Monitoring device and method for detecting anomalies
A monitoring device for detecting anomalies on the basis of sensor data determined over time is provided, including an input interface to receive a new sensor data point, an analysis unit to determine a minimum reachability distance for the new sensor data point with respect to a selection of adjacent training data points and to determine a minimum position for the new sensor data point in a reachability diagram, to insert the new sensor data point in the reachability diagram after the minimum position and before the training data point having a greater reachability distance than the determined minimum reachability distance, to assign the new sensor data point to a particular cluster and to assign a status as normal or abnormal, and an output interface to output the assignment determined for the new sensor data point as the result of the anomaly detection.
1 . A monitoring apparatus for anomaly detection in a technical system, in which parameters which are relevant to the state of the system are measured by sensors continuously over time, comprising:
an input interface, configured in such a way as to receive a new sensor data point relating to the technical system,
an analysis unit, configured in such a way as
to ascertain for the new sensor data point a minimum reachability distance with respect to a selection of neighboring training data points, and
to ascertain for the new sensor data point a minimum position in the sequence of the training data points in a reachability graph, which was created by a density-based clustering function using predetermined training data points as input values and in which the sequence of the training data points is in ascending order based on an order of processing of the training data points and in which the reachability distance is indicated for each training data point,
to insert the new sensor data point in the reachability graph after the minimum position and before the training data point that has a greater reachability distance than the ascertained minimum reachability distance,
to assign the new sensor data point to a specific cluster according to the position of the data point in the enhanced reachability graph and to assign a status as normal or abnormal according to the minimum reachability distance, each cluster being assigned to a different operating state of the technical system, and
an output interface configure in such a way as to output the assignment ascertained for the new sensor data point in regard to an operating mode, and the indication of a status as normal or abnormal, as the result of the anomaly detection,
and to trigger an alarm function on the basis of the result of the anomaly detection.
2 . The monitoring apparatus as claimed in claim 1 , wherein the density-based clustering function is an “ordering-points-to-identify-the-clustering-structure” method, OPTICS method for short.
3 . The monitoring apparatus as claimed in claim 1 , configured in such a way as to apply the density-based clustering function to the reachability graph enhanced with the new sensor data point and to assign to the new sensor data point the cluster ascertained for it therefrom and the status.
4 . The monitoring apparatus as claimed in claim 1 , wherein the selection of the neighboring training data points contains all training data points that are at a predefined interval from the new sensor data point.
5 . The monitoring apparatus as claimed in claim 4 , configured in such a way as to assign a core distance having the value infinity to the new sensor data point if the number of neighboring training data points is less than a predefined number.
6 . The monitoring apparatus as claimed in claim 4 , configured in such a way as to ascertain for each training data point in the selection of the training data points a reachability distance from the new sensor data point and to assign the shortest of the ascertained reachability distances to the new sensor data point as the minimum reachability distance.
7 . The monitoring apparatus as claimed in claim 6 , configured in such a way as to ascertain in the reachability graph the position of that training data point from the selection of the training data points that has the shortest ascertained reachability distance as the predecessor position and to ascertain the next position as the minimum position for the new sensor data point.
8 . The monitoring apparatus as claimed in claim 6 , configured in such a way as to insert the new sensor data point at the end of the reachability graph if the reachability distance of each training data point arranged after the predecessor position in the sequence is less than the minimum reachability distance of the new sensor data point.
9 . The monitoring apparatus as claimed in claim 1 , configured in such a way as to perform the steps performed in the analysis unit for all new sensor data points received in a time window of predefined length or for a predefined minimum number of temporally successive new sensor data points, and to output as abnormal only if the ascertained assignments are consistent with a predefined rule.
10 . The monitoring apparatus as claimed in claim 9 , wherein one rule is a minimum number of new sensor data points detected as abnormal.
11 . The monitoring apparatus as claimed in claim 9 , wherein one rule is a rising number of new sensor data points detected as abnormal in successive time windows.
12 . The monitoring apparatus as claimed in claim 9 , which additionally has a user interface and is configured in such a way as to receive the length of the time window, the minimum number of new sensor data points or the type of rule.
13 . The monitoring apparatus as claimed in claim 1 , wherein a technical system is one or more machines or devices of an automation plant, a power distribution plant or a power generation or energy extraction plant.
14 . A method for anomaly detection relating to a technical system, in which parameters which are relevant to the state of the system are measured by sensors continuously over time, carried out by a monitoring apparatus, comprising:
receiving a new sensor data point relating to the technical system,
ascertaining for the new sensor data point a minimum reachability distance with respect to a selection of neighboring training data points, and
ascertaining for the new sensor data point a minimum position in the sequence of the training data points in a reachability graph, which was created by a density-based clustering function using predetermined training data points as input values and in which the sequence of the training data points is in ascending order based on an order of processing of the training data points and in which the reachability distance is indicated for each training data point,
inserting the new sensor data point in the reachability graph after the minimum position and before the training data point that has a greater reachability distance than the ascertained minimum reachability distance,
assigning a specific cluster to the new sensor data point according to the position of the data point in the enhanced reachability graph and assigning a status as normal or abnormal according to the minimum reachability distance, each cluster being assigned to a different operating state of the technical system, and
outputting the assigned status and/or the assigned cluster as the result of the anomaly detection, and
triggering an alarm function on the basis of the result of the anomaly detection.
15 . A computer program product, comprising a computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement a method comprising a nonvolatile computer-readable medium that can be loaded directly into a memory of a digital computer, comprising program code parts suitable for performing the steps of the method as claimed in claim 14 .