault classification, a novel dimensionality reduction algorithm called joint sparsity and collaboration preserving projections (JSCPP) is proposed in this article, based on the platform of graph embedding framework. A joint combination of sparse representation (SR) and collaborative representation (CR) is used to construct the intrinsic and penalty graphs. SR emphasizes only on the dictionary atoms highly correlated to the query sample for local optimum while CR takes every atom into consideration for global optimum, thus applying a joint combination would make it benefit from the merits of both for graph construction. After JSCPP seeks the optimal projection directions by minimizing the intra-class compactness and maximizing the inter-class separability, a nearest neighbor classifier is then used. Through two sets of vibration data with white Gaussian noise interfered, the capability of JSCPP is demonstrated by effectively classifying different defect types and severity degrees of faulty bearings. The experimental results have also proved that the classification performance of the proposed method is much superior to the other compared algorithms in both accuracy rates and reliability.
Highlights
With the development of modern industry, rotating electrical machines have been intensively utilized under extreme operating conditions, and their variable-speed drives with high switching frequencies can gradually erode their interior structure [1], [2]
To evaluate the performance of these methods when applied in harsh operating environments, different levels of white Gaussian noise are artificially imposed on the original vibration signals for simulation at the first step
The curve across the entire considered range of dimensions with signal-to-noise ratio (SNR) = −6 dB stays higher than the one with SNR = −12 dB for each method, implying that noise does enhance the difficulty of classification
Summary
With the development of modern industry, rotating electrical machines have been intensively utilized under extreme operating conditions, and their variable-speed drives with high switching frequencies can gradually erode their interior structure [1], [2]. In [28], an algorithm called local and non-local preserving projection (LNPP), along with a supervised-learning-based LNPP (SLNPP), was proposed for bearing fault diagnosis and performance prognostics All these methods mentioned above can be unified in the graph embedding framework [29]. The number of neighbors k and the ball radius ε are manually adopted based on experience, as well as the graph edge weights, which cannot be self-adaptive to data from various applications To deal with this problem, collaborative representation (CR), which employs samples from different classes to collaboratively represent the query sample via -2 norm optimization, is introduced, as well as sparse representation (SR), which forces the representations to be sparse via -0 norm or -1 norm.
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 callDisclaimer: 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.
