Cryocoolerplaysanextremelyimportantrolein thefield ofinfraredremote sensing. Thenor-maloperationandperformanceofthedetectorwillbeaffectedifthecryocoolerbreaksdown. Anewin-telligent fault diagnosis method for cryocooler has been proposed based on wavelet packet transform, genetic algorithm and SVM for rubbing fault. First,wavelet transform is applied to the vibration sig-nal,and the vibration signal is extracted in time domain. The evaluation factors of the combined fea-ture set are calculatedby using the distance evaluation technique,and the corresponding sensitive fea-tures are selected. Then,the parameters of SVM are optimized by genetic algorithm. Finally,the se-lected sensitive features are inputinto the optimizedSVM to identifydifferent machine operation states automatically. The effectiveness of the method is verified by the fault simulation test of the cryocooler. Experimental results show that this method can identify and locate the cryocooler rubbing fault accu-rately,andtheaccuracyis95%.