基于行波解析分析的柔性直流输电线路故障智能检测方法OA北大核心CSTPCD

The lack of fault data is an important reason restricting the application of data-driven fault detection methods.To solve this problem,this paper propose an intelligent fault detection method of flexible HVDC line based on travelling wave(TW)analysis.Based on the prior experience of TW analytic expression,training samples are generated to effectively express the main characteristics of the internal and external fault TW.A multi-layer perception(MLP)model is constructed to establish the mapping relationship between the wave characteristics and the fault location and then output the fault detection result.Finally,a two-terminal flexible DC transmission system model is built in PSCAD/EMTDC,and the simulation samples are generated to test the trained model.The results show that this method does not rely on a large number of historical fault data.Based on the knowledge in the relay protection field of TW analytic expression,the TW characteristics is extracted and the internal and external faults of the DC line are accurately identified.This method has strong tolerance to fault resistance,and provides a feasible way to solve the problem that the traditional model is subject to historical fault data.