FLUID LEAK DETECTION SYSTEM, FLUID LEAK DETECTOR AND TRAINING DEVICE Russian patent published in 2021 - IPC G01M3/00 G01M3/02 G01M3/38 

Abstract RU 2759815 C1

FIELD: fluid leak detection systems.

SUBSTANCE: invention relates to a fluid leak detection system for detecting fluid leaks in buildings. A fluid leakage detection system comprising: a plurality of sensors provided in the building, which respectively detect detection target values ​​at their mounting positions; a fluid leak detection device that detects a fluid leak in a building by a leak state estimation algorithm used to estimate a fluid leak state in a building based on the detection target values ​​detected by the plurality of sensors; and a teaching unit that trains a leak state estimation algorithm, the fluid leak detecting device comprises: an actual measured value acquiring unit that obtains detection target value values ​​detected by the plurality of sensors; and a leakage state estimating unit that estimates the leakage state of a fluid in a building by an algorithm for estimating a leak condition based on distributions of detection target value values ​​obtained by the actual measured value obtaining unit, the teaching unit comprises: a teaching unit that trains an algorithm for evaluating a leak state by means of machine teaching unit, as training data, the values ​​of the detection target values ​​respectively detected by a plurality of sensors during a fluid leak from a predetermined position of the building; a structural data storage unit that stores structural data of a building; and a 3D flow simulator that simulates the behavior of a fluid in a building during fluid leakage from a predetermined position of a building by performing a 3D flow simulation based on the structural data of the building stored in the structural data storage unit, the teaching unit teaching the leak state estimation algorithm by machine learning, further using, as training data, the detection target values ​​calculated based on the result of the 3D flow simulation performed by the 3D flow simulator.

EFFECT: accurate detection of fluid leakage conditions in buildings.

17 cl, 7 dwg

Similar patents RU2759815C1

Title Year Author Number
SYSTEM AND METHOD OF FUEL LEAK DETECTION AND METHOD OF FLUID MEDIUM LEAK DETECTION 2013
  • Romig Bryan Wesley
  • Simons Derrick
  • Dean Douglas
RU2615303C2
METHOD FOR EQUIPMENT CONTROL, EQUIPMENT DESIGN DEVICE AND EQUIPMENT CONTROL DEVICE 2020
  • Ikawa Shizuka
  • Yasui Takehito
  • Furuichi Kazuya
  • Hamada Yuki
RU2785523C1
METHOD OF LOCATING FIRE SOURCE USING MULTILAYER RECURRENT PERCEPTRON 2021
  • Malykhina Galina Fedorovna
  • Krugleevskii Vladimir Nikolaevich
  • Obraztsov Ivan Viktorovich
  • Guseva Alena Igorevna
RU2815322C2
SYSTEM FOR ASSISTANCE IN SETTING OF INSTALLATION OPERATING MODE, TRAINING DEVICE, AND DEVICE FOR ASSISTANCE IN SETTING OF OPERATING MODE 2019
  • Yasui Takehito
  • Ikawa Shizuka
  • Toki Akifumi
  • Sogabe Masaru
  • Suwa Yusuke
RU2780340C2
METHOD FOR CREATING CONTROLLERS FOR CONTROLLING WALKING ROBOTS BASED ON REINFORCEMENT LEARNING 2022
  • Babaev Azer Kakhraman Ogly
  • Volchenkov Andrej Valerevich
  • Gorbachev Roman Aleksandrovich
  • Davydenko Egor Viktorovich
  • Dorzhieva Ekaterina Matveevna
  • Litvinenko Vladimir Viktorovich
  • Minashina Inna Konstantinovna
  • Sytnik Kirill Igorevich
RU2816639C1
METHOD OF DETECTING TRAINING DATA FOR MACHINE LEARNING OF COMPUTER SYSTEM OF INDUSTRIAL INTERNET OF THINGS POWERED BY RECHARGEABLE BATTERY 2023
  • Grebeshkov Aleksandr Iurevich
  • Batyrshina Iana Aleksandrovna
RU2819568C1
METHOD OF DETECTING LEAKAGE OF FLUID MEDIUM IN TURBOMACHINE AND FLUID MEDIUM DISTRIBUTION SYSTEM 2015
  • Rodhain, Arnaud
  • Everwyn, Alexandre, Patrick, Jacques, Roger
RU2693147C2
SUPPORT APPARATUS, TRAINING APPARATUS AND SUPPORT SYSTEM FOR SETTING THE OPERATING CONDITIONS OF A UNIT 2018
  • Furuichi Kazuya
  • Oki Eisuke
  • Ikawa Shizuka
RU2773864C1
METHOD AND SYSTEM FOR DETERMINING THE REMAINING SERVICE LIFE OF A PROCESS DEVICE THROUGH WHICH A FLUID FLOWS 2018
  • Kroner Andreas
  • Pottmann Martin
  • Slaby Oliver
RU2773762C2
METHOD FOR TRAINING MACHINE LEARNING ALGORITHM FOR PREDICTING INTENT PARAMETER FOR OBJECT ON GROUND FOR USE IN UNMANNED VEHICLES 2021
  • Yangel Boris Konstantinovich
  • Stebelev Maksim Ilich
RU2810934C2

RU 2 759 815 C1

Authors

Ogiso, Ryoji

Kato, Michiyo

Hioki, Teruo

Dates

2021-11-18Published

2019-08-01Filed