Aggregate and correlate data from different types of sensors

Patent metadata

Field	Value
Publication number	US-11830341-B2
Application number	US-202117406309-A
Country	US
Kind code	B2
Filing date	Aug 19, 2021
Priority date	Aug 19, 2021
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

A method for correlating data from sensors includes receiving sensor information from a plurality of sensors of an industrial operation. Sensor information from component sensors is used for functionality of a component of the industrial operation and sensor information from additional sensors monitor conditions of a portion of the industrial operation different from the component. The method includes deriving, using the sensor information, correlations between component sensors and additional sensors and deriving a baseline signature from the sensor information and the correlations. The baseline signature encompasses a range of normal operating conditions. The method includes identifying an abnormal operating condition based on a comparison between additional sensor information and the baseline signature. The sensor information is used differently for functionality of the component than for deriving the correlations and baseline signature and identifying the abnormal operating condition. The method includes sending an alert with the abnormal operating condition.

First claim

What is claimed is:

1. A method comprising:
receiving sensor information from a plurality of sensors of an industrial operation, wherein a first portion of the sensor information is from one or more component sensors of the plurality sensors is used for functionality of a component of the industrial operation and a second portion of the sensor information is from one or more additional sensors of the plurality of sensors different from the one or more component sensors and monitor conditions of a portion of the industrial operation different from the functionality of the component, wherein the one or more component sensors provide the first portion of the sensor information to a controller of the component and the one or more additional sensors are monitored by a sensing system different than the controller;
deriving, using the sensor information, correlations between the first portion of sensor information of sensors of the one or more component sensors and the second portion of sensor information of the one or more additional sensors, wherein deriving the correlations comprises determining whether a first sensor of the plurality of sensors and a second sensor of the plurality of sensors are related based on whether a first condition measured by the first sensor changes when a second condition measured by the second sensor changes;
deriving a baseline signature from the sensor information and the correlations, the baseline signature encompassing a range of normal operating conditions;
identifying an abnormal operating condition of the industrial operation based on a comparison between additional sensor information from the plurality of sensors and the baseline signature, wherein identifying the abnormal operating condition comprises determining whether a change in the first condition measured by the first sensor occurs without a corresponding change in the second condition measured by the second sensor when the correlations indicate the first sensor and the second sensor are related, wherein the first portion of the sensor information is used for the functionality of the component in addition to being used for deriving the correlations and baseline signature and identifying the abnormal operating condition and the second portion of the sensor information is not used for the functionality of the component; and
sending an alert comprising the identified abnormal operating condition.

2. The method of claim 1 , wherein the component is a first component and the second portion of the sensor information from the additional sensors is used for functionality of one or more additional components of the industrial operation.

3. The method of claim 1 , wherein the one or more additional sensors are general purpose sensors independent of functionality of the component.

4. The method of claim 1 , wherein identifying the abnormal operating condition comprises identifying a trend in the additional sensor information that varies from the baseline signature.

5. The method of claim 1 , wherein:
deriving the correlations from the sensor information comprises using a machine learning algorithm to derive the correlations; and/or
identifying the abnormal operating condition of the industrial operation comprises using a machine learning algorithm to identify a trend in the additional sensor information that deviates from the baseline signature.

6. The method of claim 1 , wherein deriving the baseline signature from the sensor information comprises identifying one or more contexts of the industrial operation, the one or more contexts each for different normal operating conditions in the industrial operation and wherein identifying the abnormal operating condition of the industrial operation comprises identifying additional sensor information outside of the one or more contexts.

7. The method of claim 1 , wherein the baseline signature comprises one or more thresholds and identifying the abnormal operating condition of the industrial operation comprises identifying that the additional sensor information exceeds at least one of the one or more thresholds.

8. The method of claim 1 , wherein the sensor information comprises location information for at least a portion of the plurality of sensors and identifying the abnormal condition comprises using the location information to identify a source of the abnormal condition.

9. The method of claim 1 , further comprising synchronizing the sensor information from the plurality of sensors.

10. The method of claim 1 , wherein the plurality of sensors include sensors of different types.

11. The method of claim 10 , wherein the plurality of sensors sense one or more of temperature, humidity, vibration, current, voltage, motion, acoustic noise, strain, movement, odor, and pressure.

12. The method of claim 1 , wherein the sensor information includes command information about operational commands issued to equipment of the industrial operation.

13. The method of claim 1 , wherein the component exports sensor information from the one or more component sensors to a computing device external to the component.

14. A system comprising:
a plurality of sensors sensing conditions on equipment of an industrial operation, wherein one or more component sensors of the plurality of sensors provide first sensor information for functionality of a component of the industrial operation and one or more additional sensors of the plurality of sensors different from the one or more component sensors provide second sensor information to monitor conditions of a portion of the industrial operation different from the functionality of the component, wherein the one or more component sensors provide the first sensor information to a controller of the component and the one or more additional sensors are monitored by a sensing system different than the controller;
a sensor module configured to receive sensor information from the plurality of sensors, the sensor information from the plurality of sensors comprising the first sensor information and the second sensor information;
a correlation module configured to derive, using the sensor information, correlations between the first sensor information of sensors of the one or more component sensors and the second sensor information of the one or more additional sensors, wherein deriving the correlations comprises determining whether a first sensor of the plurality of sensors and a second sensor of the plurality of sensors are related based on whether a first condition measured by the first sensor changes when a second condition measured by the second sensor changes;
a baseline module configured to derive a baseline signature from the sensor information and the correlations, the baseline signature encompassing a range of normal operating conditions;
an error module configured to identify an abnormal operating condition of the industrial operation based on a comparison between additional sensor information from the plurality of sensors and the baseline signature, wherein identifying the abnormal operating condition comprises determining whether a change in the first condition measured by the first sensor occurs without a corresponding change in the second condition measured by the second sensor when the correlations indicate the first sensor and the second sensor are related, wherein the first sensor information is used for the functionality of the component in addition to being used for deriving the correlations and baseline signature and identifying the abnormal operating condition and the second portion of the sensor information is not used for the functionality of the component; and
an alert module configured to

Assignees

• Rockwell Automation Tech Inc

Inventors

• Malkan Chirag
• Crum Kyle
• Vasko David
• Haensgen Steven T
• Sayyarrodsari Bijan
• Sokolnicki Katherine
• Cai Yongyao

Classifications

• G08B21/182 Primary

  Level alarms, e.g. alarms responsive to variables exceeding a threshold · CPC title

• G01M99/005

  Testing of complete machines, e.g. washing-machines or mobile phones (testing of machine parts G01M13/00; testing of electric apparatus or components G01R31/50) · CPC title

• G05B19/4155

  characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program · CPC title

• G05B2219/31449

  Monitor workflow, to optimize business, industrial processes · CPC title

• G05B23/0283 Primary

  Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06) · CPC title