Dynamic Execution of Predictive Models & Workflows

• US 20160371406A1
• Filed: 06/19/2015
• Published: 12/22/2016
• Est. Priority Date: 06/05/2015
• Status: Active Grant

• Current Assignee: Uptake Technologies, Inc.
• Original Assignee: Uptake Technologies, Inc.
• Inventors: Nicholas, Brad
• Granted Patent: US 10,176,279 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 2219/34477 Fault prediction, analyzing signal trends
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 9/46 Multiprogramming arrangements

Abstract

Disclosed herein are systems, devices, and methods related to assets and predictive models and corresponding workflows that are related to the operation of assets. In particular, examples involve defining and deploying aggregate, predictive models and corresponding workflows, defining and deploying individualized, predictive models and/or corresponding workflows, and dynamically adjusting the execution of model-workflow pairs.

Claims

1. A computing system comprising:

at least one processor;

a non-transitory computer-readable medium; and

program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor to cause the computing system to;

define a predictive model and corresponding workflow that are related to the operation of an asset;

transmit the predictive model and corresponding workflow to the asset for local execution;

detect an indication that the asset is locally executing at least one of the predictive model or the corresponding workflow; and

based on the detected indication, modify central execution by the computing system of at least one of the predictive model or the corresponding workflow.

2. The computing system of claim 1, wherein detecting the indication comprises:

receiving data for the asset; and

detecting a characteristic of the received data.

3. The computing system of claim 2, wherein detecting the characteristic of the received data comprises detecting a change in a type of the received data.

4. The computing system of claim 3, wherein the received data comprises data generated by at least one of a plurality of sensors or a plurality of actuators, and wherein detecting the change in the type of the received data comprises detecting a change in the at least one of the plurality of sensors or the plurality of actuators that generated the data.

5. The computing system of claim 2, wherein detecting the characteristic of the received data comprises detecting a change in an amount of the received data.

6. The computing system of claim 2, wherein detecting the characteristic of the received data comprises detecting a change in a frequency at which the received data is received.

7. The computing system of claim 2, wherein the received data comprises data generated by at least one of a plurality of sensors or a plurality of actuators, and wherein detecting the characteristic of the received data comprises detecting an identifier identifying one of a given sensor of the plurality of sensors or a given actuator of the plurality of actuators that generated the data.

8. The computing system of claim 1, wherein the indication comprises an indication that the asset is locally executing at least the predictive model, and wherein modifying the central execution by the computing system of at least one of the predictive model or the corresponding workflow comprises modifying the central execution by the computing system of at least the predictive model.

9. The computing system of claim 8, wherein modifying the central execution by the computing system of the predictive model comprises ceasing to execute the predictive model.

10. The computing system of claim 1, wherein the program instructions further comprise instructions that are executable to cause the computing system to:

determine a characteristic of a communication network that communicatively couples the asset and the computing system; and

based on the determined characteristic of the communication network, modify central execution by the computing system of at least one of the predictive model or the corresponding workflow.

11. The computing system of claim 10, wherein the determined characteristic of the communication is a signal strength.

12. A non-transitory computer-readable medium having instructions stored thereon that are executable to cause a computing system to:

define a predictive model and corresponding workflow that are related to the operation of an asset;

transmit the predictive model and corresponding workflow to the asset for local execution;

detect an indication that the asset is locally executing at least one of the predictive model or the corresponding workflow; and

based on the detected indication, modify central execution by the computing system of at least one of the predictive model or the corresponding workflow.

13. The non-transitory computer-readable medium of claim 12, wherein detecting the indication comprises:

receiving data for the asset; and

detecting a characteristic of the received data.

14. The non-transitory computer-readable medium of claim 13, wherein detecting the characteristic of the received data comprises detecting a change in a type of the received data.

15. The non-transitory computer-readable medium of claim 14, wherein the received data comprises sensor data generated by a plurality of sensors, and wherein detecting the change in the type of the received data comprises detecting a change in the plurality of sensors that generated the sensor data.

16. The non-transitory computer-readable medium of claim 13, wherein detecting the characteristic of the received data comprises detecting a change in an amount of the received data.

17. The non-transitory computer-readable medium of claim 13, wherein detecting the characteristic of the received data comprises detecting a change in a frequency at which the received data is received.

18. A computer-implemented method comprising:

defining, by a computing system, a predictive model and corresponding workflow that are related to the operation of an asset;

transmitting, by the computing system to the asset, the predictive model and corresponding workflow for local execution by the asset;

detecting, by the computing system, an indication that the asset is locally executing at least one of the predictive model or the corresponding workflow; and

based on the detected indication, modifying central execution by the computing system of at least one of the predictive model or the corresponding workflow.

19. The computer-implemented method of claim 18, wherein the indication comprises an indication that the asset is locally executing at least the predictive model, and wherein modifying the central execution by the computing system of at least one of the predictive model or the corresponding workflow comprises modifying the central execution by the computing system of at least the predictive model.

20. The computer-implemented method of claim 19, wherein modifying the central execution by the computing system of the predictive model comprises ceasing to execute the predictive model.