Transformers Fault Detection Using Artificial Intelligence Technique
An artificial recognition system of defective type for epoxy-resin insulation based transformers through acoustic emission (AE) from partial discharge (PD) experiment is proposed. Most of the PD detection methods could be performed only at the shutdown period of equipments. By using Acoustic Emission (AE), the real-time and online detection could be achieved. Therefore, in this paper a series of high voltage tests were conducted on prefaulty transformers to collect transformer mechanical data such as vibration from the faulty transformer. These vibration signals can be gathered with the help of accelerometer (50 kHz) which can be further used for recognition needed. The selected features can be extracted from the experimental AEásignals and used as input to the recognition system. According to these features, effective identification of their faulty types can be done using the proposed particle swarm optimization combined with neural network. To demonstrate the effectiveness and feasibility of the proposed approach, the artificial intelligence identification system is applied on both noisy and
noiseless circumstances,the recognition rates of the two being 80% and 86% respectively.