A method for detecting an anomaly in time series sensor data. The method may include identifying a noisiest cycle from the time series sensor data; for an evaluation of the noisiest cycle indicative of the anomaly being detected at a confidence level above a threshold, providing an output associated with the noisiest cycle as being the anomaly; and for the evaluation of the noisiest cycle indicative of the anomaly being detected at the confidence level not above the threshold: identifying a cycle from the time series sensor data having a most differing shape; and providing the output associated with the cycle having the most differing shape as being the anomaly.

A method for monitoring failure tolerance for an automation installation is disclosed. The automation installation operates a process via a controlled system. At least two control apparatuses alternately regulate the controlled system in a control mode by outputting control outputs and failure of the currently regulating control apparatus prompts changeover to another of the control apparatuses. During the changeover, the controlled system continues to be operated in controller-less fashion for a down time. At least one operating point for the controlled system that is possible in control mode is ascertained. Controller-less operation is respectively simulated for each operating point for the duration of the down time. A state trajectory setting out from the operating point is ascertained for the controlled system and a check is performed to determine whether the state trajectory fails to meet a predetermined safety criterion. A predetermined protective measure is initiated to avoid the operating point.

A method for detecting an anomaly in time series sensor data. The method may include identifying a noisiest cycle from the time series sensor data; for an evaluation of the noisiest cycle indicative of the anomaly being detected at a confidence level above a threshold, providing an output associated with the noisiest cycle as being the anomaly; and for the evaluation of the noisiest cycle indicative of the anomaly being detected at the confidence level not above the threshold: identifying a cycle from the time series sensor data having a most differing shape; and providing the output associated with the cycle having the most differing shape as being the anomaly.