Mechanical Faults Diagnosis of High-Voltage Circuit Breaker via Hybrid Features and Integrated Extreme Learning Machine

Abstract

As key electrical equipment in the power system, the normal operation of a high-voltage circuit breaker is related to the reliability and economy of the power supply. In this paper, a mechanical fault diagnostic method for a high-voltage circuit breaker via the hybrid feature extraction and the integrated extreme learning machine (IELM) is investigated. First, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the vibration signal to obtain intrinsic mode functions (IMF). Then, the sub-band reconstruction of each order IMF component is performed by combining the Hilbert transform and the band-pass filter in order to obtain the time-frequency matrix. Moreover, mechanical fault feature vectors can be formed by the time-frequency entropy and the singular entropy, which are extracted by transforming the time-frequency matrix into the energy matrix and normalizing the frequency bands via the normal cumulative distribution function (NCDF). In addition, an IELM is built for the fault classification. The advantages of the proposed CEEMDAN scheme in combination with band-pass filtering can eliminate the modal aliasing, reduce the number of auxiliary noise additions, and improve the decomposition efficiency. Besides, the performance of the singular entropy normalized by the NCDF is more stable, and the IELM composed of multiple weak classifiers can solve the shortcomings of the traditional extreme learning machine. The experimental results based on measured data show the proposed method can effectively diagnose the mechanical failure via small samples of high-voltage circuit breakers. INDEX TERMS High-voltage circuit breaker, vibration signal, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), time-frequency entropy, singular entropy, integrated extreme learning machine (IELM).

Condition Monitoring of High Voltage Circuit Breakers: Past to Future

“…The vibration signal generated during the opening and closing operation of the CBs has gradually become the mainstream research owing to convenient data acquisition as well as its suitability for non-invasive and real-time evaluation, which could cover the most origins of the failures occurring in the operating mechanism of CBs [46], [49]- [52]. This signal as shown in Figure 6 could reveal the anomalies in the mechanical section.…”

“…To give an illustration, using frequency response has been recently suggested as a noninvasive diagnosis approach for CBs. A broadband micro-strip antenna has been employed as the new diagnostic sensor to evaluate the degradation of contacts through establishment of the correlation between the arc duration and signal energy and radiated wave in [49]. In another effort [59], the correlation between different working status of the CBs and the timefrequency characteristics of switching transient E-fields have been addressed to early predict the insulation defect of the HV CBs.…”

“…Energy entropy of Hilbert marginal spectrum (HMS), variational mode decomposition (VMD), [53] (2019) Wavelet, stacked auto encoder neural network [46] (2018) Current vibration signal entropy weight characteristic, grey wolf optimization-support vector machine (GWO-SVM), [49] (2019) Phase space reconstruction, Lyapunov exponent (LLE), correlation dimension (CD),Kolmogorov entropy (KE) [51] (2019) Empirical mode decomposition (EMD) energy entropy, multi-class support vector machine (MSVM) [ Neural network and support vector machine (SVM) [18] (2019) empirical mode decomposition (EMD), empirical wavelet transform (EWT), wavelet packet transform (WPT), variational mode decomposition (VMD) for extraction of features. Subsequently, this signal can be transformed into several intrinsic mode functions.…”

Multiscale Entropy Feature Extraction Method of Running Power Equipment Sound

“…In light of this, the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was proposed [ 35 ]. Due to its powerful complex signal analysis capability, CEEMDAN is favored in different fields such as fault diagnosis [ 36 , 37 , 38 ], seismology [ 39 ], traffic flow prediction [ 40 ], and medicine [ 41 , 42 ]. However, CEEMDAN may produce some spurious modes in the early stage of decomposition [ 43 ].…”

Research on Novel Bearing Fault Diagnosis Method Based on Improved Krill Herd Algorithm and Kernel Extreme Learning Machine

“…In the eld of bearing fault diagnosis, novel intelligent fault diagnosis methods emerge one after another in recent years, namely, the method based on statistics having Pearson's correlation coe cient (PCC) [11], the method based on signal processing having modi ed variable modal decomposition (MVMD) [12], improved ensemble local mean decomposition (IELMD) [13], maximum kurtosis spectral entropy deconvolution (MKSED) [14], regression residual signal based on improved intrinsic timescale decomposition [15], enhanced singular spectrum decomposition (ESSD) [16], weighted cyclic harmonic-tonoise ratio [17], time-frequency analysis [18], multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) [19], and so on [20]. In recent years, with the development of big data, machine learning methods and deep learning methods have been widely used to solve practical engineering problems [21][22][23][24][25][26]. Machine learning methods or deep learning methods were applied in the field of bearing fault diagnosis, including the support vector machine (SVM) [27,28], BP neural network (BP) [29], deep convolutional transfer learning network (CNN) [30], and kernel extreme learning machine (ELM) [31,32].…”