基于长短期记忆网络的短路电流过零点预测方法

Fast Prediction Method of Short-circuit Current Zero Based on an Algorithm of Long Short Term Memory

短路电流快速相控开断的关键与难点在于解决故障辨识和零点预测快速性与精准性之间的固有矛盾。为此,研究并提出一种基于长短期记忆网络(long short term memory,LSTM)算法的短路电流零点快速预测方法。搭建了相控装置试验平台,通过实时数字仿真(real time digital simulation system,RTDS)试验及短路故障录波试验对LSTM算法的电流预测能力进行了验证;研究并讨论了LSTM网络隐藏层节点数、采样窗口长度、故障起始相角、工频分量幅值、直流衰减时间常数以及信噪比等因素对零点预测误差的影响。仿真与试验结果表明,故障识别时间为0.3 ms,零点预测采样时间为3 ms,零点预测误差为±0.5 ms,LSTM方法能在保证预测精度与传统方法相当的条件下,显著缩短预测时间,提升预测快速性,为系统故障的快速开断提供理论依据和技术支撑。

The key and difficult point of fast phase controlled breaking of short circuit current is to solve the inherent contradiction between the rapidity and accuracy of fault identification and zero prediction.Therefore,we investigated and proposed a fast prediction method of short-circuit current zero crossing based on the long short term memory(LSTM)al-gorithm.A phase control device test platform was built,and the current prediction ability of the LSTM algorithm was verified by the RTDS test and artificial short-circuit fault recording test.Moreover,we studied and discussed the influ-ences of the number of nodes in the hidden layer of LSTM network,the length of the sampling window,the initial phase angle of the fault,the amplitude of the power frequency component,the DC attenuation time constant and the signal to noise ratio on the zero prediction error.The simulation and test results show that the fault identification time is 0.3 ms,the zero-prediction sampling time is 3 ms,and the zero-prediction error is±0.5 ms.Under the condition that the prediction accuracy is equivalent to that of traditional methods,LSTM method can be adopted to significantly shorten the prediction time and to improve the prediction rapidity.The results can provide a theoretical basis and technical support for the fast breaking of system faults.