The feature extraction and pattern recognition of partial discharge signal are key steps of equipment condition assessment and fault diagnosis. Time-frequency analysis on PD pulse can extract more comprehensive and effective information from waveform. However

the cross interference terms have the influence on the commonly used timefrequency analysis method. Consequently

we put forward a method of joint time-frequency analysis on PD pulse signal based on EEMD and Cohen’s class

studied the end effect of EEMD

and proposed an extending technology based on SVR-regression fitting method. Moreover

the exponential attenuation oscillating function added with Gaussian white noise and narrow band interference was used to simulate the high frequency current PD signal of power equipment. The results show that this method can accurately identify the characteristic PD pulse. It can not only guarantee the time-frequency concentration of effective signal

but also inhibit the influence of IMFs’ cross interference terms. Finally

we prove the effectiveness and practicality of this method by applying it to analyze the PD signal which is measured in substation.