Fan Wang

During transformer operation, long-term vibration causes the winding to loosen axially. When hit by a short-circuit, the winding deforms to different extents. Thus, identifying early looseness faults in transformer windings is vital for power systems’ stability. To address issues including scarce vibration data across multiple load conditions for transformer winding looseness faults, inadequate extraction of two-dimensional spectrogram features, and the inability to boost recognition accuracy caused by overfitting during fault recognition model training, this study constructed a 10 kV power transformer vibration test platform. It measured the vibration signals on the box surface under various winding looseness conditions and built a time–frequency-domain vibration spectrum library for different load currents. Then, a fault identification model based on vibration spectra and ConvNeXt was constructed, and model verification and analysis were carried out. The results indicate that after training, the fault recognition accuracy of the spectrum containing three load conditions is comparable to that of a single load condition. The average recognition accuracy at six box-surface measuring points reaches 97.9%. Moreover, the ConvNeXt model outperforms the traditional ResNet50 by 1.2%. This new model effectively addresses overfitting and offers strong technical support for detecting different transformer winding looseness faults.

Transformer oil will inevitably be contaminated by impurity particles in the actual operation process; Carbon particles are the most abundant conductive particles in transformer oil. The adhesion behavior on the internal insulating surface will cause electric field distortion, which will pose a serious threat to the safe and stable operation of oil-immersed power equipment. To this end, this paper builds an experimental platform for simulating the adhesion behavior of carbon particles in transformer oil, studies the adhesion characteristics of carbon particles, and analyzes the influence of electric field, particle size, oil flow velocity, and other factors on the adhesion of carbon particles. The results show that: the DC electric field is the main factor driving the adhesion of carbon particles on the surface of epoxy resin (with the increase in electric field strength, the degree of adhesion of carbon particles firstly rises and then decreases); the smaller the size of the carbon particles, the easier it is to adhere, and the corresponding electric field strength is different for different sizes of carbon particles when the degree of adhesion is the largest; the velocity of the transformer oil will have a significant impact on the adhesion behavior of the carbon particles (with the increase in the flow velocity, the degree of adhesion of carbon particles firstly rises and then decreases). The research conclusion of this article is helpful in guiding the evaluation of insulation performance and the optimization of insulation structure design in the converter transformer valve-side bushing considering the phenomenon of particle adhesion.