Techniques for determining a location of a leak in a water distribution system are described herein. In some examples, a remote leak detection service and/or a leak detection device may receive measurements from a pressure sensor, a contamination sensor, and a flow rate sensor positioned along the water distribution system. Based on a difference in time between a change in pressure detected by the pressure sensor and a subsequent change in contamination detected by the contamination sensor, the flow rate measured by the flow rate sensor, and dimensions of the water distribution system, the remote leak detection system may determine the location of the leak.

Example aspects of a nozzle cap for a fire hydrant and a method of detecting a leak in a fluid system are disclosed. The nozzle cap for a fire hydrant can include an outer housing defining a first end, a second end opposite the first end, and a substantially circumferential wall extending from the first end to the second end; an antenna coupled to the substantially circumferential wall of the outer housing; a cap cover coupled to the outer housing at the first end; and an inner housing coupled to the outer housing at the second end.

A device that detects fluid flow may include a housing member that couples to a conduit and an apparatus that outputs the fluid. The device may also include a flow mechanism that detects the fluid flow through the conduit and the apparatus and a transmitter that transmits a signal indicative of the fluid flow to a computing device.

Converting a sound to a sound signature and then interpreting the signature based on a machine learning analytical approach. Generally, “interpreting” means quantifying and classifying. A system for identifying statuses of one or more target objects may comprise a device for observing sounds comprising a sound detector, a housing affixing the sound detector on, or in the vicinity of a target object, a processor, a power supply, and a device interface. The system may further comprise a data transmitter, a remote server for receiving data from one or more devices for observing sound of a target object and/or the surrounding environment, a plurality of server-side applications applying analytical operations to the data, and a plurality of end-user devices for accessing the data through a plurality of user interfaces. The status identification system can be used to detect statuses and events of target objects.

The invention relates in part to an autonomous, self-powered valve for continuous monitoring of water flow within a domestic or commercial water pipe network. The invention also relates to a network in which the valve is remotely monitored for detection of abnormalities in water use patterns.

Provided are an analyzing device and the like capable of suppressing erroneous determination. This analyzing device is provided with: a cross correlation calculating unit that obtains a cross correlation function with respect to vibrations detected at two points contained in a measurement sector of a pipeline; an estimating unit that estimates a cause of the vibrations, on the basis of the continuity of peaks in the cross correlation function; and an analyzing unit that analyzes the actual generation location of the vibrations and cause of the vibrations on the basis of an estimated generation location of the vibrations and cause of the vibrations and information relating to the configuration of a pipeline network.

A water monitoring system has aback-end system comprising an authentication module, a machine learning module, an alerts module, and a third-party module. The back-end system remotely connects to a local system which has a water monitoring device and the authentication module authenticates the connection relative to a user. The back-end system remotely connects to a third-party system using the third-party module and the authentication module authenticates the connection relative to the same user. The back-end system receives data from the local system and the third-party system, the machine learning module analyzes the data to determine one or more rules which identify water usage as intended or unintended, and the alerts module provides an alert to one or more of the local system, the third-party system, or a client device when the water monitoring device measures water flow data which indicates a leak according to the one or more rules.

Disclosed is a sensor system for retrofitting a water supply of an airplane to detect leakage. The system includes a housing having a first band with an inner diameter sized to receive a necked portion of a valve for consumer access to the water supply. The system includes a first transducer disposed on the first band operable to provide a position measurement corresponding to a relative position between a head of the valve and the necked portion. The system includes a second transducer operable to provide a pressure measurement corresponding to a pressure of a compressed gas in a water tank of the water supply. The system includes a controller having input channels operable to receive the position measurement and the pressure measurement. The controller is operable to indicate a leak condition.

Techniques for managing delivery of water or other fluids have been disclosed. A central server provides real-time data and cost analysis to a client. In addition, fluid delivery techniques provide alerts or automatic schedule suspensions to reduce risk of loss. The techniques reduce or eliminate the impact of air or gas captured with water or other fluid of a fluid delivery system. The techniques allow a preexisting fluid delivery system to be retrofitted to communicate with a central system and one or more sensors of a fluid delivery system.

Disclosed herein is a method and system for predicting water leakage events in district metered area of water distribution network. The method comprises receiving historic data of water flow and water pressure associated with DMA for predicting flow data and pressure data of water in the DMA for predefined future time period. Thereafter, method comprises retrieving plurality of cluster points corresponding to the predicted flow data, the pressure data, and an anomaly score identified for each of the plurality of cluster points from machine learning model. The method detects one or more cluster points as anomaly points by comparing anomaly scores with lower bound value and upper bound value and thereafter predicts leakage events corresponding to each of the detected anomaly points. In this manner, present disclosure predicts water leakage events in DMA for future time intervals and hence necessary leakage maintenance actions may be taken to avoid such events.