IEEE Transactions on Instrumentation and Measurement · 2019 · 47 citations · 33 references
EngineeringElectrical EngineeringSystems EngineeringCondition AssessmentMachine LearningVibrationCondition MonitoringDiagnosticsFault DetectionFault DiagnosisSupport Vector MachinesVibration MeasurementBreakersEmpirical Mode DecompositionFault ClassificationFault IdentificationSupport Vector ClassificationSupport Vector Machine ClassificationVibration Data AnalysisVibration-based Diagnostics
Mechanical condition assessment of circuit breakers (CBs) in the power system, if correctly applied, can make an optimal decision on whether, where, and how to perform maintenance. This article presents a new approach to the detection and identification of CB's mechanical states, using its vibration data during switching operations. The morphological correlation coefficient (MCC), which can detect whether or not a fault is present in a CB, is introduced first. Then, a quantitative methodology to specify the specific fault type of the CB, i.e., the ensemble empirical mode decomposition (EEMD)-Hilbert marginal spectrum energy entropy (HMSEE), combined with a classifier [e.g., support vector machine (SVM)], is proposed. By using this approach, the mechanical condition of CBs can be reliably estimated. Some typical mechanical faults of a 12-kV vacuum CB were simulated in the test laboratory to evaluate the effectiveness of the proposed approach. The application in two field cases demonstrates the applicability of the proposed approach.
33
Norden E. Huang, Steven Long, Man‐Li C. Wu et al. · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · 1998 · 23.3K citations · Full text
Computing, Computational Engineering, Biomedical Signal Processing +16
Nonparametric Tests Against Trend
Henry B. Mann · Econometrica · 1945 · 16.7K citations
F. N. David, M. G. Kendall · Journal of the Royal Statistical Society Series A (General) · 1956 · 1.6K citations