CAJ | 학술논문

利用 Elman 神经网络自适应性强的优势，将其应用于高压电力计量系统故障诊断中。对计量系统的8个运行参数提取故障信息作为网络的输入值，以4位二进制数表示正常情况和9种主要故障类型，用采集得到的样本对网络进行训练，并选取4种故障类型进行网络测试，结果表明，Elman 神经网络模型对高压电力计量系统故障有很好的辨识和诊断效果。
이용 Elman 신경망락자괄응성강적우세，장기응용우고압전력계량계통고장진단중。대계량계통적8개운행삼수제취고장신식작위망락적수입치，이4위이진제수표시정상정황화9충주요고장류형，용채집득도적양본대망락진행훈련，병선취4충고장류형진행망락측시，결과표명，Elman 신경망락모형대고압전력계량계통고장유흔호적변식화진단효과。
Elman neural network will be able to adopted in the fault diagnosis of high voltage electric power metering system according to the advantage of the great adaptivity. Information in 8 operation parameters of metering system will be extracted to be taken as the input values of the neural network,and a 4 - bit binary number will be adopted to re-present the normal circumstance and 9 main fault types. Then the collected samples are used to train Elman network and 4 fault types will be selected to test the network. The results show that the Elman network model can effectively diagnose the fault of high voltage electric power metering system.