Failure modeling by incorporation of terrestrial conditions
A system and method to schedule inspections for a plurality of assets at a corresponding plurality of outdoor locations are described. The method includes retrieving location attributes of each of the plurality of assets, retrieving terrestrial geotagged images that include one or more of the plurality of assets, obtaining parameters associated with each of the plurality of assets based on information from the images, and determining risk factors associated with each of the plurality of assets based on the associated parameters and a failure mapping. The method also includes determining a risk score for each of the plurality of assets based on the corresponding risk factors, and scheduling inspections of the plurality of assets based on the risk score associated with each of the plurality of assets.
1. A system comprising:
an input interface configured to obtain a selection of a set of utility poles; and
a processor configured to:
retrieve aerial images of a subset of the set of utility poles, the aerial images comprising terrestrial geotagged images including geotagged image data;
for each of a plurality of inspected utility poles of the set of utility poles:
determine a risk vector for a particular inspected utility pole of the plurality of inspected utility poles, the risk vector including a set of risk factors associated with the particular inspected utility pole, each of the risk factors quantifying a risk of a different type of failure, the risk factors including a probability of mechanical breakdown, a risk of wood rot and a risk of forest fire, each of the risk factors being within a same predetermined range, each of the risk factors having been determined from inspection;
determine a parameter vector for the particular inspected utility pole of the plurality of inspected utility poles, the parameter vector including a first set of parameters associated with the particular inspected utility pole, one parameter of the first set of parameters associated with the particular inspected utility pole including a value based on geographic location of the particular inspected utility pole, the first set of parameters being obtained from a physical inspection of the particular inspected utility pole, the first set of parameters also being determined based on the terrestrial geotagged images of the particular inspected utility pole, the geographic location of the particular inspected utility pole being obtained from a global positioning system associated with the particular inspected utility pole; and
determine a failure mapping array for the particular inspected utility pole of the plurality of inspected utility poles, the failure mapping array being determined based on a ratio of the risk vector for the particular inspected utility pole and the parameter vector for the particular inspected utility pole;
determine a failure mapping matrix (F) based on the plurality of failure mapping arrays associated with the plurality of inspected utility poles, the determining the failure mapping matric (F) comprising at least a portion of a machine learning process;
obtain, from the geotagged image data, a second set of parameters for each of a plurality of uninspected utility poles of the set of utility poles, wherein to obtain includes:
assign, by the processor, grayscale values to pixels of the terrestrial geotagged images;
identify, by the processor, types of areas in the terrestrial geotagged images by grayscale values of pixels; and
identify, by the processor, at least one of the parameters of the second set of parameters by parameterizing a ratio of a number of pixels identified as a particular type of area to a total number of pixels in a particular terrestrial geotagged image;
determine, based on the second set of parameters and the failure mapping matrix (F), a risk vector for each of the plurality of uninspected utility poles being based on the set of risk factors associated with the plurality of uninspected utility poles;
determine a respective risk score for each of the plurality of uninspected utility poles, each of the respective risk scores determined based on the risk vector for each of the plurality of uninspected utility poles;
determine a schedule for inspection of the plurality of uninspected utility poles based on the respective risk scores of the plurality of uninspected utility poles to determine the portion of the plurality of uninspected utility poles which require inspection sooner than another portion of the plurality of uninspected utility poles, such that the plurality of uninspected utility poles may be inspected according to the schedule; and
schedule a plurality of inspections of the plurality of uninspected utility poles according to the schedule.
2. The system according to claim 1 , further comprising a memory device, wherein the processor obtains the terrestrial geotagged images from the memory device.
3. The system according to claim 1 , wherein the processor obtains the terrestrial geotagged images from the input interface via a geographic information system (GIS) application.
4. The system according to claim 1 , wherein the processor identifies at least one of the parameters of the second set of parameters based on the information from the terrestrial geotagged images by parameterizing a distance from each of the plurality of uninspected utility poles to a corresponding nearest road and a distance from each of the plurality of uninspected utility poles to a corresponding nearest intersection.
5. The system according to claim 1 , wherein the processor identifies at least one of the parameters of the second set of perameters based on information from the terrestrial geotagged images by parameterizing a ratio of a size of an area comprising woods, water, or grass to a total size of an area of a corresponding image of the terrestrial geotagged images.
6. The system according to claim 1 , wherein the processor is further configured to determine risk points associated with each of the plurality of uninspected utility poles based on the associated parameters.
7. The system according to claim 6 , wherein the processor determines the risk score of each of the plurality of uninspected utility poles based on corresponding risk factors and corresponding risk points of each of the plurality of uninspected utility poles.
8. The system according to claim 1 , wherein the processor solves the failure mapping (F) based on inspecting and analyzing the plurality of inspected utility poles.
9. An apparatus, comprising:
a processor; and
a non-transitory computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:
retrieving aerial images of a plurality of inspected utility poles and a plurality of uninspected utility poles, the aerial images comprising terrestrial geotagged images which includes geotagged image data;
for each of the plurality of inspected utility poles:
determining a risk vector for a particular inspected utility pole of the plurality of inspected utility poles, the risk vector including a set of risk factors associated with the particular inspected utility pole, each of the risk factors of the set of risk factors being associated with one or more inspected utility poles of the plurality of inspected utility poles, each of the risk factors quantifying a risk of a different type of failure, the risk factors including a probability of mechanical breakdown, a risk of wood rot and a risk of forest fire, each of the risk factors being within a same predetermine range, each of the risk factors having been determined from inspection;
determining a parameter vector for the particular inspected utility pole of the plurality of inspected utility poles, the parameter vector including a first set of parameters associated with the particular inspected utility pole, one parameter of the first set of parameters associated with the particular inspected utility pole including a value based on geographic location of the particular inspected utility pole, the first set of parameters being obtained from a physical inspection of the particular inspected utility pole, the first set of parameters also being determined based on the terrestrial geotagged images of the particular inspected utility pole, the geographic location of the particular inspected utility pole being obtained from a global positioning system associated with the particular inspected utility pole; and
determining a failure mapping array for the particular inspected utility pole of the plurality of inspected utility poles, the failure mapping array being determined based on a ratio of the risk vector for the particular inspected utility pole and the parameter vector for the particular inspected utility pole;
determining a failure mapping matrix (F) based on the plurality of failure mapping arrays associated with the plurality of inspected utility poles, the determining the failure mapping matrix (F) comprising at least a portion of a machine learning process;
obtaining, from the geotagged image data, a second set of parameters for each of the plurality of uninspected utility poles, wherein obtaining includes:
assigning, by the processor, grayscale values to pixels of the terrestrial geotagged images;
identifying, by the processor, types of areas in the terrestrial geotagged images by grayscale values of pixels; and
identifying, by the processor, at least one of the parameters of the second set of parameters by parameterizing a ratio of a number of pixels identified as a particular type of area to a total number of pixels in a particular terrestrial geotagged image;
determining, based on the second set of parameters and the failure mapping matrix (F), a risk vector for each of the plurality of uninspected utility poles, the risk vector for each of the plurality of uninspected utility poles being based on the set of risk factors associated with the plurality of uninspected utility poles;
determining a respective risk score for each of the plurality of uninspected utility poles, each of the respective risk scores determined based on the risk vector for each of the plurality of uninspected utility poles;
determining a schedule for inspection of the plurality of uninspected utility poles based on the respective risk scores of the plurality of uninspected utility poles to determine the portion of the plurality of uninspected utility poles which require inspection sooner than another portion of the plurality of uninspected utility poles, such that the plurality of uninspected utility poles may be inspected according to the schedule; and
scheduling a plurality of inspections of the plurality of uninspected utility poles according to the schedule.
10. The apparatus according to claim 9 , wherein the processor obtains the terrestrial geotagged images from a memory device.
11. The apparatus according to claim 9 , wherein the processor obtains the terrestrial geotagged images from a geographic information system (GIS) application.
12. The apparatus according to claim 9 , wherein the processor identifies at least one of the parameters of the second set of parameters based on information from the terrestrial geotagged images by parameterizing a distance from each of the plurality of uninspected utility poles to a corresponding nearest road and a distance from each of the plurality of uninspected utility poles to a corresponding nearest intersection.
13. The apparatus according to claim 9 , wherein the processor identifies at least one of the parameters of the second set of parameters based on information from the terrestrial geotagged images by parameterizing a ratio of a size of an area comprising woods, water, or grass to a total size of an area of a corresponding image of the terrestrial geotagged images.
14. The apparatus according to claim 9 , wherein the operations further comprise:
determining risk points associated with each of the plurality of uninspected utility poles based on the associated second set of parameters.
15. The apparatus according to claim 14 , wherein the risk score of each of the plurality of uninspected utility poles is determined based on corresponding risk factors and corresponding risk points of each of the plurality of uninspected utility poles.
16. The apparatus according to claim 9 , wherein the failure mapping matrix (F) is solved based on inspecting and analyzing the plurality of inspected utility poles.
17. The system according to claim 5 wherein the processor identifies at least one of the parameters of the second set of parameters based on a ratio of a number of pixels in the area comprising woods, water, or grass to a number of pixels in the area of the corresponding image of the terrestrial geotagged images.
18. The apparatus according to claim 13 wherein the processor identifies at least one of the parameters of the second set of parameters based on a ratio of a number of pixels in the area comprising woods, water, or grass to a number of pixels in the area of the corresponding image of the terrestrial geotagged images.