Abstract: In order to solve the problem that the failure rate of downhole fan is high and the failure trend is difficult to predict effectively, the uncertainty reasoning method of cloud model is adopted to study the prediction of failure rate of mine fan. By exploring the relationship between the fan aging status and the two evaluation parameters of external influencing factors and the development trend of fan failure, a two-factor cloud prediction model of the fan aging index-external influencing factors evaluation based on the cloud generator was constructed, and the implementation steps of the cloud prediction model of fan failure were illustrated. The application results show that the model has high prediction accuracy and can effectively solve the problems of randomness and uncertainty in the prediction of failure rate of downhole fan.