A hybrid model for tool wear monitoring via physics-based and data-driven utilizing unscented Kalman Filter

Key Points

• Improved tool wear monitoring is achieved using a hybrid model that integrates data-driven approaches with physics-based methods.
• The unscented Kalman filter plays a crucial role in the hybrid model, enhancing monitoring accuracy through effective data assimilation.
• Observational analysis utilizes both physical models and data-driven techniques to refine wear prediction across various conditions.
• The significance of this work lies in its potential to optimize manufacturing efficiency through better tool management.