The invention discloses an intelligent fault diagnosis system and method for a large composite dry separator, and relates to the field of ore dressing machineries. The system comprises a detection module and an analysis and diagnosis module, wherein the detection module is used for detecting the temperatures of a bearing and a motor of the composite dry separator, the amplitude and frequency of the motor, the deformation of a beam and the noise decibel of the separator, and transmitting detection data to the analysis and diagnosis module; and the analysis and diagnosis module is used for analyzing the detection data, judging whether the composite dry separator has a mechanical fault or not, storing a fault waveform, predicting and judging a fault type, issuing a fault suggestion solution and sending alarm information. According to the intelligent fault diagnosis system and method for the composite dry separator, the safe operation of equipment can be guaranteed, accidents are preventedand reduced, the production efficiency is improved, and the economic loss of a coal preparation plant is reduced.