Abstract
In order to solve the problem of selection of appropriate wavelet basis function and clearly show the physical meaning of Empirical Mode Decomposition (EMD), an improved Variational Mode Decomposition (VMD) method with Long Short-Term Memory (LSTM) neural network is proposed. With the Cuckoo Search (CS) algorithm, the central frequency updating rules of VMD are optimized. And the low efficiency and local optimum problem is avoided. Meanwhile the decomposition layer number is found by the instantaneous frequency theory. For improving the prediction accuracy in traditional regression prediction methods, a LSTM neural network is designed for regression prediction of time sequence characteristics. The proposed method is implemented on actual bearings data which is derived from the bearing laboratory of Case West Reserve University in the United States and the University of Cincinnati Bearing Data Center. The experimental results showed that the improved VMD method was more robust and more accurate than the other traditional methods. And it has some practical value for real application and guiding significance for theory.
Highlights
As a precision component, rolling bearings are widely used in rotating machinery
Li et al presented an integration method of artificial neural network and empirical mode decomposition to identify fault severity in rolling bearings, and the results demonstrated that the integration method had been successful in machine fault severity diagnosis [12], but it had been hard to obtain so lots of data to support the training of ANN
support vector regression (SVR) is better than K-nearest neighbor (KNN) and ANN in regression prediction, the selection of parameters in SVR has a great influence on the accuracy
Summary
As a precision component, rolling bearings are widely used in rotating machinery. Because of the natural working conditions, the rolling bearings are vulnerable. The performance assessment of rolling bearings and its maintenance according to its situation are the most important works to ensure the safe, stable, efficient and accurate operation of rotating machinery. It is one of the most popular subjects of research in the academic and industrial area [3]. FAULT SEVERITY ASSESSMENT OF ROLLING BEARINGS METHOD BASED ON IMPROVED VMD AND LSTM. SVR is better than KNN and ANN in regression prediction, the selection of parameters in SVR has a great influence on the accuracy These traditional regression prediction methods have certain effects on the processing of non-timing signals. Note: The frequency units are Hz, the amplitude/var/rms/kurtosis units are mm and the data units are group except for special instructions in this paper
Sign-in/Register to view highlights & summary 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.
