Abstract
To avoid the burden of much storage requirements and processing time, this paper proposes a three-stage hybrid method, compressive sampling with correlated principal and discriminant components (CS-CPDC), for bearing faults diagnosis based on compressed measurements. In the first stage, CS is utilized to obtain compressively sampled signals from raw vibration data. In the second stage, an effective multistep feature learning algorithm obtains fewer features from correlated principal and discriminant attributes from the compressively sampled signals, which are then concatenated to increase the performance. In the third stage, with these concatenated features, multiclass support vector machine is used to train, validate, and classify bearing faults. Results show that the proposed method, CS-CPDC, offers high classification accuracies, reduced computation time, and storage requirement, with fewer measurements.
Highlights
R OTATING machines are widely used in industry for various tasks
Rolling element (RE) bearings are the critical components in a rotating machine and their failures may lead to more major failures in machines
Motivated by the idea of compressive sampling (CS) and the advantages of principal component analysis (PCA), linear discriminant analysis (LDA), and canonical correlation analysis (CCA), we present a new method for intelligent fault diagnosis
Summary
R OTATING machines are widely used in industry for various tasks. Unforeseen machine failures may affect production schedules, product quality, and production costs. In [26], an intelligent condition monitoring method for bearing faults based on CS and sparse overcomplete feature learning algorithm using SAE was proposed. In a recent paper by Ahmed et al [27], three approaches to process compressed vibration measurements were proposed for classification of bearing faults, including using the compressed measurements directly as the input to the classifier, and extracting features from these compressed measurements using PCA and LDA. We propose to combine PCA and LDA features via CCA in a three-step process to transform the characteristic space of compressively sampled signal into a low-dimensional space of correlated important and discriminant attributes, which are concatenated to form a vector of useful features.
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.
