US-12618742-B2 - Periodic water leak detection

US12618742B2US 12618742 B2US12618742 B2US 12618742B2US-12618742-B2

Abstract

Methods, systems, and apparatus for periodic water leak detection are disclosed. A method includes obtaining, using a water meter, water meter data representing the occurrence of water usage events at a property; determining, based on the water meter data, a periodicity of water usage events; determining that the periodicity of water usage events satisfies water leak criteria; and based on determining that the periodicity of water usage events satisfies water leak criteria, determining that a water leak exists at the property. Determining the periodicity of water usage events can include determining an average time between a start of sequential water usage events; and determining that the periodicity of water usage events satisfies water leak criteria can include determining that the average time between the start of sequential water usage events is less than a threshold time between the start of sequential water usage events.

Inventors

Grant Rudd
Robert Nathan Picardi
Daniel Marc Goodman
Craig Carl Heffernan
Harrison Wayne Donahue
Liam Shea Daly
Marc Anthony Epard

Assignees

ALARM.COM INCORPORATED

Dates

Publication Date: 20260505
Application Date: 20230918

Claims (20)

1 . A computer-implemented method for detecting a leak in an automatic refilling tank of a plumbing system, comprising: obtaining, by at least one of one or more processors, water usage data representing quantities of water flow events occurring at respective frequencies within the plumbing system; determining, by at least one of the one or more processors and using the water usage data, that a quantity of water flow events occurring at a particular frequency satisfies one or more water leak criteria; and in response to determining that the quantity of water flow events occurring at the particular frequency satisfies the one or more water leak criteria, determining, by at least one of the one or more processors, that a water leak exists in the automatic refilling tank.
2 . The computer-implemented method of claim 1 , wherein a water flow event comprises an event in which a water flow rate within the plumbing system satisfies a threshold water flow rate.
3 . The computer-implemented method of claim 2 , wherein a water flow event comprises an event in which the water flow rate within the plumbing system satisfies the threshold water flow rate for a time duration that satisfies a threshold time duration.
4 . The computer-implemented method of claim 2 , wherein a water flow event comprises an event in which the water flow rate within the plumbing system satisfies the threshold water flow rate for a time duration that exceeds a minimum threshold time duration and is less than a maximum threshold time duration.
5 . The computer-implemented method of claim 1 , wherein a start of a water flow event comprises a time when water usage measured by a water meter within the plumbing system rises above zero gallons per minute.
6 . The computer-implemented method of claim 1 , wherein: the water usage data includes at least one frequency peak; and determining that the quantity of water flow events occurring at the particular frequency satisfies the one or more water leak criteria comprises determining that a magnitude of a frequency peak at the particular frequency exceeds a threshold magnitude.
7 . The computer-implemented method of claim 1 , wherein determining that the water leak exists in the automatic refilling tank further comprises determining, using the water usage data, that an average time between the start of sequential water flow events is less than a threshold time between the start of sequential water flow events.
8 . The computer-implemented method of claim 1 , wherein determining that the water leak exists in the automatic refilling tank further comprises determining, using the water usage data, that a periodicity of water flow events satisfies a threshold periodicity.
9 . The computer-implemented method of claim 1 , wherein: the automatic refilling tank is one of a plurality of automatic refilling tanks of the plumbing system, each of the plurality of automatic refilling tanks having a respective refilling time duration; and determining that the water leak exists in the automatic refilling tank further comprises: determining, using the water usage data, a duration of each of the water flow events occurring at the particular frequency; and determining that the duration of each of the water flow events occurring at the particular frequency corresponds with a refilling time duration of the automatic refilling tank.
10 . The computer-implemented method of claim 1 , comprising: in response to determining that a water leak exists in the automatic refilling tank, transmitting, to a computing device, a notification that the water leak exists in the automatic refilling tank.
11 . The computer-implemented method of claim 1 , comprising: in response to determining that a water leak exists in the automatic refilling tank, transmitting, to a water valve within the plumbing system, an instruction that causes the water valve to adjust position.
12 . The computer-implemented method of claim 1 , wherein the water usage data includes a frequency domain waveform.
13 . The computer-implemented method of claim 1 , wherein the automatic refilling tank comprises a toilet tank, a water heater, a boiler, a fountain, a pond, a pool, an aquarium, or a fire suppression system tank.
14 . One or more non-transitory computer readable storage media storing instructions executable by a data processing apparatus and upon such execution cause the data processing apparatus to perform operations for detecting a leak in an automatic refilling tank of a plumbing system, the operations comprising: obtaining water usage data representing quantities of water flow events occurring at respective frequencies within the plumbing system; determining, using the water usage data, that a quantity of water flow events occurring at a particular frequency satisfies one or more water leak criteria; and in response to determining that the quantity of water flow events occurring at the particular frequency satisfies the one or more water leak criteria, determining, that a water leak exists in the automatic refilling tank.
15 . The one or more non-transitory computer readable storage media of claim 14 , wherein a water flow event comprises an event in which a water flow rate within the plumbing system satisfies a threshold water flow rate.
16 . The one or more non-transitory computer readable storage media of claim 15 , wherein a water flow event comprises an event in which the water flow rate within the plumbing system satisfies the threshold water flow rate for a time duration that satisfies a threshold time duration.
17 . The one or more non-transitory computer readable storage media of claim 15 , wherein a water flow event comprises an event in which the water flow rate within the plumbing system satisfies the threshold water flow rate for a time duration that exceeds a minimum threshold time duration and is less than a maximum threshold time duration.
18 . The one or more non-transitory computer readable storage media of claim 14 , wherein a start of a water flow event comprises a time when water usage measured by a water meter within the plumbing system rises above zero gallons per minute.
19 . The one or more non-transitory computer readable storage media of claim 14 , wherein: the water usage data includes at least one frequency peak; and determining that the quantity of water flow events occurring at the particular frequency satisfies the one or more water leak criteria comprises determining that a magnitude of a frequency peak at the particular frequency exceeds a threshold magnitude.
20 . A system comprising: one or more computers; and one or more storage devices, the one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations for detecting a leak in an automatic refilling tank of a plumbing system, the operations comprising: obtaining, by at least one of the one or more computers, water usage data representing quantities of water flow events occurring at respective frequencies within the plumbing system; determining, by at least one of the one or more computers and using the water usage data, that a quantity of water flow events occurring at a particular frequency satisfies one or more water leak criteria; and in response to determining that the quantity of water flow events occurring at the particular frequency satisfies the one or more water leak criteria, determining, by at least one of the one or more computers, that a water leak exists in the automatic refilling tank.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is a continuation of U.S. application Ser. No. 17/398,214, filed Aug. 10, 2021, which claims the benefit of U.S. Provisional Application No. 63/065,025, filed Aug. 13, 2020, and titled “Water Leak Detection.” The disclosure of each of the foregoing applications is incorporated herein by reference. TECHNICAL FIELD This specification relates generally to water monitoring technology. BACKGROUND Water can be consumed at a property through plumbing fixtures such as sinks, toilets, and showers. The amount of water consumption at the property can be monitored using a water meter. The water meter can measure the rate of water flowing through a pipe to the property. SUMMARY The subject matter of the present disclosure is related to technique for detecting water leaks at a property, controlling the flow of water into the monitored property, and performing other functions. A water meter can monitor water consumption rates of the property over time. By monitoring patterns of water consumption, the water meter can detect water leaks at the property. Water leaks may occur in plumbing systems of a property. Some water leaks may be small, and might not be steady or constant. For example, a small water leak from a self-filling tank, e.g., a toilet tank, might cause the tank to refill periodically. Leaks that are periodic or inconsistent can be difficult to detect. An example process for detecting periodic leaks includes counting, using a meter, the number of water flow events, or water usage events, within a specified time period. Normal water usage often includes a high number of water usage events over a short period of time, e.g., when occupants wash dishes or take showers, with long periods of little to no flow events, e.g., when the property is unoccupied, or occupants are sleeping. The number of water usage events per unit time over an extended period is therefore often small in a normal water usage scenario. When there is a periodic water leak at the property, there will likely be a higher number of water usage events during the times where little to no water usage is expected, thus increasing the number of water usage events per unit time. The meter can thus detect abnormal water usage based on the number of usage events that occur at the property during a time duration. If the number of water usage events meets criteria for a water leak, the water meter can perform a system action such as transmitting a notification of the water leak to a user, shutting off water flow to the house, sounding an audible alarm, or a number of other actions. Some processes for detecting periodic leaks rely on detecting water usage periodicity. These processes can allow the meter to detect the periodic leak more quickly than detection methods that are based on counting the number of water usage events. In some examples, Fast Fourier Transform (FFT) or autocorrelation can be used to extract the periodicity of water usage events and trigger an alert if the periodicity meets criteria for a water leak, e.g., by rising above a threshold periodicity. The FFT and autocorrelation processes can extract periodicity from a noisy signal, where noise can be defined as flow events that are non-periodic or random in nature. In some examples, periodic leaks can be detected by measuring the time between flow events and performing statistical analysis to determine the periodicity of the flow events. If the periodicity of the flow events meets criteria for a water leak, the water meter can perform a system action. In general, one innovative aspect of the subject matter described in this specification can be embodied in a method including obtaining, using a water meter, water meter data representing the occurrence of water usage events at a property; determining, based on the water meter data, a periodicity of water usage events; determining that the periodicity of water usage events satisfies water leak criteria; and based on determining that the periodicity of water usage events satisfies water leak criteria, determining that a water leak exists at the property. The foregoing and other embodiments can each optionally include one or more of the following features, alone or in combination. In some implementations, determining the periodicity of water usage events includes determining an average time between a start of sequential water usage events; and determining that the periodicity of water usage events satisfies water leak criteria includes determining that the average time between the start of sequential water usage events is less than a threshold time between the start of sequential water usage events. In some implementations, the water meter data includes a waveform of water usage in the time domain. In some implementations, the waveform of water usage in the time domain includes a waveform of water flow rate varying over time. In some implementations, determining the periodicity of water usage