Determining expected failure modes of balloons within a balloon network
View Patent ↗Example methods and systems for determining failure modes of balloons within a balloon network are described. One example method includes: (a) determining at least one cohort balloon of a first balloon, where the first balloon is operating as part of a balloon network and where each cohort balloon shares at least one property with the first balloon, (b) determining at least one expected failure mode based at least in part on at least one failure of at least one cohort balloon, (c) determining a predicted failure mode of the first balloon based at least in part on the at least one expected failure mode, and (d) causing the first balloon to operate within the balloon network based at least in part on the predicted failure mode of the first balloon.
1. A computer-implemented method comprising:
determining a similarity metric between a first balloon and each of a plurality of balloons operating as part of a balloon network, wherein the similarity metric between the first balloon and a particular balloon of the plurality of balloons indicates an amount of similarity between the first balloon and the particular balloon based on one or more shared properties between the first balloon and the particular balloon;
identifying, based on the similarity metric between the first balloon and each of the plurality of balloons, at least one cohort balloon from the plurality of balloons operating as part of the balloon network;
identifying at least one failure of the at least one cohort balloon;
determining a predicted failure mode of the first balloon based on the at least one identified failure of the at least one cohort balloon; and causing the first balloon to operate within the balloon network based on the predicted failure mode of the first balloon.
2. The method of claim 1 , further comprising:
receiving sensor data from at least one sensor located on the first balloon; and
wherein the predicted failure mode of the first balloon is determined based at least in part on the sensor data.
3. The method of claim 1 , wherein determining the predicted failure mode of the first balloon comprises determining a weighted average of a plurality of failures of the at least one cohort balloon.
4. The method of claim 1 , wherein determining the predicted failure mode of the first balloon comprises determining a probability distribution over time of a plurality of failures of the at least one cohort balloon.
5. The method of claim 1 , wherein determining the predicted failure mode of the first balloon comprises determining a failure mode from a plurality of failure modes that is expected to occur at an earliest point in time.
6. The method of claim 1 , further comprising periodically updating the predicted failure mode of the first balloon based at least in part on at least one additional failure of the at least one cohort balloon.
7. The method of claim 1 , wherein at least one property shared by one or more of the cohort balloons and the first balloon comprises a specific balloon model.
8. The method of claim 1 , wherein at least one property shared by one or more of the cohort balloons and the first balloon comprises a manufacturer.
9. The method of claim 1 , wherein at least one property shared by one or more of the cohort balloons and the first balloon comprises a material used in the construction of the first balloon.
10. The method of claim 1 , wherein at least one property shared by one or more of the cohort balloons and the first balloon comprises a supplier.
11. The method of claim 1 , wherein at least one property shared by one or more of the cohort balloons and the first balloon comprises a production batch.
12. The method of claim 1 , wherein the predicted failure mode of the first balloon comprises a failure in a balloon material.
13. The method of claim 1 , wherein the predicted failure mode of the first balloon comprises a failure in a communication system of the first balloon.
14. The method of claim 1 , wherein the predicted failure mode comprises a failure in a power system of the first balloon.
15. The method of claim 2 , wherein the at least one sensor comprises at least one strain sensor.
16. The method of claim 2 , wherein the at least one sensor comprises at least one pressure gauge.
17. The method of claim 2 , wherein the at least one sensor comprises at least one temperature sensor.
18. The method of claim 2 , wherein the at least one sensor comprises at least one light sensor.
19. The method of claim 2 , wherein the at least one sensor comprises at least one altitude sensor.
20. The method of claim 2 , wherein the at least one sensor comprises at least one acoustic resonance sensor.
21. A non-transitory computer readable storage medium having stored therein instructions, that when executed by a computing device, cause the computing device to perform functions comprising:
determining a similarity metric between a first balloon and each of a plurality of balloons operating as part of a balloon network, wherein the similarity metric between the first balloon and a particular balloon of the plurality of balloons indicates an amount of similarity between the first balloon and the particular balloon based on one or more shared properties between the first balloon and the particular balloon;
identifying, based on the similarity metric between the first balloon and each of the plurality of balloons, at least one cohort balloon from the plurality of balloons operating as part of the balloon network;
identifying at least one failure of the at least one cohort balloon;
determining a predicted failure mode of the first balloon based on the at least one identified failure of the at least one cohort balloon; and
causing the first balloon to operate within the balloon network based on the predicted failure mode of the first balloon.
22. The non-transitory computer readable storage medium of claim 21 , further comprising instructions, that when executed by the computing device, cause the computing device to perform a function comprising receiving sensor data from at least one sensor located on the first balloon; and
wherein the predicted failure mode of the first balloon is determined based at least in part on the sensor data.
23. The non-transitory computer readable storage medium of claim 21 , wherein determining the predicted failure mode of the first balloon comprises determining a weighted average of a plurality of failures of a plurality of cohort balloons.
24. A system, comprising: at least one processor; and data storage comprising program instructions executable by the at least one processor to cause the at least one processor to perform functions comprising:
determining a similarity metric between a first balloon and each of a plurality of balloons operating as part of a balloon network, wherein the similarity metric between the first balloon and a particular balloon of the plurality of balloons indicates an amount of similarity between the first balloon and the particular balloon based on one or more shared properties between the first balloon and the particular balloon;
identifying, based on the similarity metric between the first balloon and each of the plurality of balloons, at least one cohort balloon from the plurality of balloons operating as part of the balloon network;
identifying at least one failure of the at least one cohort balloon;
determining a predicted failure mode of the first balloon based on the at least one identified failure of the at least one cohort balloon; and
causing the first balloon to operate within the balloon network based on the predicted failure mode of the first balloon.
25. The system of claim 24 , wherein the data storage further comprises program instructions executable by the at least one processor to cause the at least one processor to perform a function comprising:
receiving sensor data from at least one sensor located on the first balloon; and
wherein the predicted failure mode of the first balloon is determined based at least in part on the sensor data.
26. The system of claim 24 , wherein determining the failure mode of the first balloon comprises determining a weighted average of a plurality of failures of a plurality of cohort balloons.
27. The method of claim 1 , further comprising:
comparing the similarity metric between the first balloon and each of the plurality of balloons to a threshold;
identifying at least one balloon of the plurality of balloons for which the similarity metric between the first balloon and the at least one identified balloon is above the threshold; and
determining the at least one cohort balloon to be the at least one identified balloon of the plurality of balloons for which the similarity metric is above the threshold.
28. The method of claim 1 , further comprising:
identifying a number of shared properties between the first balloon and each of the plurality of balloons; and
determining the at least one cohort balloon to be at least one balloon of the plurality of balloons for which the identified number of shared properties between the first balloon and the at least one balloon is above a threshold number of shared properties.
29. The method of claim 1 , further comprising:
identifying, based on the similarity metric between the first balloon and each of the plurality of balloons, a certain number of nearest neighbour balloons from the plurality of balloons, wherein the nearest neighbour balloons are the certain number of most similar balloons to the first balloon out of the plurality of balloons; and
determining the at least one cohort balloon to be the nearest neighbour balloons.