Abstract
Mechanical fault diagnosis of a circuit breaker can help improve the reliability of power systems. Therefore, a new method based on multiscale entropy (MSE) and the support vector machine (SVM) is proposed to diagnose the fault in high voltage circuit breakers. First, Variational Mode Decomposition (VMD) is used to process the high voltage circuit breaker’s vibration signals, and the reconstructed signal can eliminate the effect of noise. Second, the multiscale entropy of the reconstructed signal is calculated and selected as a feature vector. Finally, based on the feature vector, the fault identification and classification are realized by SVM. The feature vector constructed by multiscale entropy is compared with other feature vectors to illustrate the superiority of the proposed method. Through experimentation on a 35 kV SF6 circuit breaker, the feasibility and applicability of the proposed method for fault diagnosis are verified.
Highlights
High voltage circuit breakers are important components used for protection and control purposes in power systems
Wu et al [21] applied Empirical Mode Decomposition (EMD) energy to extract the feature vector from the vibration signal of a circuit breaker, and the results showed that the method could identify different vibration signals and fault types
In the proposed extraction method based on Variational Mode Decomposition (VMD) and multiscale entropy, the VMD is taken as a preprocessor to decompose the vibration signal into an ensemble of band-limited intrinsic mode functions (IMFs) and the multiscale entropy is used to extract the fault features
Summary
High voltage circuit breakers are important components used for protection and control purposes in power systems. Wu et al [21] applied Empirical Mode Decomposition (EMD) energy to extract the feature vector from the vibration signal of a circuit breaker, and the results showed that the method could identify different vibration signals and fault types. In 2014, American researcher Konstantin Dragomiretskiy proposed a new method of signal processing called Variational Mode Decomposition (VMD) [22]. This method gets rid of cyclic-recursive screening to obtain the signal components. The experimental results demonstrate that the proposed method can extract the fault vibration signal’s feature vector quickly and efficiently. It can classify the circuit breaker’s states perfectly.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
