Condition monitoring of bearings is an open issue. The use of the stator current to monitor induction motors has been validated as a very advantageous and practical way to detect several types of faults. Nevertheless, for bearing faults, the use of vibrations or sound generally offers better results in the accuracy of the detection, although with some disadvantages related to the sensors used for monitoring. To improve the performance of bearing monitoring, it is proposed to take advantage of more information available in the current spectra, beyond the usually employed, incorporating the amplitude of a significant number of sidebands around the first eleven harmonics, growing exponentially the number of fault signatures. This is especially interesting for inverter-fed motors. But, in turn, this leads to the problem of overfitting when applying a classifier to perform the fault diagnosis. To overcome this problem, and still exploit all the useful information available in the spectra, it is proposed to use shrinkage methods, which have been lately proposed in machine learning to solve the overfitting issue when the problem has many more variables than examples to classify. A case study with a motor is shown to prove the validity of the proposal.
Condition monitoring of bearings is an open issue. The use of the stator current to monitor 11 induction motors has been validated as a very advantageous and practical way to detect several 12 types of faults. Nevertheless, for bearing faults the use of vibrations or sound generally offers better 13 results in the accuracy of the detection although with some disadvantages related to the sensors 14 used for monitoring. To improve the performance of bearing monitoring, it is proposed to take 15 advantage of more information available in the current spectra, beyond the usually employed, 16incorporating the amplitude of a significant number of sidebands around the first eleven harmonics, 17 growing exponentially the number of fault signatures. This is especially interesting for inverter-fed 18 motors. But, in turn, this leads to the problem of overfitting when applying a classifier to perform 19 the fault diagnosis. To overcome this problem, and still exploit all the useful information available 20 in the spectra, it is proposed to use shrinkage methods, which have been lately proposed in machine 21 learning to solve the overfitting issue when the problem has much more variables than examples to 22 classify. A case study with a motor is shown to prove the validity of the proposal. 23 24 25 35 implementation. Mainly, the low energy of the vibrations associated to the fault, which makes it 36 difficult to distinguish in the current spectrum the frequency components related to the fault that 37 may be buried in the noise [1,5,6]. Besides, for inverter-fed motors the noise is higher and there are 38 other harmonics present in the spectrum which complicates even more the detection of the faulty 39 related components [7]. Consistently, in [8] denoising techniques are applied to highlight the faulty 40 components in the current spectrum. Other advanced spectral techniques have also been proposed 41 such as wavelets [9,10], Short-Time Fourier Transform [11], Gabor spectrogram [11] Hilbert-Huang 42 Transform [12], Empirical Mode Decomposition [13] MUSIC [13,14], space vector angular fluctuation 43 method [15]. These techniques have the drawback of a high computational cost.44 Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 28 130 group, there are several classifiers available. Using these classifiers, it has been proved (as shown in 131 the results section) the huge increase in performance of all the classifiers when using the 968 fault 132 signatures instead of the usual 8 signatures. 133However, when using such high number of signatures, and with a reduced number of tests, the 134 risk of overfitting is certain. Shrinkage techniques allow to make use of all the predictors but 135 shrinking the coefficients towards zero, hence, reducing variance [36]. If applied in linear models 136 (which has the advantage in terms of interpretability of the model), it performs as follows: let xi be 137 the m predictors (or fault signatures in the context of condition monitoring) and yi the response for 138 Preprints (www.prepri...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.