Fault diagnosis method for medium-voltage modular multilevel converter

Abstract

The invention relates to a fault diagnosis method for a medium-voltage modular multilevel converter (MMC), which belongs to the field of power electronics, and comprises the following steps of: constructing a data set by using the collected capacitor voltage values of each sub-module and the current values of each bridge arm of the MMC, wherein the data set comprises normal operation state data and fault operation state data of sub-modules of the MMC; carrying out one-hot coding on the sample set according to the operation state of the modular multilevel converter to obtain a coding vector as a class label; performing parameter training on the training set by adopting a neural network and based on a BP back propagation algorithm to obtain a modular multilevel converter fault diagnosis model; and inputting the test set into an MMC fault diagnosis model, performing open-circuit fault diagnosis on each sub-module of the modular multilevel converter, and obtaining a fault type through matching with a class label. New devices such as sensors do not need to be introduced, and the system cost and complexity are not increased.

Description

technical field [0001] The invention belongs to the field of power electronics and relates to a fault diagnosis method for a medium-voltage modular multilevel converter. Background technique [0002] Modular multilevel converter (MMC), as a converter used in the medium and high voltage field, because of its good scalability, flexible switch state combination, superior voltage and current resistance and good output waveform Quality is getting more and more attention. Especially in the field of high-voltage flexible DC transmission and medium-voltage converter equipment for high-speed rail, it is more and more popular. However, due to the relatively large number of switches involved, the open circuit fault of the switch has also attracted people's attention. [0003] At present, with the development of modular multilevel converter technology, a variety of fault detection and location methods have been proposed. Some scholars have proposed a sub-module fault detection method ...

AI Technical Summary

Problems solved by technology

However, these methods are difficult to establish accurate mathematical models

Later, some scholars proposed to increase the hardware circuit detection equipment, but this method increased the cost and system complexity

In recent years, some scholars have proposed the use of machine learning for fault location, but only at the fault bridge arm level or fault type level, and cannot determine the specific location of the fault point.

Images