Bearing fault diagnosis based on ensemble empirical mode decomposition and t-distribution Quantum Particle Swarm optimized XGBoost

To improve the accuracy and robustness of bearing fault diagnosis in rotating machinery, this paper proposes a fault diagnosis method based on Ensemble Empirical Mode Decomposition (EEMD) and a t-distribution mutation Quantum Particle Swarm Optimization–optimized Extreme Gradient Boosting (tQPSO–XGBoost) model. First, EEMD is applied to decompose the collected vibration signals into several physically meaningful Intrinsic Mode Functions (IMFs). Through correlation analysis, noise and interference components are removed, and the signals are reconstructed to highlight fault-related features. Then, typical time-domain and frequency-domain features are extracted from the reconstructed signals. Principal Component Analysis (PCA) is employed for feature screening and dimensionality reduction to eliminate redundant information and enhance feature sensitivity. Finally, a t-distribution mutation strategy is introduced to improve the Quantum Particle Swarm Optimization (QPSO) algorithm, which adaptively searches and optimizes the hyperparameters of the XGBoost model for intelligent recognition of bearing health states. Experimental results demonstrate that, compared with conventional PSO–XGBoost, GWO–XGBoost, and standard XGBoost methods, the proposed EEMD–tQPSO–XGBoost method exhibits significant advantages in convergence speed, classification accuracy, and robustness. This study provides an efficient and stable solution for intelligent bearing fault diagnosis under complex working conditions.