Abstract: Apparatus and method for operating a machine with a tool, wherein the method includes capturing at least one operating data point for the machine and/or the tool, calculating at least one estimate value from the at least one operating data point based on an ML model, determining an anomaly in the form of a discrete-time anomaly value based on the at least one estimate value via a comparison with a predetermined comparison value for the at least one estimate and detection of a match for the estimate comparison, storing the discrete-time anomaly value in a memory and aggregating the trend in the anomaly value over time to form a smoothed anomaly value, comparing the smoothed anomaly value with at least one predetermined comparison value for the anomaly and detecting a match for the anomaly comparison, and outputting a control operation to the machine based on the smoothed anomaly value.