US 12,253,219 B2
Method for detecting leaks in a gas network under pressure or under vacuum and gas network
Philippe Geuens, Wilrijk (BE); and Ebrahim Louarroudi, Wilrijk (BE)
Assigned to ATLAS COPCO AIRPOWER, NAAMLOZE VENNOOTSCHAP, Wilrijk (BE)
Appl. No. 17/418,389
Filed by ATLAS COPCO AIRPOWER, NAAMLOZE VENNOOTSCHAP, Wilrijk (BE)
PCT Filed Nov. 28, 2019, PCT No. PCT/IB2019/060290
§ 371(c)(1), (2) Date Jun. 25, 2021,
PCT Pub. No. WO2020/136475, PCT Pub. Date Jul. 2, 2020.
Claims priority of provisional application 62/785,254, filed on Dec. 27, 2018.
Claims priority of application No. 2019/5838 (BE), filed on Nov. 26, 2019.
Prior Publication US 2022/0057048 A1, Feb. 24, 2022
Int. Cl. F17D 5/02 (2006.01); F15B 19/00 (2006.01); G01M 3/28 (2006.01); G08B 21/18 (2006.01)
CPC F17D 5/02 (2013.01) [F15B 19/005 (2013.01); G01M 3/28 (2013.01); G08B 21/18 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A method for detecting and quantifying leaks in a gas network under pressure or vacuum, the gas network including: one or more sources of compressed gas or vacuum; one or more consumers or consumer areas of compressed gas or vacuum applications; pipelines or a network of pipelines to transport the gas or vacuum from the sources to the consumers, consumer areas or applications; and a plurality of sensors providing one or more physical parameters of the gas at different times and locations within the gas network; wherein the gas network is also provided with one or a plurality of sensors capable of recording the state or status of one or a plurality of sources, consumers, consumer areas or applications and that the method comprises the following steps:
during a start-up phase, calibrating the aforementioned sensors before use;
during a training phase, determining a physical model or mathematical relationship between measurements of a first set of sensors and a second set of sensors based on physical laws using estimation algorithms, wherein the physical model or mathematical relationship represents a relationship between different physical parameters of the gas;
during an operational phase executed after the training phase, using the determined physical model or mathematical relationship between the measurements of the first set of sensors and the second set of sensors from the training phase to predict leaks in the gas network;
wherein the operational phase comprises the following steps:
reading out a first group of sensors;
calculating or determining values of a second group of sensors from the readings of the first group of sensors based on the physical model or mathematical relationship determined in the training phase;
comparing the calculated or determined values of the second group of sensors with the read values of the second group of sensors and determining the difference between them;
determining, on the basis of a residual value analysis, whether there is a leak in the gas network;
generating an alarm and/or generating a leakage rate and/or generating a corresponding leakage cost if a leak is detected.