Non-negative EMD manifold for feature extraction in machinery fault diagnosis

Gan, Meng; Zhu, Changan

doi:10.1016/j.measurement.2015.04.006

Cited by 38 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EMD helps to smooth processing of the signal, decompose the fluctuations or trends of signal in different scales gradually, and overcome the pre-filter center frequency and bandwidth problem in traditional envelope analysis. EMD is suitable for nonstationary and nonlinear signal analysis, and it has been widely used in many fields [11][12][13][14], and the steps of EMD can be shown as follows. Firstly, the raw vibration signal was decomposed; see…”

Section: Features Extractionmentioning

confidence: 99%

“…Empirical mode decomposition (EMD), as a formidable and effective time-frequency analysis method, is programed to analyze the nonstationary signals and can be adaptive to decompose 2 Shock and Vibration the confusion signal into intrinsic mode functions (IMFs) by the inherent characteristics of the signals [11][12][13]. Features extraction by EMD is appropriate for distinguishing different mechanical signals [14][15][16]. Wang et al [14] propose a novel feature extraction method by nonnegative EMD manifold in machinery fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

“…Features extraction by EMD is appropriate for distinguishing different mechanical signals [14][15][16]. Wang et al [14] propose a novel feature extraction method by nonnegative EMD manifold in machinery fault diagnosis. Saidi et al [15] proposed an EMD-based fault diagnosis module to detect the incipient bearing faults based on the raw vibration signals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiple‐Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

Zhang

Cai

Cheng

2018

Shock and Vibration

View full text Add to dashboard Cite

Identification of rolling bearing fault patterns, especially for the compound faults, has attracted notable attention and is still a challenge in fault diagnosis. In this paper, a novel method called multiscale feature extraction (MFE) and multiclass support vector machine (MSVM) with particle parameter adaptive (PPA) is proposed. MFE is used to preprocess the process signals, which decomposes the data into intrinsic mode function by empirical mode decomposition method, and instantaneous frequency of decomposed components was obtained by Hilbert transformation. Then, statistical features and principal component analysis are utilized to extract significant information from the features, to get effective data from multiple faults. MSVM method with PPA parameters optimization will classify the fault patterns. The results of a case study of the rolling bearings faults data from Case Western Reserve University show that (1) the proposed intelligent method (MFE PPA MSVM) improves the classification recognition rate; (2) the accuracy will decline when the number of fault patterns increases; (3) prediction accuracy can be the best when the training set size is increased to 70% of the total sample set. It verifies the method is feasible and efficient for fault diagnosis.

show abstract

Section: Features Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple‐Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

Zhang

Cai

Cheng

2018

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Wang et al [26] proposed a novel non-negative empirical mode decomposition manifold method for feature extraction from the fault-related intrinsic mode functions in machinery fault diagnosis. Shi et al [27] proposed a method of empirical mode decomposition based on a cascaded multi-stable stochastic resonance system.…”

Section: Introductionmentioning

confidence: 99%

A New Feature Extraction Method Based on EEMD and Multi-Scale Fuzzy Entropy for Motor Bearing

Zhao

Sun

Deng

et al. 2016

Entropy

182

View full text Add to dashboard Cite

Abstract:Feature extraction is one of the most important, pivotal, and difficult problems in mechanical fault diagnosis, which directly relates to the accuracy of fault diagnosis and the reliability of early fault prediction. Therefore, a new fault feature extraction method, called the EDOMFE method based on integrating ensemble empirical mode decomposition (EEMD), mode selection, and multi-scale fuzzy entropy is proposed to accurately diagnose fault in this paper. The EEMD method is used to decompose the vibration signal into a series of intrinsic mode functions (IMFs) with a different physical significance. The correlation coefficient analysis method is used to calculate and determine three improved IMFs, which are close to the original signal. The multi-scale fuzzy entropy with the ability of effective distinguishing the complexity of different signals is used to calculate the entropy values of the selected three IMFs in order to form a feature vector with the complexity measure, which is regarded as the inputs of the support vector machine (SVM) model for training and constructing a SVM classifier (EOMSMFD based on EDOMFE and SVM) for fulfilling fault pattern recognition. Finally, the effectiveness of the proposed method is validated by real bearing vibration signals of the motor with different loads and fault severities. The experiment results show that the proposed EDOMFE method can effectively extract fault features from the vibration signal and that the proposed EOMSMFD method can accurately diagnose the fault types and fault severities for the inner race fault, the outer race fault, and rolling element fault of the motor bearing. Therefore, the proposed method provides a new fault diagnosis technology for rotating machinery.

show abstract

“…The research results have provided effective theoretical support for accident prevention and pipeline maintenance and greatly reduced maintenance costs. In recent years, wavelet transform and Fourier transform, information entropy, neural network, bispectrum analysis, feature fusion, evidence theory, chaos theory, fractal theory, decision tree, and SVM have been widely applied to the fault diagnosis of reciprocating machinery, and many significant research achievements have been obtained [7][8][9][10][11][12][13][14][15][16]. Yet compared with the fault diagnosis of rotating machinery, there are still many research 2 Complexity contents to be improved: (1) the data sample size of reciprocating machinery is huge and a great deal of multisource heterogeneous information is held within them due to the influence of complex structure, multiple excitation source, multiple wearing parts, coupling of the signal, and strong nonlinearity of reciprocating machinery.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine

Wang

2017

Complexity

View full text Add to dashboard Cite

Check valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. However, in the fault diagnosis of check valve, the classification models with single kernel function can not fully interpret the classification decision function, and meanwhile unreasonable assumption of diagnostic cost equalization has a significant impact on classification results. Therefore, the multikernel function and cost-sensitive mechanism are introduced to construct the fault diagnosis model of check valve based on the multikernel cost-sensitive extreme learning machine (MKL-CS-ELM) in this paper. The comparative test results of check valve for high pressure diaphragm pump show that MKL-CS-ELM can obtain fairly or slightly better performance than ELM, CS-ELM, MKL-ELM, and multikernel cost-sensitive support vector learning machine (MKL-CS-SVM). At the same time, the presented method can obtain very high accuracy under imbalance datasets condition and effectively overcome the weakness of diagnostic cost equalization and improve the interpretability and reliability of the decision function of classification model. It, therefore, is more suitable for the practical application.

show abstract

Non-negative EMD manifold for feature extraction in machinery fault diagnosis

Cited by 38 publications

References 35 publications

Multiple‐Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

Multiple‐Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

A New Feature Extraction Method Based on EEMD and Multi-Scale Fuzzy Entropy for Motor Bearing

Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine

Contact Info

Product

Resources

About