On-Line Detection Method of Transformer Measurement Error Based On BP Neural Network

The offline detection method for the measurement error of the transformer can not truly reflect the actual operating conditions of the transformer. This paper proposes an online detection method for the error of high-voltage measurement transformer. In this method, the inter-frequency signal is applied to the secondary side of the transformer, and the transmission relationship between the primary side and the secondary side of the transformer is established according to the inter-frequency voltage and current on the secondary side. The BP(back propagation) neural network algorithm is used to obtain the measurement error of the transformer. The method can reflect the actual parameters of the transformer under online operation, and only needs to be measured on the secondary side of the transformer. The method is simple, safe and accurate. The simulation results verify the accuracy of the proposed method and provide a theoretical basis for on-line detection of high voltage voltage and current transformer measurement errors.