Abstract: Since to the feature of the magnetic control seam tracking signal is nonlinearly and not smooth, A signal extraction and analytical method of the system based on Hilbert Huang transform and Cohen nuclear magnetic control arc seam tracking sensor is propesed. The magnetic control to track the signal motivated by cycle is decomposed into several intrinsic mode functions from high frequency to low frequency component by using the empirical mode decomposition. On the basis of the Hilbert marginal spectrum of each component, using Cohen nuclear distribution of time-frequency transform to each component can effectively restrain cross terms and extract the real-time signal dynamic law reflecting magnetic control seam tracking. The test result manifest this method is contribute to reveal the time-frequency of interference source and frequency spectrum.