Petrochemical unit rotating machinery fault diagnosis method, device, equipment and medium

The invention discloses a petrochemical unit rotating machinery fault diagnosis method, device, equipment and medium, and the method comprises the steps: collecting the mechanical rotation diagnosis data of a petrochemical unit through a sensor, carrying out the non-dimensionalization of the diagnosis data, and extracting the non-dimensionalization characteristic indexes; according to the extracted mutual dimensionless characteristic indexes, calculating an optimal index determined in advance according to characteristic sensitivity analysis, and taking the optimal index as a mutual dimensionless characteristic index of fault analysis; a pre-constructed adversarial network model is adopted to carry out capacity increasing on the obtained mutual dimensionless characteristic indexes, and capacity increasing characteristic indexes are obtained; and taking the capacity-increasing characteristic indexes as input of a pre-constructed diagnosis model, obtaining diagnosis result output of the subsequences, and outputt