Machine learning-based bearing fault detection using statistical feature engineering and explainable XGBoost classification

Accurate and timely detection of bearing faults is critical for ensuring the reliability and safety of rotating machinery in industrial environments. This study investigates the application of machine learning techniques for classifying ten different types of bearing faults using features extracted from vibration signals. Among various classifiers evaluated, the XGBoost algorithm demonstrated superior performance. Through a combination of standard signal preprocessing, hyperparameter optimisation via GridSearchCV, and comprehensive model evaluation using accuracy, F1-score, and confusion matrix analysis, the optimised XGBoost model achieved a high classification accuracy of 95.48%. Notably, fault types such as IR_007_1, IR_014_1, and OR_007_6_1 were classified with perfect precision and recall. While minor misclassifications occurred primarily between ball and outer race faults due to overlapping signal characteristics, the overall confusion matrix underscored the model’s strong generalisation and class discrimination capabilities. Additionally, feature importance analysis highlighted kurtosis, standard deviation (SD), and mean as the most influential statistical descriptors, with kurtosis emerging as the dominant factor for distinguishing impulsive fault characteristics. These findings affirm the efficacy of XGBoost in bearing fault classification and emphasise the diagnostic value of carefully selected time-domain features. The results suggest strong potential for deploying such models in real-time condition monitoring and predictive maintenance systems. Future research may explore integrating deep learning or hybrid ensemble methods to further enhance diagnostic accuracy in more complex or noisy fault scenarios.