Abstract <p>Condition monitoring of milling tools is crucial to achieve autonomous and resource-efficient production. It is, however, a challenging task due to the dynamic nature of the cutting process and the complex wear mechanisms. The majority of existing approaches is relying on data that is only accessible through additional instrumentation, such as cutting forces. Furthermore, high frequency data is often required. The current paper presents a novel approach for condition monitoring of milling tools using low-frequency machine-tool data. For the industrial-scale milling of titanium alloy, a decrease in signal roughness in servo-motor torque data is identified through exploratory data analysis. As a consequence, we propose a condition monitoring strategy that uses fractal analysis to quantify this effect. A threshold was set for the moving range of the fractal dimension to detect a significant drop and recommend tool exchange. For several milling experiments under identical conditions, tool exchange was recommended by our approach when the cutting tool is subject to significant damage, as documented in microscopy images, demonstrating consistency and robustness of the proposed approach. Additionally, only data stemming from sensors installed in standard machine tools in a relatively low frequency is required, leading to high industrial applicability.</p> Graphical abstract <p></p>