Intelligent monitoring system and method for building predictive models and detecting anomalies
First Claim
1. A method for detecting an anomaly in data originating from a component used in an industrial process, the method comprising steps of:
- providing predictive models in which at least one of the predictive models corresponds to at least one operating mode from a plurality of operating modes of the component;
providing, for each one of said predictive models, anomaly signatures each representative of a first set of deviations from a respective one of the predictive models for a specific timestamp;
obtaining operating data from the component, the operating data being indicative of a given operating mode from the operating modes;
selecting one of the predictive models based on the given operating mode;
generating an operating data signature by comparing the operating data with the selected predictive model, said operating signature being representative of a second set of deviations of said operating data from said selected predictive model for said specific timestamp; and
generating an alarm trigger when the operating data signature matches one of the anomaly signatures associated with the selected predictive model, thereby constituting the detection of the anomaly;
wherein at least one of the steps is performed by a processor.
1 Assignment
0 Petitions
Accused Products
Abstract
There is described a method and system for detecting an anomaly in data originating from a component used in an industrial process. The anomaly detection steps comprise: providing predictive models in which at least one of the predictive models corresponds to at least one operating mode from a plurality of operating modes of the component; obtaining operating data from the component, the operating data being indicative of a given operating mode from the operating modes; selecting at least one of the predictive models based on the given operating mode; generating estimated data using the selected at least one predictive model; comparing the operating data with the estimated data; and generating an alarm trigger when the comparison meets a given anomaly criteria thereby constituting the detection of the anomaly.
55 Citations
27 Claims
-
1. A method for detecting an anomaly in data originating from a component used in an industrial process, the method comprising steps of:
-
providing predictive models in which at least one of the predictive models corresponds to at least one operating mode from a plurality of operating modes of the component; providing, for each one of said predictive models, anomaly signatures each representative of a first set of deviations from a respective one of the predictive models for a specific timestamp; obtaining operating data from the component, the operating data being indicative of a given operating mode from the operating modes; selecting one of the predictive models based on the given operating mode; generating an operating data signature by comparing the operating data with the selected predictive model, said operating signature being representative of a second set of deviations of said operating data from said selected predictive model for said specific timestamp; and generating an alarm trigger when the operating data signature matches one of the anomaly signatures associated with the selected predictive model, thereby constituting the detection of the anomaly; wherein at least one of the steps is performed by a processor. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A system for detecting an anomaly in data originating from a component used in an industrial process, the system comprising:
at least one processor comprising an input for receiving operating data from the component, the operating data being indicative of a given operating mode from a plurality of operating modes of the component, and configured as; a predictive model builder for providing predictive models in which at least one of the predictive models corresponds to at least one of the plurality of operating modes, and for each one of said predictive models, providing anomaly signatures each representative of a first set of deviations from a respective one of the predictive models for a specific timestamp; a calculation engine for selecting one of the predictive models based on a given operating mode from the operating modes and generating an operating data signature by comparing the operating data with the selected predictive model, said operating signature being representative of a second set of deviations of said operating data from said selected predictive model for said specific timestamp; and an anomaly recognition engine for generating an alarm trigger when the operating data signature matches one of the anomaly signatures associated with the selected predictive model, thereby constituting the detection of the anomaly. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27)
Specification