Permanent magnet motor short circuit fault prediction method and device

The invention discloses a permanent magnet motor short circuit fault prediction method and device, and the method comprises the steps: obtaining the current change trend of a current fundamental wave component in a set time under the actual operation condition of a current traction system; and in response to a condition that a difference value of the first and second high-dimensional correlation coefficients satisfies a preset condition, performing permanent magnet motor short-circuit fault prediction according to a current change trend, wherein the first high-dimensional correlation coefficient is obtained through calculation based on a joint distribution function constructed by the current between the inverter and the isolation contactor and all the influence factors, and the second high-dimensional correlation coefficient is obtained through calculation based on a joint distribution function, obtained through a Pair-Copula method, between all the influence factors related to the current. High-dimensional c