In the SINS/GPS integrated navigation system,the measurement signals provided by GPS are easily disturbed,which leads to the degradation of filtering accuracy.To solve this problem,a fault-tolerance method for the integrated navigation system based on EM algorithm is proposed.By establishing a two-dimensional Gaussian mixture model for each component of the measurement noise,an indicator variable is introduced to indicate the probability of measurement value sampling from abnormal distribution.Based on the state equation of the system,the state estimate of the last moment and the measurement value of the current moment,the EM algorithm is utilized to calculate the maximum likelihood estimate of the true measurement at the current moment.Besides,the sequential filtering algorithm is applied to finely detect and correct the measurement value of each component.Experiment aboard cars shows that the proposed method can effectively improve the fusion accuracy and reliability of the SINS/GPS integrated navigation system in the case of GPS signal anomaly.