Aiming at the problems of data imbalance and low accuracy of classifier in the fault diagnosis of the internal circuit of intelligent appliances, a fault diagnosis method based on ADASYN algorithm over-sampling and random forest is proposed. The current signal is decomposed by wavelet packet, and the energy of each node in the last layer is extracted as the feature vector. The training data set is expanded by ADASYN algorithm, and the random forest fault diagnosis model is obtained and tested. The experimental results show that the ADASYN-random forest fault diagnosis model has high diagnosis accuracy for the internal circuit fault of intelligent household appliances, and has certain practical value and guiding significance for fault diagnosis.