Spectrum correlation (SC), as a typical demodulation algorithm, has been investigated for fault extraction by restraining interference components. However, SC ignores the uneven distribution of fault features in the entire frequency range, which makes the results vulnerable to interference components. To overcome these shortcomings, a novel robust modulation spectrum correlation (RMSC) gram is proposed. Firstly, the signal is demodulated into a bi-spectral map display containing fundamental and modulation frequency through RMSC, and utilize finite impulse response filter on fundamental frequency to obtain RMSC subbands. Subsequently, the fault feature index of subbands under healthy and fault conditions is calculated, and utilize its failure signature ratio (FSR) to generate RMSC gram. Finally, the RMSC with the maximum FSR is selected as optimal subband, and envelope analysis is executed on subband to obtain fault features. Simulations and experiments are performed to validate the effectiveness of RMSC in comparison with the stateof-the-art methods.