Method and device for monitoring a milling machine

An apparatus comprising:

• a processor;
• and
• memory,
• wherein the processor is configured to monitor a milling machine, the processor being configured to monitor the milling machine comprising the processor being configured to:
• deploy an untrained machine learning model for determination of one or more anomalies in time series data;
• obtain, by the untrained machine learning model, during operation of the milling machine, first time series data representing a rotational speed of a milling head of the milling machine and at least one further operating parameter of the milling machine;
• train the untrained machine learning model, during operation of the milling machine, based on the obtained first time series data;
• obtain, by the trained machine learning model, during operation of the milling machine, second time series data representing the rotational speed of the milling head of the milling machine and the further operating parameter;
• and
• determine, by the trained machine learning model, during operation of the milling machine, one or more anomalies in the second time series data, the determining of the one or more anomalies comprising determining a distribution over residuals and defining a domain for residuals of normal operation.