Coupling fault diagnosis method and system and storage medium

The embodiment of the invention provides a coupling fault diagnosis method and system and a storage medium, and the method comprises the steps: carrying out the data conversion of a sample of a source domain and a sample of a target domain based on a time-frequency change method, obtaining the respective frequency signals, carrying out the extraction through a depth feature extraction network, and obtaining the respective extraction features; performing global feature alignment on the extracted features of the source domain and the extracted features of the target domain, and performing local space structure alignment on the extracted features of the source domain and the extracted features of the target domain to obtain a pseudo-similarity relationship of samples of the target domain; training the sample of the source domain and the sample of the target domain to form a coupling fault diagnosis model of multi-label transfer learning; and identifying the to-be-detected coupling fault data by adopting the mult