A deep learning-based identification method for complex working conditions of transformers

Abstract

The invention discloses a transformer complex working condition identification method based on deep learning. The method comprises the following steps that 1, original sample data is acquired; 2, theoriginal sample data is built into a data set with type identification, a data set without type identification and a data set of test data; 3, according to a certain time window, window obtaining andgrouping are conducted on the built data sets; 4, voltage and current sequence signals in the window are processed to obtain frequency spectrum data; 5, the frequency spectrum data is subjected to recurrent neural network training; 6, a trained recurrent neural network is tested and optimized; 7, field data is input to the optimized recurrent neural network for conducting identification and precise positioning of transformer complex working conditions. According to the method, by adopting the recurrent network, complex mixed faults can be accurately judged and precisely positioned, and the robustness and a practical level of transformer complex working condition identification are improved.

Description

technical field [0001] The invention belongs to the field of automation, in particular to an intelligent identification method for complex working conditions of a transformer applied in a fault information system. Background technique [0002] According to statistics, before 2005, the correct action rate of transformer protection was only 70% to 80%, which was far lower than the correct action rate (about 99%) of generator protection and line protection. A lot of theoretical technology and simulation test research have been carried out, and some progress has been made, which has significantly reduced the number of misoperations and refusals of transformer protection. For example, in 2009, the correct operation rate of differential protection of transformers above 220kV in my country reached 97.83%. However, transformer protection is still at a relatively low level, so it is particularly important to quickly and reliably identify inrush currents and internal faults as the key ...

AI Technical Summary

Problems solved by technology

The current methods for identifying inrush currents and internal faults (mostly based on the principle of second harmonic and waveform symmetry in engineering) have their own advantages and disadvantages, and finally did not form a perfect solution. In some complex scenarios: such as transformers airdropped in Internal faults or serious faults in the area, DC bias, saturation of the iron core to a certain extent, interference noise, etc., will cause malfunction or refusal of transformer protection

Images