A High-Voltage Circuit Breaker Condition Assessment Method using the Vibration Fingerprint based on VMD-EM method

Condition Assessment of Power Circuit Breakers Based on Machine Learning Algorithms

“…Another series of vibration events are evident after the contacts are closed. Operation of the CB (making and breaking main or arcing contacts) yields highspeed movement and high-intensity impacts resulting in the acceleration from zero to several meters per second in tens of milliseconds [2]. This makes the extraction of the exact closing time as defined by the standard, as well as changes in the total motion of the moving contacts (stroke), almost impossible.…”

“…Due to fact that the CB is an electro-mechanical system, the energy stored in the operating mechanism is released and transmitted to the moving contacts through the mechanical elements and linkages in a very short time frame. The high energy of the moving mechanical parts transfer results in extrusion, friction and impact of components and subassemblies of the CB [2]. The mechanical nature of the CB over time results in a potential decrease in performance.…”

“…The timefrequency domain has been utilized in the form of Continues Wavelet Transform (CWT) and Discrete Wavelet Transform (DWT) [9], [10] and Hilbert Huang Transform (HHT) [11], [12]. Since the non-stationary nature of the CB vibration fingerprint, some of the provided approaches in the literature are based on spectral decomposition of the signal based on Empirical Mode Decomposition (EMD) [13], Ensemble Empirical Mode Decomposition (EEMD) [14], Local Mean Decomposition (LMD) [15], ensemble empirical mode decomposition with adaptive noise (CEEMDAN) [16] and Variable Mode Decomposition (VMD) [2], [17]. Combining previously mentioned frequency and time-frequency methods with fields such as chaos theory, some authors based their work on fractal dimension [14], [18], [19] or ergodic quantities such as Largest Lyapunov exponent [20] or information entropy [21], [22].…”

High Voltage Circuit Breaker Vibration Signature Indices Evaluation for Condition Assessment

“…The mechanical nature of the HVCB results in the movement and collision of its subassemblies. All movement and collisions create series of superimposed percussion waves, which contains rich information about the health and condition of mechanical subassemblies of the HVCB [6], [7], [8]. The imperative is to obtain indices that would reliably reflect the condition of the HVCB.…”

“…The third group consists of methods that do not use previously mentioned methods as a base. In this group, the following methods can be included: local mean decomposition (LMD), empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), or variational mode decomposition (VMD) [15], [16], [6]. Very few authors in relevant literature address the HVCB condition assessment methods based on the chaos theory.…”