The invention relates to an intelligent electric energy meter fault judgment method based on a BP neural network, and aims at solving the disadvantages that the present intelligent electric energy meter fault judgment technology is difficult to be accurate to fault judgment of circuit components and the detection efficiency and the accuracy are low. The method comprises the steps that all sets oftraining sample data and the corresponding fault type in case of fault of the intelligent electric energy meter are extracted; all sets of training sample data are normalized so as to acquire all setsof normalized training sample data; the number K of the neurons of the hidden layer of a neural network to be constructed is acquired according to the number N of the neurons of the input layer of the neural network to be constructed and the number M of the neurons of the output layer of the neural network to be constructed; the neural network is constructed; and the failure components corresponding to the fault of the intelligent electric energy meter are judged. The intelligent electric energy meter fault judgment method based on the BP neural network is suitable for fault detection of theintelligent electric energy meter.