Methods for maintaining infrastructure equipment and related apparatus

• US 9,679,253 B2
• Filed: 10/05/2015
• Issued: 06/13/2017
• Est. Priority Date: 11/06/2014
• Status: Active Grant

• Current Assignee: Copperleaf Technologies Inc.
• Original Assignee: Copperleaf Technologies Inc.
• Inventors: Gnocato, Giuseppe, Malcolm, Nicholas James, Coleman, Stanley Thomas
• Primary Examiner(s): Ahn, Sangwoo
• Application Number:
  US14/875,060
• Publication Number:
  US 20160132550A1
• Time in Patent Office: 617 Days
• Field of Search: None
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

Apparatus and methods for managing and upgrading components in an infrastructure are provided. Records relating to components may be retrieved from a database and separated into subsets based on conditions of those components, the types of those components, deterioration models of those components, and/or other factors. Future condition values may be calculated for each subset, and likelihoods of failure of components may be determined for each subset based on those future condition values. The estimated condition values may be used in order to determine an optimal approach to maintaining, refurbishing, and/or replacing the components in the infrastructure. Computational efficiency is increased.

Claims

1. A method for coordinating maintenance of components of an infrastructure, the method performed using a computer system comprising one or more programmed data processors, the method comprising:

determining, by the one or more data processors, a current physical condition for each of a plurality of the infrastructure components, the current physical condition comprising a value indicating a current degree of deterioration of the corresponding infrastructure component;

sorting, by the one or more data processors, the plurality of infrastructure components into a plurality of groups based at least in part on the current physical conditions of the plurality of infrastructure components, each of the groups comprising a subset of the plurality of infrastructure components for which the determined current physical conditions of the infrastructure components sorted into the subset are similar to one another according to one or more similarity criteria;

by the one or more processors, associating a representative condition value with each of the groups, the representative condition values representative of the current physical conditions of the infrastructure components belonging to the respective groups;

estimating, by the one or more data processors, for each of the groups, using a deterioration model, a time series of estimated future physical conditions for the infrastructure components of the group, based on the representative condition associated with the group, the estimated future physical conditions each comprising a value indicating an estimated degree of deterioration of the infrastructure components of the group at a corresponding one of a plurality of future times which constitute the time series;

by the one or more data processors, performing an optimization to yield an optimized schedule of projects, each of the projects associated with one of the groups and comprising at least one of;

replacing, upgrading and refurbishing the infrastructure components of the group wherein the optimization is based on the estimated time series of future physical conditions for the groups; and

maintaining the infrastructure by at least one of;

replacing, upgrading and refurbishing the infrastructure components of one of the groups according to the schedule of projects.

2. A method according to claim 1 wherein grouping the infrastructure components into the groups comprises computing a value representing a consequence of failure for each of the plurality of infrastructure components and including in each of the groups infrastructure components for which the consequence of failure has a similar value.

3. A method according to claim 2 comprising estimating a time series of future failure risks for each of the groups, the future failure risks based on the representative conditions for the groups wherein the optimization is based at least in part on the future failure risks.

4. A method according to claim 2 wherein:

the one or more similarity criteria comprise a severity range associated with one of the groups, the severity range defining a range of severity of failure consequences; and

sorting the infrastructure components into the groups comprises, for at least the one of the groups, comparing measures of severity of failure consequences for the plurality of infrastructure components to the severity range associated with the group and including in the group only one of the infrastructure components for which the severity of failure consequences is in the severity range.

5. A method according to claim 1 wherein the current physical condition values for the infrastructure components are represented by values on a scale, the similarity criteria comprise a range of the values for the current physical conditions to include in each of the groups, the method comprises calculating a representative failure risk based on at least one of the estimated future physical conditions, and the ranges of values are such that the representative failure risk for each of the groups is within 12% of failure risks determined for individual ones of the infrastructure components of the group based on the current physical conditions of the infrastructure components.

6. A method according to claim 1 wherein sorting the infrastructure components into groups comprises looking up replacement costs for the infrastructure components and including in each of the groups infrastructure components for which replacement costs are within a range specified by a replacement cost criterion of the one or more similarity criteria such that differences between replacement costs for all of the infrastructure components in each of the groups is less than a threshold amount.

7. A method according to claim 6 wherein:

the one or more similarity criteria comprise, for at least one of the plurality of groups, a replacement cost range associated with the group; and

sorting the infrastructure components into the groups comprises including in each of the at least one groups only infrastructure components having replacement costs falling within the replacement cost range associated with the group.

8. A method according to claim 1 wherein optimizing a schedule of projects comprises performing a plurality of optimizations, each of the optimizations subject to a corresponding set of constraints, a first optimization of the plurality of optimizations associated with a different set of constraints than a second optimization of the plurality of optimizations.

9. A method according to claim 1 wherein determining the current physical conditions of the infrastructure components comprises, for each of the plurality of infrastructure components, retrieving from a database one or more data items related to the physical condition of the infrastructure component and determining the current physical condition of the infrastructure component by processing the plurality of data items.

10. A method according to claim 9 wherein the database contains results of testing the infrastructure components and the method determines the current physical condition based on the testing results.

11. A method according to claim 10 wherein the testing results comprise results of testing samples of oil from the infrastructure components.

12. A method according to claim 1 wherein:

the one or more similarity criteria comprise, for at least one of the plurality of groups, a condition threshold range associated with the group; and

sorting the infrastructure components into the groups comprises including in the at least one group only infrastructure components for which the current physical condition is within the condition threshold range associated with the at least one of the groups.

13. A method according to claim 12 comprising establishing the condition threshold range associated with the at least one group based on analysis of a range of current physical conditions of the plurality of infrastructure components.

14. A method according to claim 1 comprising establishing the similarity criteria for inclusion of the infrastructure components in the groups such that an equal number of the infrastructure components is sorted into each of the plurality of groups.

15. A method according to claim 1 wherein the plurality of infrastructure components comprises at least one of:

transformers, utility poles, switchgear, pipeline sections, consumption meters, and valves.

16. A method according to claim 1 comprising:

providing a database containing a record for each of the infrastructure components, the record including one or more fields containing data describing at least a first condition of the infrastructure component;

wherein sorting the plurality of components into the groups comprises, for each of the infrastructure components, comparing the data from the one or more fields describing a first condition of the infrastructure components to representative condition values associated with the groups;

by the one or more data processors, for a first one of the groups, computing an estimated future physical condition based on the one or more representative values associated with the first group; and

by the one or more data processors, assigning the estimated future physical condition to all of the infrastructure components in the first group.

17. A method according to claim 16 wherein the one or more fields comprises a plurality of fields, each of the plurality of fields containing data describing an aspect of the first condition of the infrastructure component.

18. A method according to claim 16 comprising, by the one or more data processors, establishing the one or more similarity criteria based on analysis of the one or more fields for the plurality of infrastructure components.

19. A method according to claim 18 comprising, by the one or more data processors, for each of the plurality of groups, automatically determining the one or more representative values associated with the group so that an equal number of the plurality of objects is sorted into each of the plurality of groups.

20. A method according to claim 18 wherein the one or more representative values comprise a representative severity of a consequence of failure of an infrastructure component and the one or more fields comprise a severity of a consequence of failure of the infrastructure component corresponding to the one or more fields and wherein the one or more similarity criteria comprise automatically determining that the severity is equal to the representative severity.

21. A method according to claim 16 comprising, by the one or more data processors, receiving one or more sensor values associated with one or more of the infrastructure components, processing the one or more sensor values to yield data, storing the data in the database, and using the data to compute or represent the first condition of the infrastructure component.

22. A method according to claim 16 comprising, by the one or more data processors, determining a type of one of the plurality of infrastructure components, processing the one or more fields according to an algorithm associated with the type to yield information indicative of a probability of failure of the infrastructure component, and storing the information indicative of the probability of failure of the infrastructure component in the database.

23. A method according to claim 16 wherein performing the optimization is based on failure risks for the groups.

24. A method according to claim 16 comprising, by the one or more data processors, ranking the infrastructure components based on the one or more fields describing the first conditions of the infrastructure components.

25. A method according to claim 16 comprising limiting the number of infrastructure components associated with each of the groups to be less than a maximum number.

26. A method according to claim 16 wherein the one or more representative values comprise a range of values and computing an estimated future physical condition based on the one or more representative values associated with the first group comprises computing an estimated future physical condition based on a midpoint of the range of values.

27. A method according to claim 16 comprising, by the one or more data processors, for each of the plurality of groups, computing an estimated future physical condition based on the one or more representative values associated with the group;

and, by the one or more data processors, assigning the estimated future physical condition to all of the infrastructure components in the group.

28. A method according to claim 27 wherein the estimated future physical condition comprises a first future condition corresponding to a first time and wherein the method comprises, by the one or more data processors, for the first group, computing a second estimated future physical condition based on the one or more representative values corresponding to a second time;

and wherein the method further comprises, by the one or more data processors, assigning the second future physical condition to all of the objects in the first group.

29. A method according to claim 1 wherein the current physical conditions of the infrastructure components are based at least in part on physical measurements of the component or evaluations of the condition of the component based upon inspections by technical personnel.

30. An infrastructure management system comprising:

one or more data processors;

an inventory database comprising a non-transitory data store storing information identifying infrastructure components of an infrastructure, the stored information including current physical condition information indicative of current physical conditions of the infrastructure components, the current physical conditions each indicating a current degree of deterioration of the corresponding infrastructure component;

a classifier implemented on the one or more data processors and in communication with the inventory database, and configured to sort, by the one or more data processors, the infrastructure components into a plurality of groups based on the current physical condition information for the infrastructure components such that those of the infrastructure components in any one of the groups have current physical condition information satisfying one or more similarity criteria associated with the group;

a future condition determining unit Implemented on the one or more data processors and comprising one or more deterioration models for modeling changes of condition of the infrastructure components over time, each group being associated with one of the one or more deterioration models, the future condition determining unit configured to determine, by the one or more data processors, a time series of predicted future physical conditions for each of the groups based on the deterioration model associated with the group and a representative condition value associated with the group, the representative condition value representative of the current physical conditions of the infrastructure components belonging to the group, and the predicted future physical conditions each comprising a value indicating an estimated degree of deterioration of the infrastructure components of the group at a corresponding one of a plurality of future times which constitute the time series;

an optimizer configured to optimize, by the one or more data processors, a schedule of projects based at least in part on the predicted future physical conditions and one or more constraints, each project associated with one of the groups and comprising at least one of;

replacing, upgrading and refurbishing each of the infrastructure components of the group.

31. An infrastructure management system according to claim 30 wherein the classifier is operative to sort the infrastructure components into the groups at least in part by comparing values indicative of severity of consequences of failure of the infrastructure components to severity ranges wherein one of the severity ranges is associated with each of the groups.