Abnormality detection system, support device, and model generation method
AssigneeOMRON Corporation
InventorsShinsuke Kawanoue, Kota Miyamoto
Life of this patent
Estimating the term…
Abstract
An abnormality detection system, support device, and model generation method for generating a more highly accurate abnormality detection model before an actual operation are provided. A model generation part includes a section for generating feature values from state values provided from a state value storage part; a section for calculating importance levels respectively for the generated feature values based on plural methods, wherein the importance levels indicating a degree that is effective for abnormality detection; and a section for integrating the importance levels calculated based on the plural methods for each of the generated feature values and determining rankings of the importance levels of the generated feature values.
Claims20
An abnormality detection system, comprising:
- a control computation part, executing a control computation for controlling a control target;
- an abnormality detection part, detecting an abnormality that occurs in a monitoring target by giving a state value related to the monitoring target among state values collected by the control computation part to a model that indicates the monitoring target, wherein the model is defined by an abnormality detection parameter and a learning data set and;
- a state value storage part, storing at least a state value related to the monitoring target among the state values collected by the control computation part;
- and
- a model generation part, determining the abnormality detection parameter and the learning data set,
- wherein the model generation part includes:
- a section for generating a plurality of feature values from the state values provided from the state value storage part;
- a section for calculating importance levels respectively for the plurality of generated feature values based on a plurality of methods, wherein the importance levels indicate a degree that is effective for abnormality detection;
- and
- a section for integrating the importance levels calculated based on the plurality of the methods for each of the plurality of the generated feature values and determining rankings of the importance levels of the plurality of the generated feature values.
A support device that is connected to a control device for controlling a control target, the control device including an abnormality detection part that detects an abnormality that occur in a monitoring target by giving a state value related to the monitoring target among collected state values to a model that indicates the monitoring target and the model is defined by an abnormality detection parameter and a learning data set;
- and a state value storage part that stores at least a state value related to the monitoring target among the collected state values, the support device comprising:
- a model generation part that determines the abnormality detection parameter and the learning data set,
- wherein the model generation part includes
- a section for generating a plurality of feature values from the state values provided from the state value storage part;
- a section for calculating importance levels respectively for the plurality of generated feature values based on a plurality of methods, wherein the importance levels indicate a degree that is effective for abnormality detection;
- and
- a section for integrating the importance levels calculated based on the plurality of methods for each of the plurality of the generated feature values and determining rankings of the importance levels of the plurality of the generated feature values.
A model generation method of an abnormality detection system, the abnormality detection system including:
- a control computation part, executing a control computation for controlling a control target;
- an abnormality detection part, detecting an abnormality that occur in a monitoring target by giving a state value related to the monitoring target among state values collected by the control computation part to a model that indicates the monitoring target, wherein the model is defined by an abnormality detection parameter and a learning data set;
- a state value storage part, storing at least a state value related to the monitoring target among the state values collected by the control computation part;
- and
- a model generation part, determining the abnormality detection parameter and the learning data set,
- the model generation method comprising:
- generating a plurality of feature values from the state values provided by the state value storage part;
- calculating importance levels respectively for the plurality of generated feature values based on a plurality of methods, wherein the importance levels indicate a degree that is effective for abnormality detection;
- and
- integrating the importance levels calculated based on the plurality of methods for each of the plurality of the generated feature values and determining rankings of the importance levels of the plurality of the generated feature values.
Dependencies are inferred from the claim text.