Single-phase half-bridge five-level inverter switching tube open-circuit fault diagnosis method

Abstract

The invention discloses a single-phase half-bridge five-level inverter switching tube open-circuit fault diagnosis method, which belongs to the field of power electronic circuit fault diagnosis, and comprises the steps of building a semi-physical experiment platform taking a DSP controller and an RT-LAB real-time simulator as cores, and selecting an output side voltage as a fault signal variable, extracting a fault feature vector by using empirical mode decomposition, extracting a Hilbert-Huang transform time-frequency diagram of the fault feature vector, and converting the voltage signal into diagram data to obtain time-frequency diagram fuzzy sets corresponding to different fault types, fusing the time-frequency diagram fuzzy sets of the same fault type to obtain a fused image retaining more fault features, and inputting the fused images corresponding to all the fault types into a deep convolutional neural network for training and testing to obtain a fault diagnosis result. The method can improve the accuracy and stability of single-phase half-bridge five-level inverter fault diagnosis, and can be extensively applied to fault diagnosis of other power electronic equipment.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of power electronic circuits, and more specifically relates to a method for diagnosing an open-circuit fault of a switch tube of a single-phase half-bridge five-level inverter. Background technique [0002] At present, with the increase in the number of power electronic switching devices and circuit complexity, the signal data obtained in the long-term monitoring process is generally a large amount of data, and the current traditional signal-based feature extraction methods generally do not work when dealing with a large amount of signal data. Compress the amount of data by sampling, or directly discard part of the signal details to generate a small-scale data set, and then use it for subsequent training and learning and establish a fault diagnosis model. In addition, the signal-based fault diagnosis method is extremely slow when processing a large amount of signal data, and the diagnosis method oft...

AI Technical Summary

Problems solved by technology

In addition, the signal-based fault diagnosis method is extremely slow when processing a large amount of signal data, and the diagnosis method often produces invalid learning and weak generalization problems when training and learning a large amount of feature data, so that it cannot effectively identify faults

Images