IOP Conference Series Materials Science and Engineering · 2018 · 10 citations · 9 references
EngineeringComputer ScienceElectrical EngineeringFeature EngineeringMachine LearningPower ElectronicsDc-ac InvertersDiagnosisDiagnosticsElectrical System DiagnosticsFault DetectionFault DiagnosisElectrical Fault DiagnosisFault Detection RateInverter Fault DiagnosisMachine Learning For Fault DetectionMachine Learning-based Fault DiagnosisOpen-circuit Fault DetectionRandom Forest ClassificationTime-domain Features
The inverter circuit is widely used, and the switching tube has the highest incidence of open circuit failure. In order to improve the recognition rate of the open circuit fault of the inverter circuit, this paper proposes a method to extract the output voltage, output current and input current time domain features and then use the Random Forest and K-Nearest Neighbor to identify the fault. In this paper, through the simulation of single-phase full-bridge inverter circuit, the open-circuit fault test of the switch tube is simulated, and the output voltage, output current and DC-side input current of each switch tube open-circuit fault are obtained, and then the time domain feature extraction is performed. The Random Forest and K-Nearest Neighbor are used for diagnostic comparison. The results show that the single-tube fault recognition rate can reach more than 96% and the highest fault recognition rate can reach 99.77%.
9
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Real-time human pose recognition in parts from single depth images
Jamie Shotton, Toby Sharp, Alex Kipman et al. · Communications of the ACM · 2013 · 2.1K citations
Face Alignment at 3000 FPS via Regressing Local Binary Features
Shaoqing Ren, Xudong Cao, Yichen Wei et al. · 2014 · 896 citations
Global refinement of random forest
Shaoqing Ren, Xudong Cao, Yichen Wei et al. · 2015 · 80 citations