Subsystem health score

Patent metadata

Field	Value
Publication number	US-10176032-B2
Application number	US-201514732285-A
Country	US
Kind code	B2
Filing date	Jun 5, 2015
Priority date	Dec 1, 2014
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

Disclosed herein are systems, devices, and methods related to assets and asset operating conditions. In particular, examples involve defining and executing predictive models for outputting health metrics that estimate the operating health of an asset or a part thereof, analyzing health metrics to determine variables that are associated with high health metrics, and modifying the handling of abnormal-condition indicators in accordance with a prediction of a likely response to such abnormal-condition indicators, among other examples.

First claim

The invention claimed is:

1. A computing system comprising:
a network interface configured to facilitate communication with a plurality of assets and a plurality of computing devices;
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:
identify a group of abnormal-condition types associated with a group of possible failure types for a given type of subsystem of an asset;
based on the identified group of abnormal-condition types, identify a subset of historical operating data comprising (i) historical abnormal-condition data for a plurality of assets that indicates past occurrences of the identified group of abnormal-condition types at the given type of subsystem of the plurality of assets and (ii) historical sensor data for the plurality of assets that indicates sensor measurements associated with the past occurrences of the identified group of abnormal-condition types at the given type of subsystem of the plurality of assets;
apply a supervised machine learning technique to the identified subset of historical operating data to define a predictive model that is configured to (i) receive sensor data for an asset as input, (ii) for each of at least two failure types from the group of possible failure types for the given type of subsystem, make a respective prediction of whether the failure type is likely to occur at the given type of subsystem of the asset within a given period of time in the future, and (iii) based on the respective predictions, determine and output a health metric indicating whether at least one failure type from the group of possible failure types is likely to occur at the given type of subsystem of the asset within the given period of time in the future;
receive sensor data indicating operating conditions of a given asset;
apply the predictive model to the received sensor data and thereby determine, for the given asset, a health metric indicating whether at least one failure type from the group of possible failure types is likely to occur at the given type of subsystem of the given asset within the given period of time in the future;
compare the health metric for the given type of subsystem of the given asset to a threshold condition that defines whether the given type of subsystem is considered to be in a state of impending failure and thereby make a determination that the health metric satisfies the threshold condition such that the given type of subsystem of the given asset is considered to be in a state of impending failure; and
responsive to the determination that the given type of subsystem of the given asset is considered to be in a state of impending failure, carry out a remedial action that comprises at least one of (i) automatically generating and sending, to a computing device associated with an individual responsible for overseeing the given asset, an alert indicating that the given type of subsystem of the given asset is considered to be in a state of impending failure, (ii) automatically generating and sending, to the given asset, an instruction for the given asset to modify its operation to account for the determination that the given type of subsystem is considered to be in a state of impending failure, (iii) automatically generating and sending, to a repair facility, an instruction to repair the given type of subsystem of the given asset, and (iv) automatically generating and sending, to a parts-ordering system, an instruction for the parts ordering system to order a given component of the given type of subsystem for the given asset.

2. The computing system of claim 1 , wherein identifying the group of abnormal-condition types associated with the group of possible failure types for the given type of subsystem comprises:
identifying one or more sensors associated with the given type of subsystem; and
identifying one or more abnormal-condition types corresponding to the one or more sensors.

3. The computing system of claim 2 , wherein identifying the one or more sensors associated with the given type of subsystem comprises identifying the one or more sensors associated with the given type of subsystem based on the historical operating data and at least one of historical repair data or sensor attributes.

4. The computing system of claim 1 , wherein the group of possible failure types comprises one or more failure types that could render the given type of subsystem inoperable when the one or more failure types occur.

5. The computing system of claim 1 , wherein each failure type from the group of possible failure types corresponds to at least one abnormal-condition type from the identified group of abnormal-condition types.

6. The computing system of claim 5 , wherein the health metric comprises a probability that any of the identified group of abnormal-condition types will be triggered within the given period of time in the future.

7. The computing system of claim 1 , wherein the health metric for the given type of subsystem of the given asset comprises one of (i) a probability that no failure type from the group of possible failure types will occur at the given type of subsystem within the given period of time in the future or (ii) a probability that at least one failure type from the group of possible failure types will occur at the given type of subsystem within the given period of time in the future.

8. The computing system of claim 1 , wherein identifying the group of abnormal-condition types associated with the group of possible failure types for a given type of subsystem of an asset comprises identifying the group of abnormal-condition types based on user input.

9. A non-transitory computer-readable medium having instructions stored thereon that are executable to cause a computing system to:
identify a group of abnormal-condition types associated with a group of possible failure types for a given type of subsystem of an asset;
based on the identified group of abnormal-condition types, identify a subset of historical operating data comprising (i) historical abnormal-condition data for a plurality of assets that indicates past occurrences of the identified group of abnormal-condition types at the given type of subsystem of the plurality of assets and (ii) historical sensor data for the plurality of assets that indicates sensor measurements associated with the past occurrences of the identified group of abnormal-condition types at the given type of subsystem of the plurality of assets;
apply a supervised machine learning technique to the identified subset of the historical operating data to define a predictive model that is configured to receive sensor data for an asset as input, (ii) for each of at least two failure types from the group of possible failure types for the given type of subsystem, make a respective prediction of whether the failure type is likely to occur at the given type of subsystem of the asset within a given period of time in the future, and (iii) based on the respective predictions, determine and output a health metric indicating whether at least one failure type from the group of possible failure types is likely to occur at the given type of subsystem within the given period of time in the future;
receive sensor data indicating operating conditions of a given asset;
apply the predictive model to the received sensor data and thereby determine, for the given asset, a health metric indicating whether at least one failure type from the group of possible failure types is likely to occur at the given type of subsystem of the given asset within the given period of time in the future;
compare the health met

Assignees

• Uptake Tech Inc

Inventors

• Horrell Michael
• Ciasulli John
• Zhong Sheng
• Mcelhinney Adam
• Silva Brian

Classifications

• G06Q10/20 Primary

  Administration of product repair or maintenance · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06Q10/0633

  Workflow analysis · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G08B21/18

  Status alarms (G08B21/02 takes precedence) · CPC title