Chirp signals show energy aggregation in the fractional Fourier domain (FrFD) which can be used to estimate the parameter of the signals. In this paper, a parameter estimation method for multi-component chirp signal which corrupted by white Gaussian noise is proposed based on the discrete fractional Fourier transform (DFrFT) and the differential evolution (DE) algorithm. The proposed algorithm uses the DE algorithm instead of the conventional fine search algorithm to detect the peak of the signals in the FrFD. The paper simulated the influence of the noise and the resolution of the proposed algorithm. The results of the simulation show the proposed method does not only improve the estimation accuracy of the peak coordinate, but also reduces time consuming.