Aiming at the problem that the traditional residual chi-square test can detect the fault but can’t identify the fault subsystem in an integrated GPS/Inertial navigation system, a fault diagnosis method based on support vector regression is proposed. The residual chi-square test is used to do real-time detection for the integrated navigation system. The support vector regression prediction model is constructed to realize the prediction of the inertial navigation system. The output difference between the system model and the prediction model is an auxiliary to diagnose the system fault source. The simulation results show that the method can fast and accurately identify the fault subsystem, and thus fault isolation and system reconfiguration can be done to ensure the performance of the integrated navigation system.