基于Seq2Seq技术的输电线路故障类型识别方法

基于Seq2Seq技术构建了用于输电线路故障类型识别的深度学习模型，通过设置仿真算例验证了所提方法的有效性。首先，利用MATLAB/Simulink生成输电线路故障数据集；然后，基于Seq2Seq技术构建适用于故障数据时序型特征的深度学习模型；最后，以IEEE118节点系统为例对所提方法进行验证。仿真结果表明:所提方法能够适应输电线路故障的时序型特点，故障类型辨识准确率为100%。与其他故障类型识别方法相比，所提方法仅基于海量数据，不考虑电力系统具体结构，具有显著的优越性。

Fault Type Recognition Method of Transmission Line Based on Seq2seq Technology

Based on Seq2Seq technology， a deep learning model for transmission line fault type identification is constructed. The effectiveness of the proposed method is verified by setting simulation examples. Firstly， the transmission line fault data set is generated by using MATLAB/Simulink. Then， a deep learning model based on Seq2Seq technology is constructed for the time series characteristics of fault data. Finally， the proposed method is validated with the IEEE-118 bus system as an example. The simulation results show that the proposed method can adapt to the time series characteristics of transmission line faults， and the accuracy of fault type identification is 100%. Compared with other similar methods， the proposed method is only based on massive data， without considering the specific structure of power system， and has significant advantages.