Water-leak state estimation system, method, and recording medium
US-2018136076-A1 · May 17, 2018 · US
US10830664B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10830664-B2 |
| Application number | US-201916664911-A |
| Country | US |
| Kind code | B2 |
| Filing date | Oct 27, 2019 |
| Priority date | Oct 28, 2018 |
| Publication date | Nov 10, 2020 |
| Grant date | Nov 10, 2020 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods described herein allow for reliable and computationally efficient detection of fluid leak events or abnormal fluid usage/flow events. A fluid flow meter can measure fluid flow parameter values during a training phase. The fluid flow meter can generate, using the fluid flow parameter data, a training fluid flow duration pattern indicative of, for each value range of a plurality of value ranges of a respective time threshold value. The time threshold value can represent an estimate of a maximum fluid flow duration, within a given fluid flow event, for fluid flow associated with the corresponding value range. During a detection phase, the fluid flow meter can determine, for a value range, a respective fluid flow duration within a current fluid flow event. The fluid flow meter can detect a leak event upon the fluid flow duration exceeds the time threshold value for the same value range.
Opening claim text (preview).
What is claimed is: 1. A fluid flow meter comprising: a fluid flow sensor to generate fluid flow measurement signals indicative of fluid flow through a lumen of a fluid distribution system; a memory to store data and computer code instructions; and a processor communicatively coupled to the fluid flow sensor and the memory, the processor to execute the computer code instructions to: determine, using a plurality of first measurement signals generated by the fluid flow sensor during a training phase subsequent to installation of the fluid flow meter in the fluid distribution system, a corresponding plurality of first measurements of a fluid flow parameter and first timing information, the fluid flow parameter including fluid flow rate or fluid flow velocity, and the first timing information indicative of time intervals between consecutive first measurements; identify, using the plurality of first measurements, a plurality of first fluid flow events, each first fluid flow event representing a sequence of non-zero measurements of the plurality of first measurements; generate, using the plurality of first measurements, the first timing information and the plurality of first fluid flow events, a training flow duration pattern including a plurality of bins, each bin representing (i) a value range of a plurality of value ranges of the fluid flow parameter and (ii) a corresponding time duration threshold representing an estimate of maximum cumulative time during which the fluid flow parameter, for any of the plurality of fluid flow events, is within the respective value range; determine, using a plurality of second measurement signals obtained from the fluid flow sensor during a detection phase subsequent to the training phase, a plurality of second measurements of the fluid flow parameter and second timing information, the second timing information indicative of time intervals between consecutive second measurements and the plurality of second measurements associated with a second fluid flow event representing a sequence of non-zero measurements; determine, using the plurality of second measurements and the second timing information, for a first bin of the plurality of bins associated with a respective first value range of the plurality of value ranges, a second time duration representing cumulative time of the second fluid flow event during which the fluid flow parameter is within the first value range; and detect a leak event based on a comparison of the second time duration to the time duration threshold of the first bin. 2. The fluid flow meter of claim 1 , wherein the fluid flow sensor includes an ultrasonic fluid flow sensor. 3. The fluid flow meter of claim 1 , wherein in generating the training flow duration pattern the processor is configured to: assign, for each bin of the plurality of bins, a respective time counter; for each first fluid flow event of the plurality of first fluid flow events, process the respective sequence of non-zero measurements by (i) identifying a bin of the plurality of bins with a respective value range to which a current measurement of the respective sequence of non-zero measurements belongs, and (ii) incrementing a time counter of the identified bin by a time increment equal to a time interval between the current measurement and a preceding measurement; for each bin of the plurality of bins, (a) compare the respective time counter for the bin to the time duration threshold for the bin, and (b) responsive to determining that the time duration threshold for the bin is less than the respective time counter for the bin, update the respective time duration threshold for the bin to be equal to the respective time counter for the bin; and reset, for each bin of the plurality of bins values ranges, the respective time counter to zero after processing the respective sequence of non-zero measurements. 4. The fluid flow meter of claim 3 , wherein in incrementing the respective time counter for the identified bin, the processor is configured to further increment one or more other time counters associated with one or more other bins in the neighborhood of the identified bin by the time increment equal to the time interval between the current measurement and the previous measurement. 5. The fluid flow meter of claim 1 , wherein in generating the training flow duration pattern the processor is configured to: assign, for each bin of the plurality of bins, a respective time counter; for each first fluid flow event of the plurality of first fluid flow events, process the respective sequence of non-zero measurements by (i) determining, for a current measurement, a maximum measurement of already processed measurements among the respective sequence of non-zero measurements, (ii) identifying a bin of the plurality of bins with a respective value range to which the maximum measurement belongs, and (iii) incrementing a respective time counter of the identified bin by a time increment equal to a time interval between the current measurement and a preceding measurement; for each bin of the plurality of bins, (a) compare the respective time counter for the bin to the time duration threshold for the bin, and (b) responsive to determining that the time duration threshold for the bin is less than the respective time counter for the bin, update the respective time duration threshold for the bin to be equal to the respective time counter for the bin; and reset, for each bin of the plurality of bins values ranges, the respective time counter to zero after processing the respective sequence of non-zero measurements. 6. The fluid flow meter of claim 5 , wherein in incrementing the respective time counter for the identified bin, the processor is configured to further increment one or more other time counters associated with one or more other bins in the neighborhood of the identified bin by the time increment equal to the time interval between the current measurement and the previous measurement. 7. The fluid flow meter of claim 1 , wherein in generating the training flow duration pattern the processor is configured to: assign, for each bin of the plurality of bins, a respective time counter; for each first fluid flow event of the plurality of first fluid flow events, process the respective sequence of non-zero measurements by (i) identifying a bin of the plurality of bins with a respective value range of the plurality of value ranges to which a current measurement of the respective sequence of non-zero measurements belongs, and (ii) incrementing time counters of bins equal to or lower than the identified bin by a time increment equal to a time interval between the current measurement and a preceding measurement; for each bin of the plurality of bins, (a) compare the respective time counter for the bin to the time duration threshold for the bin, and (b) responsive to determining that the time duration threshold for the bin is less than the respective time counter for the bin, update the respective time duration threshold for the bin to be equal to the respective time counter for the bin; and reset, for each bin of the plurality of bins, the respective time counter to zero after processing the respective sequence of non-zero measurements. 8. The fluid flow meter of claim 1 , wherein the processor is further configured to post-process the training flow duration pattern by incrementing each time duration threshold associated with a corresponding bin of the plurality of bins with a respective constant time value. 9. The fluid flow meter of claim 1 , further comprising a communication interface for communicating with a remote computing device, the processor further configured to transmit an alert to the remote computing device
Constructional details · CPC title
Arrangement of flowmeters · CPC title
for pipes (G01M3/2892, G01M3/30 take precedence) · CPC title
using electrically-operated integrating means · CPC title
using electromagnetic, electric or electronic means (G01F15/002, G01F15/02 take precedence) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.