Fault detection and estimation method and system based on migration type generation model, and medium

The invention belongs to the field of industrial fault diagnosis, and discloses a fault detection and estimation method and system based on a migration type generation model, and a medium, and the method comprises the steps: selecting a normal sample set, carrying out the data preprocessing, and constructing a fault sample; defining a normal domain and a fault domain; constructing a generative adversarial network framework to enable a generator and a discriminator to perform iterative training; after training is completed, the generator reconstructs a normal sample, and migrates a fault sample to a normal domain to obtain a generated sample; the discriminator performs binary decision on the normal samples and the generated samples and judges the probability that the generated samples meet the distribution of the normal samples; calculating a fault detection and estimation index to obtain a difference value between a normal sample and a fault sample, and determining a normal domain threshold by calculating a t