Fault diagnosis of a CNC hobbing cutter through machine learning using three axis vibration data.

This research presents a novel approach to fault diagnosis for CNC hobbing cutters using machine learning techniques, leveraging three-axis vibration data to ensure machining precision and tool reliability. Traditional methods of tool monitoring are insufficient for real-time and complex machining environments, prompting the integration of automated machine learning models. A robust dataset was collected from a CNC hobbing machine, capturing vibration signals under healthy and faulty tool conditions. Statistical features, including Root Mean Square (RMS), Crest Factor, and Kurtosis, were extracted from the vibration data for model training. Various machine learning algorithms, including Decision Trees, Efficient Linear models, Neural Networks, and Ensemble methods, were evaluated for their classification accuracy. Among these, the Ensemble model achieved perfect classification accuracy (100 %) with minimal computational cost, making it optimal for real-time applications. Explainable AI techniques, such as LIME and Shapley values, were employed to interpret model predictions, enhancing the system's transparency and reliability. The proposed framework demonstrated superior performance compared to existing methodologies in the literature, addressing key gaps such as overfitting, data quality, and model explainability. Real-world deployment challenges, including diverse operating conditions and generalizability across machines, were also discussed, with recommendations for incorporating multi-sensor data and transfer learning approaches in future research. This study establishes a foundation for predictive maintenance in CNC machining, significantly reducing downtime and improving operational efficiency through precise fault diagnosis in hobbing cutters.