The Application of Pseudo-Phase Portrait in Machine Condition Monitoring

An improved singular value decomposition method of gear fault identification based on Hilbert-Huang transform was proposed to overcome the problem of reconstructing a feature matrix of singular value decomposition. The method includes three steps. First, the instantaneous frequency and amplitude matrices were acquired by Hilbert-Huang transform from faulted gear signals. Second, after the matrices were decomposed by singular value decomposition, the defined distances of singular value vectors and the optimal threshold of the distance for classification were calculated. Third, the fault characteristics of a gearbox were identified and classified by the threshold of the distances. The result demonstrates that the proposed method effectively identifies the gear fault and can realize an automatic gear fault diagnosis.

show abstract

“…An important property of U and V is that they are mutually orthogonal [10]. The sampling signal is a time series.…”

Section: Singluar Value Decomposition On Hilbert-huang Transformmentioning

confidence: 99%

“…Finally, the phase space reconstructed from a vibration signal must be multidimensional. To achieve these requirements, the plane of projection of the attractor must be carefully selected [10,11].…”

Section: Introductionmentioning

confidence: 99%

Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform

Zhang

Jia

et al. 2011

J Mech Sci Technol

View full text Add to dashboard Cite

show abstract

“…This same approach to finding dimension was used in Refs. [51,52] using local SVD. The effects of varying the threshold (hence varying m) will be explored in the results.…”

Section: Stochastic Forcing and The Role Of Dimensionalitymentioning

confidence: 99%

Structural health monitoring of offshore structures using ambient excitation

Nichols

2003

Applied Ocean Research

View full text Add to dashboard Cite

“…As the singular value of a matrix is relatively stable and it could represent its natural characteristic, it is desirable to be used to detect periodic faults. Moreover, it is not necessary to manually choose the reconstruction parameters in SVD because the initial feature vector matrix can be generated by combining the IMFs directly [18]. When considering the periodic impulse could reveal related faults by singular values of the matrixes while applying SVD, the SVD technique based on EEMD is proposed.…”

Section: Introductionmentioning

confidence: 99%

Correlated EEMD and Effective Feature Extraction for Both Periodic and Irregular Faults Diagnosis in Rotating Machinery

2017

View full text Add to dashboard Cite

Intelligent fault diagnosis of complex machinery is crucial for industries to reduce the maintenance cost and to improve fault prediction performance. Acoustic signal is an ideal source for diagnosis because of its inherent characteristics in terms of being non-directional and insensitive to structural resonances. However, there are also two main drawbacks of acoustic signal, one of which is the low signal to noise ratio (SNR) caused by its high sensitivity and the other one is the low computational efficiency caused by the huge data size. These would decrease the performance of the fault diagnosis system. Therefore, it is significant to develop a proper feature extraction method to improve computational efficiency and performance in both periodic and irregular fault diagnosis. To enhance SNR of the acquired acoustic signal, the correlation coefficient (CC) method is employed to eliminate the redundant intrinsic mode functions (IMF), which comes from the decomposition procedure of pre-processing known as ensemble empirical mode decomposition (EEMD), because the higher the correlated coefficient of an IMF is, the more significant fault signatures it would contain, and the redundant IMF would compromise both the SNR and the computational cost performance. Singular value decomposition (SVD) and sample Entropy (SampEn) are subsequently used to extract the fault feature, by exploiting their sensitivities to irregular and periodic fault signals, respectively. In addition, the proposed feature extraction method using sparse Bayesian based pairwise coupled extreme learning machine (PC-SBELM) outperforms the existing pairwise-coupling probabilistic neural network (PC-PNN) and pairwise-coupling relevance vector machine (PC-RVM) by 1.8% and 2%, respectively, to achieve an accuracy of 93.9%. The experiments conducted on the periodic and irregular faults in the gears and bearings have demonstrated that the proposed hybrid fault diagnosis system is effective.

show abstract

The Application of Pseudo-Phase Portrait in Machine Condition Monitoring

Cited by 22 publications

References 28 publications

Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform

Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform

Structural health monitoring of offshore structures using ambient excitation

Correlated EEMD and Effective Feature Extraction for Both Periodic and Irregular Faults Diagnosis in Rotating Machinery

Contact Info

Product

Resources

About