<p>Envelope analysis, one of the most widely used methods in the field of rotating machinery fault diagnosis, aims to approximate fault impact characteristics by analyzing the envelope of the filtered signal in the demodulation band. The demodulation band is essentially the carrier frequency band and the resonant frequency band of the mechanical system. However, since the resonant frequencies of different mechanical components vary and are often unknown, accurately identifying the carrier frequency band becomes the most significant challenge in the envelope analysis process. Currently, the mainstream research approach involves the use of various metrics to evaluate the band with the most fault information and then performing envelope analysis on this band. Although these methods have shown effectiveness in practical applications, they still have notable limitations. For example, when faults occur simultaneously in different bearings and gears, existing methods can identify only one carrier frequency band, and the identified bands often lack consistency across the same set of test data. To address these issues, this paper proposes a novel demodulation band selection method that can efficiently and accurately identify all faults when signals from multiple faulty components coexist. This method has been evaluated through bearing fault simulations and case studies, and its performance outperforms traditional methods such as spectral kurtosis and Autogram. It can effectively extract the characteristic spectra of all faulty components under multi-resonance conditions, demonstrating excellent anti-interference capability and efficiency advantages. Therefore, it holds significant engineering value in improving the accuracy of fault diagnosis.</p>