Interface tool for asset fault analysis

• US 10,210,037 B2
• Filed: 08/25/2016
• Issued: 02/19/2019
• Est. Priority Date: 08/25/2016
• Status: Active Grant

• Current Assignee: Uptake Technologies, Inc.
• Original Assignee: Uptake Technologies, Inc.
• Inventors: Flyax, Alexander V.
• Primary Examiner(s): Duncan, Marc
• Assistant Examiner(s): Gibson, Jonathan D
• Application Number:
  US15/247,830
• Publication Number:
  US 20180060149A1
• Time in Patent Office: 908 Days
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06
• CPC Class Codes: G06F 11/0769 Readable error formats, e.g. cross-platform generic formats, human understandable formats
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206

Abstract

Disclosed herein are systems, devices, and methods related to analyzing faults across a population of assets. In particular, examples involve receiving a selection of variables each corresponding to an asset attribute type, accessing data associated with the selected variables, determining the number of fault occurrences across the population of assets for each combination of values of the selected variables, and facilitating the identification of outlier combination(s) that correspond to an abnormally large number of fault occurrences relative to other combination(s).

Claims

1. A computing system comprising:

a network interface configured to facilitate communications over a communication network with one or more asset-related sources and one or more client stations;

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, via the network interface from a client station configured with a user interface for use in analyzing fault occurrences across a population of assets, data indicating two or more variables that have been selected by a user via a selection pane of the user interface that includes a variable selection field, wherein the two or more variables each comprise a respective type of asset attribute having a range of possible values;

access data reflecting the respective values of the two or more selected variables at the time of each fault occurrence for the population of assets;

based on the accessed data, determine a respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables;

identify at least one outlier combination of values of the selected two or more variables that corresponds to an abnormally large number of fault occurrences relative to the other combinations of values of the selected two or more variables; and

transmit, via the network interface to the client station, data that causes the client station to present a visualization pane of the user interface that provides (1) an indication of the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables and (2) an indication of the identified at least one outlier combination of values of the selected two or more variables, wherein the visualization pane of the user interface comprises one or more of a summary table view, a pivot table view, a categorical plot view, a bar chart view, and a density plot view.

2. The computing system of claim 1, further comprising 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:

provide, via the network interface to the client station, data that defines the user interface for use in analyzing fault occurrences across the population of assets.

3. The computing system of claim 1, wherein the population of assets comprises a group of assets selected by the user via the user interface.

4. The computing system of claim 1, wherein the program instructions that are executable to cause the computing system to determine the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables comprise 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, for each given combination of values of the selected two or more variables:

analyze the data reflecting the respective values of each selected two or more variables at the time of each fault occurrence for the population of assets to identify each fault occurrence for which the respective values of each selected two or more variables comprise the given combination of values of the selected two or more variables; and

tally the number of identified fault occurrences.

5. The computing system of claim 4, wherein the program instructions that are executable to cause the computing system to determine the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables further comprise 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, for each given combination of values of the selected two or more variables:

normalize the tallied number of identified fault occurrences based on time value that reflects an amount of time that the assets in the population have been in use or a variable reflecting utilization of the assets.

6. The computing system of claim 1, wherein the program instructions that are executable to cause the computing system to identify at least one outlier combination of values of the selected two or more variables comprises 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:

determine a respective significance value for each given combination of values of the selected two or more variables, wherein the significance value reflects the difference between the number of fault occurrences for the given combination of values of the selected two or more variables and a representative number of fault occurrences; and

identify the at least one outlier combination of values of the selected two or more variables based on the respective significance value for each given combination of values of the selected two or more variables.

7. The computing system of claim 6, wherein the representative number of fault occurrences comprises an average of the respective number of fault occurrences for each combination of values of the selected two or more variables.

8. The computing device of claim 1, further comprising 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:

determine that at least one asset in the population has exhibited a given combination of values of the selected two or more variables without suffering any fault occurrence; and

impute a null value for the at least one asset to be used when determining the number of fault occurrences aggregated across the population of assets for the given combination of values of the selected two or more variables.

9. The computing system of claim 1, wherein the visualization pane of the user interface comprises a pivot table view that presents information in a pivot table, wherein the indication of the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables is shown via cells of the pivot table having a vertical axis corresponding to a first selected variable and a horizontal axis corresponding to a second selected variable, and wherein the indication of the identified at least one outlier combination of values of the selected two or more variables is shown via a highlighted bar located within the at least one cell of the pivot table corresponding to the at least one outlier combination.

10. The computing system of claim 1, further comprising 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:

determine that a given selected variable has a continuous range of possible values;

bin the continuous range of possible values into two or more discrete categories of possible ranges; and

use the two or more discrete categories of possible values as the two or more possible values of the given selected variable when determining the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables.

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

receive, via the network interface from a client station configured with a user interface for use in analyzing fault occurrences across a population of assets, data indicating two or more variables that have been selected by a user via a selection pane of the user interface that includes a variable selection field, wherein the two or more variables each comprise a respective type of asset attribute having a range of possible values;

access data reflecting the respective values of the two or more selected variables at the time of each fault occurrence for the population of assets;

based on the accessed data, determine a respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables;

identify at least one outlier combination of values of the selected two or more variables that corresponds to an abnormally large number of fault occurrences relative to the other combinations of values of the selected two or more variables; and

transmit, via the network interface to the client station, data that causes the client station to present a visualization pane of the user interface that provides (1) an indication of the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables and (2) an indication of the identified at least one outlier combination of values of the selected two or more variables, wherein the visualization pane of the user interface comprises one or more of a summary table view, a pivot table view, a categorical plot view, a bar chart view, and a density plot view.

12. The non-transitory computer-readable medium of claim 11, wherein the program instructions are further executable by the at least one processor to cause the computing device to:

provide, via the network interface to the client station, data that defines the user interface for use in analyzing fault occurrences across the population of assets.

13. The non-transitory computer-readable medium of claim 11, wherein the program instructions that are executable to cause the computing device to determine the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables comprise 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, for each given combination of values of the selected two or more variables:

analyze the data reflecting the respective values of each selected two or more variables at the time of each fault occurrence for the population of assets to identify each fault occurrence for which the respective values of each selected two or more variables comprise the given combination of values of the selected two or more variables; and

tally the number of identified fault occurrences.

14. The non-transitory computer-readable medium of claim 13, wherein the program instructions that are executable to cause the computing device to determine the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables further comprise 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, for each given combination of values of the selected two or more variables:

normalize the tallied number of identified fault occurrences based on time value that reflects an amount of time that the assets in the population have been in use.

15. The non-transitory computer-readable medium of claim 11, wherein the program instructions that are executable to cause the computing device to identify at least one outlier combination of values of the selected two or more variables comprises 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:

determine a respective significance value for each given combination of values of the selected two or more variables, wherein the significance value reflects the difference between the number of fault occurrences for the given combination of values of the selected two or more variables and a representative number of fault occurrences; and

identify the at least one outlier combination of values of the selected two or more variables based on the respective significance value for each given combination of values of the selected two or more variables.

16. A computer-implemented method comprising:

receiving, via the network interface from a client station configured with a user interface for use in analyzing fault occurrences across a population of assets, data indicating two or more variables that have been selected by a user via a selection pane of the user interface that includes a variable selection field, wherein the two or more variables each comprise a respective type of asset attribute having a range of possible values;

accessing data reflecting the respective values of the two or more selected variables at the time of each fault occurrence for the population of assets;

based on the accessed data, determining a respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables;

identifying at least one outlier combination of values of the selected two or more variables that corresponds to an abnormally large number of fault occurrences relative to the other combinations of values of the selected two or more variables; and

transmitting, via the network interface to the client station, data that causes the client station to present a visualization pane of the user interface that provides (1) an indication of the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables and (2) an indication of the identified at least one outlier combination of values of the selected two or more variables, wherein the visualization pane of the user interface comprises one or more of a summary table view, a pivot table view, a categorical plot view, a bar chart view, and a density plot view.

17. The computer-implemented method of claim 16, further comprising:

providing, via the network interface to the client station, data that defines the user interface for use in analyzing fault occurrences across the population of assets.

18. The computer-implemented method of claim 16, wherein determining the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables comprises, for each given combination of values of the selected two or more variables:

analyzing the data reflecting the respective values of each selected two or more variables at the time of each fault occurrence for the population of assets to identify each fault occurrence for which the respective values of each selected two or more variables comprise the given combination of values of the selected two or more variables; and

tallying the number of identified fault occurrences.

19. The computer-implemented method of claim 18, wherein determining the respective number of fault occurrences aggregated across the population of assets for each combination of values of the selected two or more variables further comprises, for each given combination of values of the selected two or more variables:

normalizing the tallied number of identified fault occurrences based on time value that reflects an amount of time that the assets in the population have been in use.

20. The computer-implemented method of claim 16, wherein identifying at least one outlier combination of values of the selected two or more variables comprises:

determining a respective significance value for each given combination of values of the selected two or more variables, wherein the significance value reflects the difference between the number of fault occurrences for the given combination of values of the selected two or more variables and a representative number of fault occurrences; and

identifying the at least one outlier combination of values of the selected two or more variables based on the respective significance value for each given combination of values of the selected two or more variables.