The dynamic characteristics of rolling element bearings are strongly related to their geometric and operating parameters, most importantly the bearing unbalance. Modern condition monitoring necessitates the use of intrinsic mode functions (IMFs) to diagnose unbalance bearing failure. This paper presents a Hilbert–Huang transform (HHT) method to diagnose the unbalanced rolling bearing faults of rotating machinery. To initially reduce the noise levels with slight signal distortion, the noises of the sample in normal and unbalanced fault states are measured and denoised using the wavelet threshold approach. The complex vibration signatures are decomposed into finite IMFs with ensemble empirical mode decomposition technique. Fast Fourier techniques are employed to extract the vibration responses of bearings that are artificially damaged using electrochemical machining on a newly established test setup for rotor disc bearings. The similarities between the information-contained marginal Hilbert spectra can be used to diagnose rotating machinery bearing faults. The data marginal Hilbert spectra of Mahalanobis and cosine index are compared to determine the fault indicator index’s similarity score. The HHT model’s simplicity enhanced the precision of diagnosis correlated to the results of the experiments with weak fault characteristic signals. The effectiveness of the proposed approach is evaluated with several theoretical models from the literature. The HHT approach is experimentally proven with unbalance diagnosis and capable of classifying marginal Hilbert spectra distribution. Because of its superior time-frequency characteristics and pattern identification of marginal Hilbert spectra and fault indicator indices, the newly stated HHT can process nonlinear, non-stationary, and even transient signals. The findings demonstrate that the suggested method is superior in terms of unbalance fault identification accuracy for monitoring the dynamic stability of industrial rotating machinery.