It presents a transformer fault diagnosis method based on auxiliary classifier generative adversarial network(ACGAN)

sparrow search algorithm and backpropagation(SSA-BP).Firstly

it uses ACGAN algorithm to supplement the unbalanced data of transformer oil chromatography and generate high quality fault characteristic data.Secondly

it uses the sparrow search algorithm(SSA) to improve the backpropagation(BP) neural network.Based on SSA-BP algorithm

it reduces the high dimensional features

extracts the key information and optimizes the model parameters

and obtains the transformer fault diagnosis results.Finally

it carries out the simulation by practical examples.Simulation results show that the fault classification accuracy of the proposed method is 97.6%

which is 24.4% higher than that of the traditional method

which proves the effectiveness and practicability of the algorithm and model.