This paper initial on the prediction method of transmission line icing risk. In view of the problem of poor accuracy in the existing disaster warning methods for the hazards of icing on the transmission lines, the prediction method of Transmission line icing risk based on micro-meteorological feature extraction and fuzzy inference is proposed. Firstly, the icing mechanism of transmission lines is analyzed to find out the factors that affect the hidden danger of icing. Then, the micro-meteorological features of transmission lines are extracted based on the fast search clustering algorithm of peak density, and the early warning of icing thickness is realized based on the fuzzy inference theory. Finally, combined with the prediction data of ice thickness, a four level early warning mechanism is set up to establish a real-time ice thickness early warning model. The experimental results show that the difference between the predicted icing thickness and the actual thickness of the proposed method is less than 0.5 mm, and the warning level is consistent with the actual level, which is superior to the comparison method and has better application effect.