A micro-Doppler frequency estimation and association algorithm of the space target based on the time-varying autoregressive (TVAR) model is proposed herein. The calculation time of the existing algorithms grows significantly with the problem size, and micro-Doppler frequencies of different scattering centres are associated incorrectly where the frequencies intersect. The echo of the space target is modelled by the TVAR model, then the TVAR coefficients and instantaneous frequencies are estimated through the fast sparse Bayes learning (SBL) algorithm, finally, the micro-Doppler frequencies of different scattering centres are associated in the frequency-frequency change rate domain. The effectiveness and rapidity of the proposed algorithm is demonstrated by simulation results.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.