Back to results
US 12,761,626 B2Granted
Blended IoT device health index
AssigneeRockwell Automation Canada Ltd.
InventorsAndrei Khurshudov, Stephen Skory, Nicholas Roseveare
Life of this patent
Estimating the term…
Abstract
A method is provided for a device not having an available history of either failures or degraded performance. The method includes establishing, by a computer coupled to the device, an initial baseline of sensor data from the device, receiving new sensor data after establishing the initial baseline, creating an updated baseline based on the new sensor data, evaluating, by the computer, the new sensor data compared to the updated baseline based on a plurality of different time scales, and determining whether the device is indicating an increased probability of failure or degraded performance based on the evaluated sensor data.
Claims20
A method for performing maintenance on a device, the method comprising:
- receiving sensor data from a sensor monitoring the device during a current time scale;
- creating, from a current anomaly count baseline and the sensor data, an updated anomaly count baseline comprising an updated anomaly count limit, the current time scale comprising a time period over which anomalies for the device are counted, the current anomaly count baseline established based on one or more historically relevant time scales related to the current time scale;
- determining an anomaly count for the device from the sensor data for the current time scale, the anomaly count comprising a number of anomalies within the sensor data during the current time scale, wherein an anomaly comprises sensor data exceeding a statistical outlier limit;
- comparing the anomaly count for the current time scale with the updated anomaly count limit of the updated anomaly count baseline;
- classifying the device as having a first status in response to determining that any of the sensor data has exceeded the statistical outlier limit for the sensor;
- classifying the device as having a second status in response to determining that the anomaly count of the current time scale is beyond the updated anomaly count limit;
- and
- performing maintenance or replacement of the device based on the classifying of the device, wherein a first maintenance action is performed in response to the device being classified as having the first status and a second maintenance action is performed in response to the device being classified as having the second status.
5 more elements
A program product comprising a non-transitory computer readable storage medium storing code, the code being configured to be executable by a processor to perform operations comprising:
- establishing a current anomaly count baseline based on one more historically relevant time scales related to a current time scale;
- operating a device during the current time scale to affect a physical condition measured by a sensor;
- receiving sensor data from the sensor monitoring the device during the current time scale;
- creating, from the current anomaly count baseline and the sensor data, an updated anomaly count baseline comprising an updated anomaly count limit, the current time scale comprising a time period over which the device is operated and anomalies for the device are counted;
- determining an anomaly count for the device from the sensor data for the current time scale, the anomaly count comprising a number of anomalies within the sensor data during the current time scale, wherein an anomaly comprises sensor data exceeding a statistical outlier limit;
- comparing the anomaly count for the current time scale with the updated anomaly count limit of the updated anomaly count baseline;
- classifying the anomaly count of the current time scale as anomalous in response to determining that the anomaly count of the current time scale is beyond the updated anomaly count limit;
- causing maintenance or replacement of the device in response to classifying the anomaly count for the device as anomalous;
- and
- continuing to operate the device to affect the physical condition measured by the sensor in response to classifying the anomaly count for the device as normal.
7 more elements
A device comprising:
- a processor;
- and
- non-transitory computer readable storage media storing code, the code being executable by the processor to perform operations comprising:
- establishing a current anomaly count baseline based on one more historically relevant time scales related to a current time scale;
- operating the device during the current time scale to affect a physical condition measured by a sensor;
- receiving sensor data from the sensor monitoring the device during the current time scale;
- creating, from the current anomaly count baseline and the sensor data, an updated anomaly count baseline comprising an updated anomaly count limit, the current time scale comprising a time period over which the device is operated and anomalies for the device are counted;
- determining an anomaly count for the device from the sensor data for the current time scale, the anomaly count comprising a number of anomalies within the sensor data during the current time scale, wherein an anomaly comprises sensor data exceeding a statistical outlier limit;
- comparing the anomaly count for the current time scale with the updated anomaly count limit of the updated anomaly count baseline;
- classifying the anomaly count of the current time scale as anomalous in response to determining that the anomaly count of the current time scale is beyond the updated anomaly count limit;
- causing maintenance or replacement of the device in response to classifying the anomaly count for the device as anomalous;
- and
- continuing to operate the device to affect the physical condition measured by the sensor in response to classifying the anomaly count for the device as normal.
10 more elements
Dependencies are inferred from the claim text.