A unique model for multi-sensor monitoring tool wear in smart and sustainable machining of stone

In the stone-cutting process, the chosen tool types are diamond mills and discs, whose durability and efficiency are influenced by numerous factors. Due to the abrasive, inhomogeneous, and anisotropic nature of stone, tool wear rates lead to increased cutting forces and accelerations and negative impacts on workpiece surface quality and material integrity. Therefore, sensor-based monitoring of stone cutting is essential to minimise waste, reduce tool costs, and enhance process productivity in stone-cutting operations. This study aims to present unique and simple relationships to be used in artificial intelligence processing systems in the stone cutting of tiles. This will be achieved by correlating the features of sensors’ signals with the process parameters of stone cutting. The results demonstrate that the proposed models can be used for the cutting of tiles through diamond discs and mills. The predictive capability of this model surpasses 87%. A strong correlation (Spearman’s correlation coefficient higher than 80%) is established between tool wear and the diamond grit protrusion height. This study demonstrated how a smart multi-sensor monitoring system in use, which is based on the proposed regression relationships that are general for tile cutting and simple, can reliably detect tool wear, facilitating real-time diagnosis crucial for predicting end-of-tool-life. This enables effective automation in the cutting of stone material parts. At the same time, the monitoring of the diamond tool wear based on cutting force monitoring allows for controlling the energy involved in the process, thus rendering the process more sustainable.