Bearings represent crucial components within rotating machinery, and unexpected failures can lead to significant damage and unplanned breakdowns. This paper introduces a novel approach to diagnose bearing faults under variable working conditions, leveraging the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Sequential Backward Selection (SBS). CEEMDAN automatically selects intrinsic mode functions (IMFs) from vibration and current signals to establish a comprehensive set of health indicators. Subsequently, the SBS algorithm identifies the most pertinent indicators for different bearing failure modes. The accuracy of the proposed method is evaluated on both vibration and electrical signals using data from a dedicated test bench at the Signal and Industrial Process Analysis Laboratory (LASPI). Results demonstrate the effectiveness of the proposed method in accurately identifying and classifying bearing faults across various working conditions, utilizing both types of signals. This approach holds promise for real-world industrial applications, offering a reliable method for condition monitoring and Diagnostics in bearing systems.