Abstract: [Objectives] In high-density traffic areas, the AIS signals of ships collision often occurs. As a result, the receiver often needs to separate and process the collision signal. Noise interference is often neglected in the previous studies of AIS signal separation. Traditional independent component analysis algorithms such as FastICA may have problems such as convergence failure when introducing noise components. To solve this problem, a separation algorithm S-RICA based on singular spectrum analysis(SSA) and RobustICA is proposed in this paper. [Methods] The Hankel matrix of single-channel AIS signal was processed by singular value decomposition and reconstructed by time series, and the optimal step size of each iteration of the separation matrix was calculated by using kurtosis contrast function to quickly obtain the optimal separation matrix. [Results] The simulation results show that the SMSE value of S-RICA is stable at about 1.5 when the signal length changes, while the SMSE of FastICA is very unstable. S-RICA has a bit error rate of 0.97×10-2 to 1.97×10-2 at a signal-to-noise ratio(SNR) of 0 to 9dB, an order of magnitude improvement over