Motor turn-to-turn short circuit fault online diagnosis method and system based on deep learning

The invention relates to the technical field of motor detection, in particular to a motor turn-to-turn short circuit fault online diagnosis method and system based on deep learning. The method comprises the following steps of: S1, solving an effective value of a three-phase current by using a motor three-phase current amplitude input by a sensor; s2, based on the three-phase current effective value of the motor, carrying out three-phase current balance analysis, and extracting a negative sequence current; s3, performing short-time Fourier transform on the negative-sequence current, and comprehensively drawing all spectrograms within a certain time length into a negative-sequence current spectrogram; s4, inputting the negative-sequence current spectrogram into an image classification model for diagnosing the turn-to-turn short circuit fault of the motor, and carrying out the diagnosis of the turn-to-turn short circuit fault of the motor; and S5, outputting a fault diagnosis result. The motor turn-to-turn short