The theory of cyclostationary and its application are very important for the analysis and processing of a non stationary signal. The paper introduces second order cyclostationary statistics, with emphass on discussion of cyclic periodogram arithmetic. Comparing the time smoothed cyclic periodogram with the frequency smoothed cyclic periodogram, we found that the former is more useful to extract the feature of cyclostationary signals. The method has been applied to analyze the vibration signal of a rolling element bearing measured on a test bench, and proved to be effective. Meanwhile, we have compared it with traditional power spectral density analysis, and the results prove that the time smoothed cyclic periodogram is more available to diagnose the fault of a rolling element bearing. The theory of cyclostationary and its application are very important for the analysis and processing of a non stationary signal. The paper introduces second order cyclostationary statistics, with emphass on discussion of cyclic periodogram arithmetic. Comparing the time smoothed cyclic periodogram with the frequency smoothed cyclic periodogram , we found that the former is more useful to extract the feature of cyclostationary signals. The method has been applied to analyze the vibration signal of a rolling element bearing measured on a test bench, and proved to be effective. Meanwhile, we have compared it with traditional power spectral density analysis, and the results prove that the time smoothed cyclic periodogram is more available to diagnose the fault of a rolling element bearing.