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

Abstract

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.

A Review on Vibration-Based Fault Diagnosis Techniques for Wind Turbine Gearboxes Operating Under Nonstationary Conditions

“…[20,65]. Similarly, EMD is suffers mode mixing, border distortion and EMD lacks a mathematical background [66]. Another time-frequency distribution-based technique, Wigner-Ville distribution, has also been used for the gear fault diagnosis; however, the presence of cross-terms restricts its application in gear fault diagnosis [67][68][69].…”

A Fault Feature Extraction Method for Rolling Bearings Based on Refined Composite Multi-Scale Amplitude-Aware Permutation Entropy

“…Generally, A = 0.5 is taken; update g p is the updated g p value. Then, in the whole time series, the probability of occurrence of g is shown in equation (8).…”

“…To solve these shortcomings, Richman et al [7] proposed sample entropy (SampEn), which reduced the dependence on the data length and was applied for the processing of medical and mechanical signals. Liang et al [8] and Cheng et al [9] combined ensemble empirical mode decomposition (EEMD) and SampEn for fault diagnosis of bearings and gears, respectively. Zhang et al [10] combined the wavelet packet transform and SampEn for bearing fault diagnosis.…”

A Novel Feature Extraction Method for the Condition Monitoring of Bearings

“…As we can see, the EMD is well-known in the literature [19][20][21][22][23][24][25]. The novelty of the proposed paper concerns the improvement made to the EMD and its use in the filtration of the vibration signal in order to extract a new health indicator called the Hilbert marginal.…”