As an part of the electric energy metering device, the accuracy and reliability of the transformer in operation are directly related to the fairness and justice of electricity trading. To accurately evaluate the measurement performance status of the transformer in operation, an attention mechanism is proposed to optimize the Seq2Seq network to predict the fault status of the transformer. By combining the attention mechanism, Seq2Seq network and two-way short-term memory network, sequential semantics are mined from the dynamic data of the transformer collected online, and an accurate analysis model for the online measurement status of the transformer is established. Apply external electric field interference to the capacitor voltage transformer in operation under laboratory conditions and use the model to conduct error analysis on the operation data of the transformer after the interference. The test results demonstrate that the proposed method has a good performance in the aspect of recognition rate in measuring anomaly prediction.
YAMADAT, KON S, HASHIMOTON, et al. ECT evaluation by an error measurement system according to IEC 60044-8 and 61850-9-2[J]. IEEE Transactions on Power Delivery, 2012, 27(3): 1377-1384.
[4]
ARIAS VELÁSQUEZR M, MEJÍA LARAJ V. Current transformer failure caused by electric field associated to circuit breaker and pollution in 500 kV substations[J]. Engineering Failure Analysis, 2018, 92: 163-181.
[5]
LEIT, FAIFERM, OTTOBONIR, et al. On-line fault detection technique for voltage transformers[J]. Measurement, 2017, 108: 193-200.
[6]
ÇAYCıH. A complex current ratio device for the calibration of current transformer test sets[J]. Metrology and Measurement Systems, 2011, 18(1): 159-164.
MEDEIROSR P, COSTAF B. A wavelet-based transformer differential protection with differential current transformer saturation and cross-country fault detection[J]. IEEE Transactions on Power Delivery, 2018, 33(2): 789-799.
[12]
RONANKID, WILLIAMSONS S. Evolution of power converter topologies and technical considerations of power electronic transformer-based rolling stock architectures[J]. IEEE Transactions on Transportation Electrification, 2018, 4(1): 211-219.
PRZYSTUPAK. Selected methods for improving power reliability[J]. PRZEGLĄD ELEKTROTECHNICZNY, 2018, 1(12): 272-275.
[15]
PRZYSTUPAK, KOZIELJ. Analysis of the quality of uninterruptible power supply using a UPS[C]//2018 Applications of Electromagnetics in Modern Techniques and Medicine (PTZE). Racławice: IEEE, 2018: 191-194.
[16]
TYLAVSKYD J, HEQ, MCCULLAG A, et al. Sources of error in substation distribution transformer dynamic thermal modeling[J]. IEEE Transactions on Power Delivery, 2000, 15(1): 178-185.
[17]
MAZUREKP. The intensity of electromagnetic fields in the range of GSM 900, GSM 1800 DECT, UMTS, WLAN in built-up areas[J]. PRZEGLĄD ELEKTROTECHNICZNY, 2018, 1(12): 204-207.
[18]
SUNS, PRZYSTUPAK, WEIM, et al. Fast bearing fault diagnosis of rolling element using Lévy Moth-Flame optimization algorithm and Naive Bayes[J]. Eksploatacja i Niezawodność-Maintenance and Reliability, 2020, 22(4): 730-740.