	US 12,276,638 B2
	Systems, methods, and media for generating alerts of water hammer events in steam pipes
Peter Owens, Hingham, MA (US); and David Micallef, Rabat (MT)
Assigned to Latency, LLC, Hingham, MA (US)
Filed by Latency, LLC, Hingham, MA (US)
Filed on Mar. 29, 2021, as Appl. No. 17/215,812.
Application 17/215,812 is a continuation in part of application No. 16/796,607, filed on Feb. 20, 2020.
Claims priority of provisional application 63/000,675, filed on Mar. 27, 2020.
Claims priority of provisional application 62/808,113, filed on Feb. 20, 2019.
Prior Publication US 2021/0215645 A1, Jul. 15, 2021
Int. Cl. G01N 29/46 (2006.01); F17D 1/06 (2006.01); G01N 29/12 (2006.01); G06N 3/04 (2023.01); G08B 21/18 (2006.01)

CPC G01N 29/46 (2013.01) [F17D 1/06 (2013.01); G01N 29/12 (2013.01); G06N 3/04 (2013.01); G08B 21/182 (2013.01); G01N 2291/021 (2013.01); G01N 2291/044 (2013.01)]

15 Claims

1. A system for generating an alert of an event in a steam pipe, comprising:

a memory;

a first hardware processor that is coupled to the memory and that is configured to at least:

obtain temperature measurements of the steam trap;

sample an accelerometer coupled to a steam pipe to provide accelerometer data;

determine that the accelerometer data meets or exceeds a threshold;

in response to the determining that the accelerometer data meets or exceeds the threshold:

increase the sample frequency at which the accelerometer is sampled; and

sample an ultrasonic sensor to provide ultrasonic sensor data;

detect a failed closed steam trap by detecting no accelerations in the steam trap, detecting decreased ultrasonic noise based on the ultrasonic sensor data, and detecting a drop in temperature of the steam trap; and

generate an alert of the failed closed steam trap; and

a second hardware processor that is configured to at least:

receive a plurality of alerts that a water hammer event has occurred;

determine that a period of time has passed since a first of the plurality of alerts was received; and

in response to determining that the period of time has passed, compare data from multiple sensor modules to identify one of the multiple sensor modules that is closest to the water hammer event.