The second order statistics for cyclostationary signals were introduced, and their performance were discussed. It especially researched the time lag characteristic of the cyclic autocorrelation function and spectral correlation characteristic of spectral correlation density function. It was pointed out that those functions can be available to extract the time vary information of the kind of non stationary signals. Using the relations of time lag cyclic frequency and frequency cyclic frequency independently, vibration signals of a rolling element bearing measured on test bed were analyzed. The results indicate that the second order cyclostationary statistics might provide a powerful tool for the feature extracting and fault diagnosis of rolling element bearing. The second order statistics for cyclostationary signals were introduced, and their performance were discussed. It was pointed out that those functions can be available to extract. It is researched the time lag characteristic of the cyclic autocorrelation function and spectral correlation characteristic of spectral correlation density function. the time vary information of the kind of non stationary signals. Using the relations of time lag cyclic frequency and frequency cyclic frequency independently, vibration signals of a rolling element bearing measured on test bed were analyzed. The results indicate that the second order cyclostationary statistics might provide a powerful tool for the feature extracting and fault diagnosis of rolling element bearing.