Modular multi-level DC power transmission system fault identification method based on support vector machine

Abstract

The invention provides a modular multi-level DC power transmission system fault identification method based on a support vector machine. The method is suitable for fault identification of a modular multi-level DC power transmission system. According to the method of the invention, characteristic values of a training sample are acquired, and the characteristic values are classified to a three-phasebalance fault and an imbalance fault; a corresponding fault identification model is established; then the characteristic valve of the to-be-identified power system is acquired; after fault type dividing, normalization processing is performed in a corresponding fault identification model; and finally the fault type of the system is identified through a method of the support vector machine, and thefault type is output. Actual verification results show a fact that the fault type which is identified according to the fault identification model is same with the actual fault type and low identification time is realized; quick, accurate and high-efficiency technology support can be supplied for fault testing of the modular multi-level DC power transmission system.

Description

technical field [0001] The invention relates to the field of flexible direct current transmission, in particular to a support vector machine-based fault identification method for a modular multilevel direct current transmission system. Background technique [0002] Due to its unique advantages, Modular Multilevel Converter Based High Voltage Direct Current (MMC-HVDC) has become a development trend in the field of voltage source converter HVDC transmission. [0003] During the actual operation of MMC-HVDC, many factors will cause the voltage imbalance of the AC system. From the perspective of the DC side, the single-pole ground fault increases the ground voltage of the DC non-fault pole and the phase voltage of the AC side of the converter station; the single-pole ground fault will cause serious overcurrent phenomena in the bridge arm of the converter station; Pole disconnection faults will lead to a large DC voltage change rate in the rectifier station, causing severe DC ov...

AI Technical Summary

Problems solved by technology

However, if the current MMC-HVDC system in my country operates under abnormal working conditions or the system fails, it is difficult to accurately determine the fault type and location of the system due to the characteristics of the fault itself, which is harmful, complex, and difficult to identify.

[0004] At present, in the aspect of fault identification of MMC-HVDC system, it is mainly to analyze the basic principle of MMC-HVDC system, typical fault characteristics, MMC sub-module fault identification, DC fault identification and construct corresponding protection and control strategy from the perspective of electrical mechanism. The research to realize fault identification is almost still in the blank

Images