Fluid flow analysis and management
A system and method for observing fluid flow behavior at a selected site, deriving judgments and recommendations, and further communicating data, judgments and recommendations. The system receives flow rate information, derives a time series of fluid flow events therefrom, identifies compound events consisting of contemporaneous events, disaggregates compound events by application of an unsupervised model, and applies the unsupervised model to derive a solution space of a subset sum problem-type, wherein historical data of the observed fluid flow is not necessarily accessed. The system derives a prior probability of events associated with an event conditional upon event features and attributes, and thereupon estimates prior probabilities based upon user-derived labels for events from many external sites; and/or derives a posterior probability of labels associated events, conditional upon event features and attributes, and estimates posterior probabilities based upon both prior updated information relating to the selected site and a priori calculated probabilities.
1. A computer-implemented method to acquire and characterize fluid flow information, comprising:
generating a plurality of time series flow rate measurements at a point of a plumbing system;
storing the plurality of time series flow rate measurements in a tangible medium;
determining that an event has started by at least detecting a first change in a magnitude of the flow rate measurements;
determining that the event has concluded based on the magnitude of the flow rate measurements;
associating a plurality of time series flow rate measurements in an event record in response to determining that the event has concluded;
deriving a plurality of event attributes from the plurality of time series flow rate measurements;
storing the event record when the respective flow rate is less than or equal to a baseline flow rate value;
comparing the stored event record with each of a plurality of attributes sets, wherein each attributes set of the plurality of attributes sets is derived from an individual event definition in a library of stored event definitions;
determining a closest matching attributes set in comparison with the event attributes; and
associating the stored event record with an event type identifier based on the closest matching attributes set; and
determining that the event has concluded by at least determining that a combination of changes in magnitude of the flow rate measurements satisfies a subset sum problem.
2. The method of claim 1 , wherein the stored plurality of time series flow rate measurements is associated with a label referenced by the closest matching attributes set.
3. The method of claim 1 , wherein generating the plurality of time series flow rate measurements comprises generating, by a sensor appliance, the plurality of time series flow rate measurements, the method further comprising:
receiving, by a remote device, the plurality of time series flow rate measurements; and
storing, by the remote device, the plurality of time series flow rate measurements.
4. The method of claim 1 , further comprising associating the event type identifier with an equipment type.
5. The method of claim 1 , further comprising associating the event type identifier with an equipment dysfunction.
6. The method of claim 1 , further comprising associating the event type identifier with a recommendation.
7. A device comprising:
processing circuitry;
a wireless interface communicatively coupled with the processing circuitry, the wireless interface configured to receive flow rate measurements from a flow rate monitoring sensor configured to sense a flow rate at a location of a plumbing system; and
a memory communicatively coupled with the processing circuitry and the wireless interface, the memory storing a library of event definitions received prior to receipt of the flow rate measurements from the flow rate monitoring sensor,
wherein the processing circuitry is configured to:
determine that an event has started by at least detecting a first change in the magnitude of the flow rate measurements;
determine that the event has concluded based on the magnitude of the flow rate measurements;
associate a plurality of time series flow rate measurements in an event record in response to determining that the event has concluded;
derive a plurality of event attributes from the plurality of time series flow rate measurements;
individually compare the event attributes with each of a plurality of attributes sets, wherein each attributes set of the plurality of attributes sets is derived from an individual event definition of the library of event definitions;
determine a closest matching attributes set in comparison with the event attributes;
associate the event record with an event type identifier that is associated with the closest matching attributes set; and
determine that the event has concluded by at least determining that a combination of changes in magnitude of the flow rate measurements satisfies a subset sum problem.
8. The device of claim 7 ,
wherein the device further comprises input circuitry communicatively coupled with the memory, and
wherein the processing circuitry is configured to revise the event type identifier based on a user input received via the input circuitry.
9. The device of claim 7 , wherein the processing circuitry is further configured to:
individually compare the stored event record with each of a plurality of combined attributes sets, wherein each combined attributes set is derived from a combination of at least two event definitions of the library of event definitions; and
determine a closest matching combined attributes set in comparison with the stored event record.
10. The device of claim 9 , wherein the processing circuitry is further configured to associate the stored event record with the event type identifier of a compound event.
11. The device of claim 9 , wherein the processing circuitry is further configured to form a first derivative event record, the first derivative event record associated with a first event type identifier associated with one of the attributes set included within the closest matching combined attributes set.
12. The device of claim 11 , wherein the processing circuitry is further configured to form a second derivative event record, the second derivative event record associated with a second event type identifier associated with an additional attributes set included within the closest matching combined attributes set.
13. The device of claim 7 , wherein the event type identifier is associated with an equipment type.
14. The device of claim 7 , wherein the event type identifier is associated with an equipment product name.
15. The device of claim 14 , wherein the event type identifier is associated with a dysfunction of an equipment model.
16. The device of claim 15 , wherein the event type identifier is associated with a recommendation.
17. The device of claim 7 , wherein the processing circuitry is configured to:
determine that a fluid flow rate measurement of the plurality of time series flow rate measurements is above a threshold value;
initialize a time counter in response to determining that the fluid flow rate measurement is above the threshold value;
determine that a current value of the time counter is greater than or equal to a time length constant after initializing the time counter; and
issue an alert in response to determining that the current value of the time counter exceeds the time length constant.
18. The device of claim 7 , wherein the processing circuitry is configured to:
determine a variance for the closest matching attributes set,
determine, when the variance is outside a variance range, an additional matching attributes set in comparison with the variance, wherein the additional matching attributes set is derived from an additional individual event definition of the library of event definitions, and
associate the event record with the event type identifier that is associated with the closest matching attributes set and the event type identifier that is associated with the additional matching attributes set.
19. The device of claim 7 , wherein the processing circuitry is configured to:
assign, to data associated with the event, a time of day parameter; and
assign, to data associated with the event, a frequency of occurrence of the event type identifier at the assigned time of day parameter.