The fault characteristics of complex equipment are characterized by uncertainty, nonlinearity and so on. For the uncertain fault prediction, we design a method of fault prediction，which combines intuitionistic fuzzy sets with grey model to predict fault. The new method uses the membership function to describe the normal system with the normal intuitionistic fuzzy sets and the abnormal system with the abnormal intuitionistic fuzzy sets, uses grey model to calculate predictive value, and uses membership function to calculate the membership degree. Then the fault prediction is implemented by calculating the closeness degree of predicted value of the normal membership degree with normal and abnormal intuitionistic fuzzy subset. This method predicts the fault of the three-tank-system when T2 tank starts to increase or decrease and the crack of the UH-60 planet gear plate when it starts to increase. The feasibility of the proposed method is verified by experiments, which can predict the failure of the system in time.