Research of circuit breaker intelligent fault diagnosis method based on double clustering

He, Mu; Ding, Qin; Zhao, Shutao; Yao, Wei

doi:10.1587/elex.14.20170463

Cited by 14 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After years of development, clustering has many applications in fault identification. [12][13][14] Clustering has developed a variety of clustering methods for different scenarios. 15 In the study of dynamics research, due to the complexity of modal parameters, it is very difficult to determine the number of clustering groups in advance, so the fast clustering method that does not need to determine the number of clusters in advance is what we need.…”

Section: Principle Of Machine Tool Modal Classification Analysis Methmentioning

confidence: 99%

A new modal analysis method applied to changing machine tool using clustering

Jiang

Mao

Chen

et al. 2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The states of the machine tool, such as the components’ position and the spindle speed, play leading roles in the change of dynamic parameters. However, the traditional modal analysis method that modal parameters manually identified from vibration signal is greatly interfered by harmonics, and the process of eliminating interference is very inefficient and subjective. At present, there is a lack of a standard and efficient method to characterize modal parameter changes in different states of machine tools. This paper proposes a new machine tool modal classification analysis method based on clustering. The characteristics related to the modal parameters are extracted from the response signal in different states, and the clustering results are used to reflect the changes of machine tool modal parameters. After the amplitude of the frequency response function is normalized, the characteristics related to the natural frequency are acquired, and the clustering results further reflect the difference of the natural frequency of the signal. The new method based on clustering can be a standard and efficient method to characterize modal parameter changes in different states of machine tools.

show abstract

Section: Principle Of Machine Tool Modal Classification Analysis Methmentioning

confidence: 99%

A new modal analysis method applied to changing machine tool using clustering

Jiang

Mao

Chen

et al. 2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…Then, the product functions were quantized by the approximate entropy, and the entropy value was taken as the characteristic of the fault signal. The result in [13] showed that the feature recognition accuracy extracted by double clustering is significantly higher than that of a single clustering method. Although the features extracted by the entropy as a characteristic attribute have certain characterization ability, the influence of disturbance and noise cannot be avoided, especially the statistic that directly quantizes the time series, such as the sample entropy, the permutation entropy, and the approximate entropy.…”

Section: Introductionmentioning

confidence: 97%

“…Moreover, the energy entropy from the time domain and the frequency domain was extracted to construct the timefrequency entropy, and the one-class support vector machine (OCSVM) was used to determine whether there are mechanical failures or not. He et al [13] proposed a new method for the fault identification of high-voltage circuit breakers based on the density peak clustering, the kernel fuzzy C-means clustering and the support vector machine (SVM).…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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).

show abstract

“…Literature [10] uses complementary ensemble empirical mode decomposition (CEEMD) algorithm to decompose sound-vibration signals and extracts the energy coefficient, sample entropy and power spectral entropy of IMF components as feature vectors for fault diagnosis. Literature [11] uses fuzzy peak optimization C-means clustering and SVM to diagnose sound-vibration signals. Although the above methods have achieved some achievements, there are still some existing problems:…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis method for energy storage mechanism of high voltage circuit breaker based on CNN characteristic matrix constructed by sound-vibration signal

Zhao¹,

Wang²,

Hao³

2019

J. vibroeng.

View full text Add to dashboard Cite

Aiming at the problem that some traditional high voltage circuit breaker fault diagnosis methods were over-dependent on subjective experience, the accuracy was not very high and the generalization ability was poor, a fault diagnosis method for energy storage mechanism of high voltage circuit breaker, which based on Convolutional Neural Network (CNN) characteristic matrix constructed by sound-vibration signal ,was proposed. In this paper, firstly, the morphological filtering was used for background noise cancellation of sound signal, and the time scale alignment method based on kurtosis and envelope similarity were proposed to ensure the synchronism of the sound-vibration signal. Secondly, the Pearson correlation coefficient was used to construct two-dimensional image characteristic matrix for the expanded sound-vibration signal. Finally, the characteristic matrix was trained by utilizing CNN. Local Response Normalization (LRN) and core function decorrelation were utilized to improve the structure of CNN model, which reduced the bad impact of large data fluctuation of energy storage process on the diagnostic accuracy of circuit breaker energy storage mechanism. Compared with the traditional method, the proposed method has obvious advantages, whose total accurate rate up to 98.2 % and generalization performance is excellent.

show abstract

Research of circuit breaker intelligent fault diagnosis method based on double clustering

Abstract: According to the energy variation of the mechanical transmission in the process of circuit breaker operation which is characterized by acoustic and vibration signals, a new method of high Voltage circuit breaker mechanical fault diagnosis was proposed in this paper.

Cited by 14 publications

References 9 publications

A new modal analysis method applied to changing machine tool using clustering

A new modal analysis method applied to changing machine tool using clustering

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

Fault diagnosis method for energy storage mechanism of high voltage circuit breaker based on CNN characteristic matrix constructed by sound-vibration signal

Contact Info

Product

Resources

About