The Optimal Usage of the Fourier Transform for Pattern Recognition

Gelman, Leonid M.; Braun, Simon

doi:10.1006/mssp.2000.1373

Cited by 17 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results are in accordance with previous results [7,8,14] based on the Fourier transform. Thus we recommend that one considers using the real and imaginary components of the bicoherence as an alternative to use of the bicoherence magnitude.…”

Section: Article In Presssupporting

confidence: 95%

“…In the present paper we consider an extension of the methodology described in [7,8] to HOS techniques, specifically to the bicoherence. We shall also consider its application to experimental data with the goal of detecting cracks in aircraft compressor blades.…”

Section: Introductionmentioning

confidence: 99%

“…New generic diagnostic measures were proposed [7] based on the complex Fourier transform coefficients, rather than the standard approach of looking at their squared magnitude (the power spectral density). The methodology consists of using two diagnostic (recognition) features: the real and imaginary components of the Fourier transform.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fatigue crack diagnostics: A comparison of the use of the complex bicoherence and its magnitude

Gelman

White

Hammond

2005

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

Section: Article In Presssupporting

confidence: 95%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fatigue crack diagnostics: A comparison of the use of the complex bicoherence and its magnitude

Gelman

White

Hammond

2005

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

“…It is known [60,61], that the phase spectra of single characteristic spectral components are important for fault diagnosis. However, as the proposed technologies do not employ single characteristic spectral components, but employ, simultaneously, multiple characteristic spectral components, it is shown below, via experimental trials, that it is more beneficial to exclude from consideration the phase spectra of these spectral components.…”

Section: The Cross-correlations Of Spectral Modulimentioning

confidence: 99%

Novel Nonlinear High Order Technologies for Damage Diagnosis of Complex Assets

2022

View full text Add to dashboard Cite

For the first time worldwide, innovative techniques, generic non-linear higher-order unnormalized cross-correlations of spectral moduli, for the diagnosis of complex assets, are proposed. The normalization of the proposed techniques is based on the absolute central moments, that have been proposed and widely investigated in mathematical works. The existing higher-order, cross-covariances of complex spectral components are not sufficiently effective. The novel technology is comprehensively experimentally validated for induction motor bearing diagnosis via motor current signals. Experimental results, provided by the proposed technique, confirmed high overall probabilities of correct diagnoses for bearings at early stages of damage development. The proposed diagnosis technology is compared with existing diagnosis technology, based on the triple cross-covariance of complex spectral components.

show abstract

“…However, once the envelope was obtained for each vibration signal, it was necessary to devise a method to determine automatically from that vibration spectral signal if the bearing is defective and its defect type. In the literature, different approaches in the frequency domain have been proposed (Su and Lin, 1992;Su and Sheen, 1993;Tse et al, 2001;Altmann and Mathew, 2001;Gelman and Braun, 2001;Del Castillo et al, 2002;Artes and Del Castillo, 2003;Sheen, 2004;Rivas et al, 2009). In recent years, several researchers have proposed new methods based on artificial intelligent techniques, as an alternative diagnosis technique (Korbicz et al, 2004;Andrew et al, 2006).…”

Section: Experimental Setup and Measurement Processmentioning

confidence: 99%

An intelligent system for faulty-bearing detection based on vibration spectra

Marichal

Artés

García-Prada

2010

Journal of Vibration and Control

View full text Add to dashboard Cite

In this paper, a new detection and classification system of faulty bearings is presented. This system is based on artificial intelligent techniques and vibration signals in the frequency domain produced by the faulty bearings. The system consists of several neuro-fuzzy systems in cascade, along with measurement equipment for the vibration spectral data. These neuro-fuzzy systems have been used as bi-classifiers. That is, each neuro-fuzzy system is specialized in the classification between two different types of rolling bearing status. A careful selection process for rules has been included in the learning algorithm. Moreover, the demodulated vibration signal has been used as input to the neuro-fuzzy systems based on the Sugeno approach. Several trials were carried out, taking into account the vibration spectral data collected by the measurement equipment for each bearing. Different results with three types of faulty bearings using the proposed approach are shown, where satisfactory results have been achieved.

show abstract

The Optimal Usage of the Fourier Transform for Pattern Recognition

Cited by 17 publications

References 5 publications

Fatigue crack diagnostics: A comparison of the use of the complex bicoherence and its magnitude

Fatigue crack diagnostics: A comparison of the use of the complex bicoherence and its magnitude

Novel Nonlinear High Order Technologies for Damage Diagnosis of Complex Assets

An intelligent system for faulty-bearing detection based on vibration spectra

Contact Info

Product

Resources

About