Aggregate predictive model and workflow for local execution
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.
1. A computing system comprising:
a network interface configured to communicatively couple the computing system via a communication network to assets and local analytics devices located remote from the computing system;
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:
receive operating data for a plurality of assets, wherein the operating data comprises historical sensor data associated with past occurrences of a given type of failure event at the plurality of assets;
based at least on the received historical sensor data, define (i) a predictive model that is configured to predict occurrences of the given type of failure event and (ii) a corresponding workflow that is configured to run based on an output of the predictive model; and
transmit via the communication network, to at least one particular local analytics device that corresponds to and is located at or near a particular asset, the predictive model and the corresponding workflow and thereby configure the particular local analytics device to (i) locally apply the predictive model to sensor data received from the particular asset without involvement of the computing system and thereby predict occurrences of the given type of failure event and (ii) in response to a predicted occurrence of the given type of failure event, locally execute the corresponding workflow without involvement of the computing system such that one or more operations are initiated at the particular asset.
2. The computing system of claim 1 , wherein the operating data further comprises historical abnormal-condition data associated with a failure that occurred at a given asset at a particular time, and wherein the historical sensor data indicates at least one operating condition of the given asset at the particular time.
3. The computing system of claim 1 , wherein the predictive model is defined to output a probability that the given type of failure event will occur at a given asset within a period of time into the future.
4. The computing system of claim 3 , wherein the corresponding workflow comprises one or more operations to be performed based on the determined probability.
5. The computing system of claim 1 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset triggering the asset to control one or more actuators of the asset to facilitate modifying an operating condition of the asset.
6. The computing system of claim 1 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset causing one or more diagnostic tools to be executed locally by the asset.
7. The computing system of claim 1 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset acquiring sensor data from the asset according to a particular data-acquisition scheme.
8. The computing system of claim 7 , wherein the particular data-acquisition scheme indicates one or more sensors of the asset from which data is to be acquired.
9. The computing system of claim 8 , wherein the particular data-acquisition scheme further indicates an amount of data that the local analytics device corresponding to the asset is to acquire from each of the one or more sensors of the asset.
10. The computing system of claim 1 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset transmitting data related to operation of the asset to the computing system according to a particular data-transmission scheme.
11. The computing system of claim 10 , wherein the particular data-transmission scheme indicates a frequency at which the local analytics device corresponding to the asset is to transmit the data related to operation of the asset to the computing system.
12. The computing system of claim 1 , wherein the computing system is a first computing system, and wherein the corresponding workflow comprises a local analytics device corresponding to an asset transmitting instructions to a second computing system to facilitate causing the second computing system to carry out an operation related to the asset.
13. The computing system of claim 1 , wherein the particular local analytics device that corresponds to the particular asset comprises a first local analytics device that corresponds to a first asset, and wherein transmitting the predictive model and the corresponding workflow to the at least one particular local analytics device comprises transmitting the predictive model and the corresponding workflow to both the first local analytics device and also a second local analytics device that corresponds to and is located at or near a second asset and thereby (a) configuring the first local analytics device to (i) locally apply the predictive model to sensor data received from the first asset without involvement of the computing system and thereby predict occurrences of the given type of failure event at the first asset and (ii) in response to a predicted occurrence of the given type of failure event at the first asset, locally execute the corresponding workflow without involvement of the computing system such that one or more operations are initiated at the first asset, and (b) configuring the second local analytics device to (i) locally apply the predictive model to sensor data received from the second asset without involvement of the computing system and thereby predict occurrences of the given type of failure event at the second asset and (ii) in response to a predicted occurrence of the given type of failure event at the second asset, locally execute the corresponding workflow without involvement of the computing system such that one or more operations are initiated at the second asset.
14. A non-transitory computer-readable medium having instructions stored thereon that are executable to cause a computing system comprising a network interface configured to communicatively couple the computing system via a communication network to assets and local analytics devices located remote from the computing system to:
receive operating data for a plurality of assets, wherein the operating data comprises historical sensor data associated with past occurrences of a given type of failure event at the plurality of assets;
based at least on the received historical sensor data, define (i) a predictive model that is configured to predict occurrences of the given type of failure event and (ii) a corresponding workflow that is configured to run based on an output of the predictive model; and
transmit via the communication network, to at least one particular local analytics device that corresponds to and is located at or near a particular asset, the predictive model and the corresponding workflow and thereby configure the particular local analytics device to (i) locally apply the predictive model to sensor data received from the particular asset without involvement of the computing system and thereby predict occurrences of the given type of failure event and (ii) in response to a predicted occurrence of the given type of failure event, locally execute the corresponding workflow without involvement of the computing system such that one or more operations are initiated at the particular asset.
15. The non-transitory computer-readable medium of claim 14 , wherein the predictive model is defined to output a probability that the given type of failure event will occur at a given asset within a period of time into the future.
16. The non-transitory computer-readable medium of claim 14 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset triggering the asset to control one or more actuators of the asset to facilitate modifying an operating condition of the asset.
17. The non-transitory computer-readable medium of claim 14 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset causing one or more diagnostic tools to be executed locally by the asset.
18. The non-transitory computer-readable medium of claim 14 , wherein the computing system is a first computing system, and wherein the corresponding workflow comprises a local analytics device corresponding to an asset transmitting instructions to a second computing system to facilitate causing the second computing system to carry out an operation related to the asset.
19. A computer-implemented method performed by a computing system configured to be communicatively coupled via a communication network to assets and local analytics devices located remote from the computing system, the method comprising:
receiving operating data for a plurality of assets, wherein the operating data comprises historical sensor data associated with past occurrences of a given type of failure event at the plurality of assets;
based at least on the received historical sensor data, defining (i) a predictive model that is configured to predict occurrences of the given type of failure event and (ii) a corresponding workflow that is configured to run based on an output of the predictive model; and
transmitting via the communication network, to at least one particular local analytics device that corresponds to and is located at or near a particular asset, the predictive model and the corresponding workflow and thereby configuring the particular local analytics device to (i) locally apply the predictive model to sensor data received from the particular asset without involvement of the computing system and thereby predict occurrences of the given type of failure event and (ii) in response to a predicted occurrence of the given type of failure event, locally execute the corresponding workflow without involvement of the computing system such that one or more operations are initiated at the particular asset.
20. The computer-implemented method of claim 19 , wherein the corresponding workflow comprises a local analytics device corresponding to an asset acquiring sensor data from the asset according to a particular data-acquisition scheme, and wherein the particular data-acquisition scheme indicates one or more sensors of the asset from which data is to be acquired.