CN115081340A - Micro pipe gallery gas monitoring method and system based on simulation and deep learning - Google Patents
Micro pipe gallery gas monitoring method and system based on simulation and deep learning Download PDFInfo
- Publication number
- CN115081340A CN115081340A CN202210870770.6A CN202210870770A CN115081340A CN 115081340 A CN115081340 A CN 115081340A CN 202210870770 A CN202210870770 A CN 202210870770A CN 115081340 A CN115081340 A CN 115081340A
- Authority
- CN
- China
- Prior art keywords
- pipe gallery
- gas
- micro pipe
- leakage
- micro
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 88
- 238000004088 simulation Methods 0.000 title claims abstract description 62
- 238000013135 deep learning Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000007789 gas Substances 0.000 claims abstract description 158
- 231100000331 toxic Toxicity 0.000 claims abstract description 46
- 230000002588 toxic effect Effects 0.000 claims abstract description 46
- 238000004364 calculation method Methods 0.000 claims abstract description 42
- 238000009792 diffusion process Methods 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims description 16
- RAHZWNYVWXNFOC-UHFFFAOYSA-N sulfur dioxide Inorganic materials O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 16
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 10
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 8
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 5
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 5
- 239000001569 carbon dioxide Substances 0.000 claims description 5
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 5
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 239000002341 toxic gas Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 230000007096 poisonous effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/005—Protection or supervision of installations of gas pipelines, e.g. alarm
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0063—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a threshold to release an alarm or displaying means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Combustion & Propulsion (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
A micro pipe gallery gas monitoring method and system based on simulation and deep learning belongs to the field of health monitoring, and a numerical simulation calculation model of toxic and harmful gas leakage-diffusion of a micro pipe gallery is established; carrying out simulation calculation on various leakage conditions, and obtaining a micro pipe gallery toxic and harmful gas leakage model library by using a simulation result as a training sample and a test sample for deep learning; according to the set time step length, acquiring gas content monitoring data inside the micro pipe gallery, inputting the data into a micro pipe gallery toxic and harmful gas leakage model library, and acquiring the position and the leakage amount of a leakage source; inputting the position and the leakage quantity of the leakage source into a numerical simulation calculation model for simulation calculation; the real-time distribution situation of the gas concentration inside the micro pipe gallery is displayed and alarmed, and the gas concentration distribution in the future appointed time inside the micro pipe gallery is predicted, displayed and early warned. The method can realize effective early warning of the leakage of toxic and harmful gases in the micro pipe gallery.
Description
Technical Field
The invention belongs to the technical field of health monitoring, and particularly relates to a micro pipe gallery gas monitoring method and system based on simulation and deep learning.
Background
For large-scale utility tunnel, miniature pipe gallery, cross sectional area is less (length 2.0~3.0m, wide 1.0~2.0 m), and inner space is limited, and the pipeline kind is many and distribute densely, and the staff passes in and out and overhauls the convenience slightly poor. And because the underground closed space is not ventilated and is moist, the possibility of generating volatile gas, flammable gas and toxic gas exists, and the life safety of workers can be endangered. In view of the above, the distribution state of the poisonous and harmful gases in the micro pipe gallery should be monitored. To the monitoring of miniature utility tunnel, chinese utility model patent CN210802549U discloses a monitoring system of miniature utility tunnel, include: the sensor module is used for collecting pipeline condition information in the micro comprehensive pipe rack, and the pipeline condition information at least comprises pipeline gas information, pipeline temperature and humidity information and pipeline water flow information; the transmission module is used for transmitting the pipeline condition information acquired by the sensor to the monitoring module; and the monitoring module is used for processing the pipeline condition information and presenting the pipeline condition information, and is also used for giving an alarm when monitoring that the pipeline condition information is abnormal.
At present, aiming at monitoring toxic and harmful gases in a micro pipe gallery, monitoring point data is directly processed usually by installing monitoring hardware equipment in the pipe gallery, for example, Chinese patent publication CN104880986A discloses a BIM-based comprehensive pipe gallery management system and method, wherein the system comprises a data acquisition module, an emergency processing module, an auxiliary management module, a daily maintenance module and an equipment management module; the method comprises the steps of collecting environmental state data of the comprehensive pipe gallery and medium state data in the pipe of the corridor by using a data collection module, generating an emergency treatment scheme by using an emergency treatment module when an emergency occurs, filing, managing and counting the operation data of the comprehensive pipe gallery by using an auxiliary management module, and performing daily maintenance by using a daily maintenance module and an equipment management module. Similar to the monitoring method, the existing monitoring method can only visually judge the concentration of toxic and harmful gas in the pipe gallery according to data obtained by measuring from a limited number of gas sensors, and cannot obtain the gas concentration at the position where no sensor is installed; and, can't predict the gas concentration in the piping lane according to existing measuring result to find out the position that probably has gas leakage in the piping lane, consequently, can't carry out real monitoring, prediction and early warning to the poisonous and harmful gas in the miniature piping lane.
Disclosure of Invention
The invention aims to provide a simulation and deep learning-based micro pipe gallery gas monitoring method and system, which can realize the crossing of engineering monitoring from data acquisition to data application, realize the crossing from post alarm to pre-alarm and realize the crossing from key point information to structural overall analysis by acquiring real-time monitoring data and based on-line simulation analysis and deep learning technologies.
The invention provides a micro pipe gallery gas monitoring method based on simulation and deep learning, which mainly comprises the following steps:
s01, establishing a toxic and harmful gas leakage-diffusion discrete model of the micro pipe gallery according to the physical characteristics of the micro pipe gallery;
s02, assuming the gas leakage conditions of various micro pipe galleries, and carrying out numerical simulation calculation according to the discrete model in the S01 to obtain the gas concentration distribution condition inside the micro pipe gallery; the simulation result is used as a training sample and a testing sample for deep learning to obtain a toxic and harmful gas leakage model library of the micro pipe gallery;
s03, acquiring monitoring data of the content of the gas to be detected in the micro pipe gallery according to the set time step length;
step S04, inputting the monitoring data in the step S03 into the toxic and harmful gas leakage model library in the step S02 to obtain the position and the leakage amount of a leakage source;
step S05, inputting the position and the leakage amount of the leakage source obtained in the step S04 into the numerical simulation calculation model in the step S01, and performing simulation calculation to obtain the real-time distribution condition of the gas concentration inside the micro pipe gallery and/or the gas concentration distribution condition inside the micro pipe gallery within the future designated time;
and S06, displaying and alarming the gas concentration distribution condition in the micro pipe gallery in real time, and/or displaying and early warning the gas concentration distribution in the micro pipe gallery in the future appointed time.
Further, in step S02, the gas leakage of the plurality of micro-tube lanes is assumed in the following manner: and carrying out meshing on the area containing the cable and the sump in the micro pipe gallery, wherein the size of each grid is 0.5m multiplied by 0.5m, and assuming different grids as leakage source positions of toxic and harmful gases and carrying out numerical simulation calculation.
Further, in step S03, the acquiring of the monitoring data of the content of the gas to be measured inside the micro pipe gallery includes:
(1) the method comprises the following steps that a gas sensor and a gas demodulator are arranged in a micro pipe gallery and used for collecting the content of gas to be detected in the micro pipe gallery in real time and converting collected information into monitoring data which can be identified by a monitoring system;
(2) transmitting the monitoring data to the monitoring system by adopting a data transmission system;
(3) and reading the monitoring data in the monitoring system according to the set time step.
Wherein, the type of gas sensor sets up according to the particular case of piping lane, including one or more in methane sensor, carbon monoxide sensor, oxygen sensor, carbon dioxide sensor, hydrogen sulfide sensor, sulfur dioxide sensor.
Further, in step S03, the time step is automatically adjusted according to whether there is an abnormality in the numerical simulation result.
Further, in step S06, the display mode of the result may be cloud image display and/or curve display; a global display and/or a partial magnified display.
The invention provides a micro pipe gallery gas monitoring system based on simulation and deep learning, which comprises a sensing system, a data transmission system and a monitoring system, wherein the sensing system is used for sensing the gas in a pipeline; wherein,
the sensing system is used for collecting the content of the gas to be detected in the micro pipe gallery in real time and converting the collected information into monitoring data which can be identified by the monitoring system;
the data transmission system is used for transmitting the monitoring data obtained by the perception system to the monitoring system;
the monitoring system comprises a network server end and an application end, wherein the network server end comprises an inversion and prediction module, and the application end comprises an alarm module and a display module;
the inversion and prediction module is used for obtaining a toxic and harmful gas leakage model base of the micro pipe gallery by utilizing a toxic and harmful gas leakage-diffusion numerical simulation calculation model and a deep learning algorithm of the micro pipe gallery; inputting the monitoring data of the sensing system into the micro pipe gallery toxic and harmful gas leakage model library according to the set time interval to obtain the position and the leakage amount of the toxic and harmful gas leakage source in the micro pipe gallery; the position and the leakage amount of the toxic and harmful gas leakage source obtained by the micro pipe gallery toxic and harmful gas leakage model library are used, the numerical simulation calculation model is used for carrying out real-time simulation calculation, display and alarm on the distribution situation of the concentration of the toxic and harmful gas in the micro pipe gallery, and/or carrying out prediction, display and early warning on the concentration distribution of the toxic and harmful gas in the micro pipe gallery within the future designated time, and the alarm and display information is output to the alarm module and the display module;
the alarm module is used for displaying alarm information;
the display module is used for displaying the calculation result.
Further, the perception system comprises a gas sensor and a gas demodulator.
Further, the inversion and prediction module calculates and predicts the gas concentration of the micro pipe gallery by executing corresponding steps in the micro pipe gallery gas monitoring method based on simulation and deep learning.
The method comprises the steps of obtaining a micro pipe gallery toxic and harmful gas leakage model library by using a numerical simulation calculation and deep learning method, using toxic and harmful gas monitoring data aiming at the micro pipe gallery as input data, obtaining the position and leakage amount of gas leakage by using the micro pipe gallery toxic and harmful gas leakage model library, carrying out online real-time simulation calculation to obtain the gas concentration distribution condition in the micro pipe gallery, and realizing gas leakage early warning according to the condition.
The system can monitor various combustible toxic gases such as hydrogen sulfide, gas, carbon monoxide, carbon dioxide, sulfur dioxide, oxygen and the like which are common in the micro pipe gallery in real time, judge whether a toxic and harmful gas leakage source exists or not according to the monitored gas concentration data, position a pollution source, obtain the real-time gas concentration distribution in the whole pipe gallery after positioning, and alarm the abnormal condition of the exceeding concentration; the gas concentration distribution at a certain time in the future can be further predicted, and the abnormal condition of the exceeding concentration can be pre-warned.
In addition, the simulation calculation of the invention can be carried out on line in real time, thus carrying out real-time early warning and alarming aiming at abnormal index parameters, finding problems as soon as possible and carrying out targeted and effective monitoring on the micro pipe gallery, thereby ensuring the safety and reliability of the operation of the micro pipe gallery and filling the gap of monitoring the toxic and harmful gases of the micro pipe gallery.
Drawings
For a more complete understanding of the present invention, reference is now made to the following descriptions taken in conjunction with the accompanying drawing, in which:
fig. 1 shows the specific steps of the simulation and deep learning-based micro pipe gallery gas monitoring method of the present invention.
Fig. 2 is a schematic diagram of a simulation and deep learning based micro pipe gallery gas monitoring system of the present invention.
Detailed Description
For the purpose of illustrating the invention, its technical details and its practical application to thereby enable one of ordinary skill in the art to understand and practice the invention, reference will now be made in detail to the embodiments of the present invention with reference to the accompanying drawings. It is to be understood that the embodiments described herein are merely illustrative and explanatory of the invention and are not restrictive thereof.
The invention provides a micro pipe gallery gas monitoring method based on simulation and deep learning, which mainly comprises the following steps:
step S01, establishing a toxic and harmful gas leakage-diffusion numerical simulation model of the micro pipe gallery:
the gas concentration equation does not consider the chemical reaction between the gases in the pipe gallery during the diffusion process, and is as follows:
wherein ρ i Is as followsiDensity of the seed gas, c i Is as followsiThe concentration of the seed gas is such that,
is as followsiVelocity of seed gas flow, D i Is the firstiDiffusion coefficient of seed gas, Q i Is the firstiThe source of leakage of the seed gas.
Since the air inside the micro pipe gallery is not basically circulated, it can be assumed that
Is 0, so the equation is simplified to
Step S02, assuming multiple leakage situations, performing numerical simulation calculation using the numerical simulation model in step S01, calculating the gas concentration distribution and other situations inside the micro pipe gallery, and using the simulation result as a training sample and a test sample for Deep Learning (Deep Learning), to obtain a toxic gas leakage model library for the micro pipe gallery, the specific method is as follows:
(1) because the area containing cables and water accumulation pits in the micro pipe gallery belongs to the area which is easy to generate toxic and harmful gas leakage, the area is mainly divided into grids, the size of each grid can be 0.5m multiplied by 0.5m, and the gas in each grid is assumed to meet the assumption of equation (2);
(2) any grid in the area is assumed to be a leakage source area of toxic and harmful gases, and the leakage quantity is assumed to be Q i (ii) a Will leak the quantity Q i Substituting the equation (2) into the data to perform numerical simulation calculation to obtain a set of simulation calculation results; according to the method, multiple groups of simulation calculation results are obtained by assuming multiple leakage conditions;
(3) and identifying the positions and leakage amounts of the gas leakage points according to the obtained multiple groups of simulation results through a Deep Learning algorithm (Deep Learning), so as to obtain a micro pipe gallery toxic and harmful gas leakage model library.
And S03, acquiring monitoring data of the content of the gas to be detected in the micro pipe gallery according to the set time step length.
In order to acquire monitoring data of the content of the gas to be detected in the micro pipe gallery, a gas sensor and a gas demodulator can be arranged in the micro pipe gallery and used for acquiring the content of the gas to be detected in the micro pipe gallery in real time and converting the acquired information into monitoring data which can be identified by a monitoring system; transmitting the monitoring data to the monitoring system by adopting a data transmission system; and reading the monitoring data according to the set time step.
Wherein, the type of gas sensor can set up according to the particular case of piping lane, for example, can include methane sensor, carbon monoxide sensor, oxygen sensor, carbon dioxide sensor, hydrogen sulfide sensor, sulfur dioxide sensor etc..
The data transmission can adopt a wired or wireless transmission mode commonly used in the field.
The time step can be automatically adjusted according to whether the numerical simulation result has abnormity.
And step S04, inputting the monitoring data in the step S03 into the micro pipe gallery toxic and harmful gas leakage model library in the step S02, and obtaining the position and the leakage amount of the toxic and harmful gas leakage source.
Step S05, inputting the position and amount of leakage source obtained in step S04 into the numerical simulation calculation model for leakage-diffusion of toxic and harmful gas in the micro pipe gallery stated in step S01, and performing simulation calculation with the monitoring data obtained in step S03 as boundary conditions, specifically including:
(1) inputting the position and the leakage amount of the leakage source obtained in the step S04 into the numerical simulation model in the step S01 to obtain the gas concentration distribution condition inside the micro pipe gallery at the current moment;
(2) inputting the position and the leakage amount of the leakage source obtained in the step S04 into the numerical simulation calculation model in the step S01, and obtaining the gas concentration distribution condition of the interior of the micro pipe rack at the future designated time through numerical simulation calculation according to the preset designated time, so as to realize the prediction of the gas concentration of the interior of the micro pipe rack at the future designated time.
Step S06, display and report to the police the inside gas concentration distribution situation of miniature piping lane, and/or display and the early warning the gas concentration distribution in the inside future appointed time of miniature piping lane, specifically include:
(1) outputting the calculation result of the gas concentration distribution condition in the micro pipe gallery at the current moment obtained in the step S05, displaying the calculation result, and alarming for dangerous conditions such as excessive gas concentration and the like according to the calculation result;
(2) and outputting the calculation result of the gas concentration distribution condition inside the micro pipe gallery at the specified time in the future, which is obtained in the step S05, displaying the result of the calculation result, and early warning dangerous conditions such as excessive gas concentration and the like according to the calculation result.
The display mode of the result can adopt: (1) the cloud picture shows that the gas concentration distribution condition on the whole pipe gallery can be displayed, and the gas concentration distribution condition on a certain section of the pipe gallery can also be displayed by locally amplifying; (2) the curve shows, can show the gas concentration change curve of piping lane optional position, including the monitoring point position to and the optional position beyond the monitoring point.
The invention provides a micro pipe gallery gas monitoring system based on simulation and deep learning, which is shown in figure 2 in the specification and comprises a sensing system 100, a data transmission system 200 and a monitoring system 300.
The sensing system 100 is used for collecting the content of gas to be detected in the micro pipe gallery in real time, and converting collected information into data which can be identified by the monitoring system 300. The sensing system 100 comprises a gas sensor 101 and a gas demodulator 102; the type of gas sensor 101 may be set according to the specifics of the pipe lane, and may include, for example, a methane sensor, a carbon monoxide sensor, an oxygen sensor, a carbon dioxide sensor, a hydrogen sulfide sensor, a sulfur dioxide sensor, and the like. The gas sensor 101 and the gas demodulator 102 are installed inside the pipe gallery, the gas sensor 101 is in communication connection with the gas demodulator 102, and the gas demodulator 102 converts information collected by the gas sensor 101 into monitoring data which can be identified by the monitoring system 300.
The data transmission system 200 is used for transmitting the identifiable monitoring data obtained by the sensing system 100 to the monitoring system 300. The data transmission of the data transmission system 200 may adopt a wireless or wired transmission mode commonly used in the art; the data transmission system 200 may include network cables, optical fibers, routers, and the like.
The monitoring system 300 comprises a network server side and an application side, wherein the network server side comprises an inversion and prediction module 301, and the application side comprises an alarm module 302 and a display module 303.
The inversion and prediction module 301 is configured to obtain a micro pipe gallery toxic and harmful gas leakage model library by using a toxic and harmful gas leakage-diffusion numerical simulation calculation and a deep learning algorithm of the micro pipe gallery; inputting the monitoring data of the sensing system into a micro pipe gallery toxic and harmful gas leakage model library according to a set time interval to obtain a leakage source and a leakage position of toxic and harmful gas; the numerical simulation calculation model is used for carrying out real-time simulation calculation, display and alarm on the gas concentration distribution condition in the micro pipe gallery by utilizing the leakage source and the leakage position of the toxic and harmful gas obtained by the micro pipe gallery toxic and harmful gas leakage model library, and/or carrying out prediction, display and early warning on the gas concentration distribution in the micro pipe gallery within the future designated time, and the alarm and display information is output to the alarm module 302 and the display module 303; the alarm module 302 is used for displaying alarm information; the display module 303 is configured to display the calculation result in a display manner such as a cloud image or a curve.
The inversion and prediction module 301 calculates and predicts the gas concentration of the micro pipe gallery by executing the corresponding steps of the simulation and deep learning-based gas monitoring method for the micro pipe gallery.
Claims (9)
1. A micro pipe gallery gas monitoring method based on simulation and deep learning mainly comprises the following steps:
s01, establishing a toxic and harmful gas leakage-diffusion numerical simulation calculation model of the micro pipe gallery according to the physical characteristics of the micro pipe gallery;
s02, assuming the gas leakage conditions of various micro pipe galleries, and carrying out simulation calculation according to the numerical simulation calculation model in the S01 to obtain the gas concentration distribution condition inside the micro pipe gallery; the simulation result is used as a training sample and a testing sample for deep learning to obtain a micro pipe gallery toxic and harmful gas leakage model library;
s03, acquiring monitoring data of the content of the gas to be detected in the micro pipe gallery according to the set time step length;
step S04, inputting the monitoring data in the step S03 into the toxic and harmful gas leakage model library in the step S02, and obtaining the position and the leakage amount of the toxic and harmful gas leakage source;
step S05, inputting the position and the leakage amount of the leakage source obtained in the step S04 into the numerical simulation model in the step S01, and performing simulation calculation by using the monitoring data obtained in the step S03 as boundary conditions to obtain the real-time distribution condition of the gas concentration in the micro pipe gallery and/or the gas concentration distribution condition in the micro pipe gallery in the designated time in the future;
and S06, displaying and alarming the gas concentration distribution condition in the micro pipe gallery in real time, and/or displaying and early warning the gas concentration distribution in the micro pipe gallery in the future appointed time.
2. The method of claim 1, wherein in step S02, the gas leakage of the plurality of micro tube lanes is assumed by: carrying out grid division on a region containing cables and a sump in the micro pipe gallery, wherein the size of each grid is 0.5m multiplied by 0.5m, and assuming different grids as leakage source positions of toxic and harmful gases and giving leakage amount; for each leakage case, a numerical simulation calculation was performed.
3. The method of claim 1, wherein the step S03 of obtaining the monitoring data of the gas content to be measured inside the micro pipe gallery comprises:
the method comprises the following steps that a gas sensor and a gas demodulator are arranged in a micro pipe gallery and used for collecting the content of gas to be detected in the micro pipe gallery in real time and converting collected information into monitoring data which can be identified by a monitoring system;
transmitting the monitoring data to the monitoring system by adopting a data transmission system;
and reading the monitoring data in the monitoring system according to the set time step.
4. The method of claim 3, wherein the gas sensor is of a type that is configured according to the specifications of the pipe rack, and comprises one or more of a methane sensor, a carbon monoxide sensor, an oxygen sensor, a carbon dioxide sensor, a hydrogen sulfide sensor, and a sulfur dioxide sensor.
5. The method according to claim 1, wherein in step S03, the time step is automatically adjusted according to whether there is an abnormality in the simulation result.
6. The method according to claim 1, wherein in step S06, the result is displayed in a cloud and/or curve manner; a global display and/or a partial magnified display.
7. A micro pipe gallery gas monitoring system based on simulation and deep learning comprises a sensing system, a data transmission system and a monitoring system; wherein,
the sensing system is used for collecting the content of the gas to be detected in the micro pipe gallery in real time and converting the collected information into monitoring data which can be identified by the monitoring system;
the data transmission system is used for transmitting the monitoring data obtained by the perception system to the monitoring system;
the monitoring system comprises a network server end and an application end, wherein the network server end comprises an inversion and prediction module, and the application end comprises an alarm module and a display module;
the inversion and prediction module is used for obtaining a micro pipe gallery toxic and harmful gas leakage model base by utilizing a toxic and harmful gas leakage-diffusion numerical simulation calculation model and a deep learning algorithm of the micro pipe gallery; inputting the monitoring data obtained by the monitoring system into the micro pipe gallery toxic and harmful gas leakage model library according to the set time interval to obtain the position and the leakage amount of the toxic and harmful gas in the micro pipe gallery; the position and the leakage amount of the leakage source obtained from the micro pipe gallery toxic and harmful gas leakage model library are used, the numerical calculation simulation model is adopted to perform real-time simulation calculation, display and alarm on the gas concentration distribution condition in the micro pipe gallery, and/or predict, display and early-warn the gas concentration distribution in the micro pipe gallery within the future designated time, and the alarm and display information is output to the alarm module and the display module;
the alarm module is used for displaying alarm information;
the display module is used for displaying the calculation result.
8. The system of claim 7, wherein the sensing system comprises a gas sensor and a gas demodulator.
9. The system of claim 7, wherein the inversion and prediction module calculates and predicts the micro-pipe gallery gas concentration by performing the corresponding steps of the simulation and deep learning based micro-pipe gallery gas monitoring method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210870770.6A CN115081340B (en) | 2022-07-23 | 2022-07-23 | Micro pipe gallery gas monitoring method and system based on simulation and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210870770.6A CN115081340B (en) | 2022-07-23 | 2022-07-23 | Micro pipe gallery gas monitoring method and system based on simulation and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115081340A true CN115081340A (en) | 2022-09-20 |
| CN115081340B CN115081340B (en) | 2022-10-25 |
Family
ID=83242026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210870770.6A Active CN115081340B (en) | 2022-07-23 | 2022-07-23 | Micro pipe gallery gas monitoring method and system based on simulation and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115081340B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117763934A (en) * | 2023-06-21 | 2024-03-26 | 吉林建筑大学 | Micro pipe gallery gas monitoring method and system based on deep learning |
| CN118517643A (en) * | 2024-07-25 | 2024-08-20 | 海纳云物联科技有限公司 | Method and apparatus for gas leak location, and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170026722A1 (en) * | 2015-07-23 | 2017-01-26 | Palo Alto Research Center Incorporated | Sensor network system |
| CN108038275A (en) * | 2017-11-28 | 2018-05-15 | 哈尔滨理工大学 | A kind of numerical simulation of gas pipeline leakage sound field and characteristic analysis method |
| CN109408686A (en) * | 2018-10-19 | 2019-03-01 | 中建二局安装工程有限公司 | A kind of underground pipe gallery big data visualization system and method |
| CN111141326A (en) * | 2019-12-11 | 2020-05-12 | 四川铁创科技有限公司 | Miniature utility tunnel health monitoring system based on coupling analysis of multiple physical fields |
| CN210802549U (en) * | 2019-10-18 | 2020-06-19 | 北京云庐科技有限公司 | Monitoring system of miniature comprehensive pipe gallery |
| CN111612018A (en) * | 2020-04-24 | 2020-09-01 | 国网河北省电力有限公司雄安新区供电公司 | Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion |
| CN112446543A (en) * | 2020-12-01 | 2021-03-05 | 河南汇祥通信设备有限公司 | Urban underground comprehensive pipe gallery risk management and control system and method based on neural network |
| KR102344583B1 (en) * | 2021-07-20 | 2021-12-30 | (주)동명엔터프라이즈 | Leak monitoring system for the section of the underground facility for public utilities for transporting hazardous substances |
-
2022
- 2022-07-23 CN CN202210870770.6A patent/CN115081340B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170026722A1 (en) * | 2015-07-23 | 2017-01-26 | Palo Alto Research Center Incorporated | Sensor network system |
| CN108038275A (en) * | 2017-11-28 | 2018-05-15 | 哈尔滨理工大学 | A kind of numerical simulation of gas pipeline leakage sound field and characteristic analysis method |
| CN109408686A (en) * | 2018-10-19 | 2019-03-01 | 中建二局安装工程有限公司 | A kind of underground pipe gallery big data visualization system and method |
| CN210802549U (en) * | 2019-10-18 | 2020-06-19 | 北京云庐科技有限公司 | Monitoring system of miniature comprehensive pipe gallery |
| CN111141326A (en) * | 2019-12-11 | 2020-05-12 | 四川铁创科技有限公司 | Miniature utility tunnel health monitoring system based on coupling analysis of multiple physical fields |
| CN111612018A (en) * | 2020-04-24 | 2020-09-01 | 国网河北省电力有限公司雄安新区供电公司 | Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion |
| CN112446543A (en) * | 2020-12-01 | 2021-03-05 | 河南汇祥通信设备有限公司 | Urban underground comprehensive pipe gallery risk management and control system and method based on neural network |
| KR102344583B1 (en) * | 2021-07-20 | 2021-12-30 | (주)동명엔터프라이즈 | Leak monitoring system for the section of the underground facility for public utilities for transporting hazardous substances |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117763934A (en) * | 2023-06-21 | 2024-03-26 | 吉林建筑大学 | Micro pipe gallery gas monitoring method and system based on deep learning |
| CN118517643A (en) * | 2024-07-25 | 2024-08-20 | 海纳云物联科技有限公司 | Method and apparatus for gas leak location, and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115081340B (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115081340B (en) | Micro pipe gallery gas monitoring method and system based on simulation and deep learning | |
| WO2016129715A1 (en) | Air quality prediction and management system for early detection of environmental disasters | |
| CN110926439B (en) | Operation tunnel structure health monitoring system based on BIM technology | |
| JP6989654B2 (en) | Environmental monitoring equipment, environmental monitoring system, environmental monitoring program, and environmental monitoring recording medium | |
| CN206627815U (en) | A kind of offshore wind power foundation structure remote monitoring system | |
| CN108039016A (en) | A kind of subway underground operation space safety monitoring and early warning system | |
| CN116543531B (en) | Data center system for centralized management and displaying underground monitoring and control data | |
| CN117078072A (en) | Multi-dimensional environment data supervision method and supervision system | |
| CN115393142A (en) | Intelligent park management method and management platform | |
| CN111486345B (en) | Grain depot underground pipe network liquid leakage on-line monitoring and early warning method and device | |
| CN110751420A (en) | Intelligent virtual inspection method and system for urban comprehensive pipe gallery | |
| CN117405177A (en) | Cable tunnel harmful gas leakage early warning method, system, equipment and medium | |
| CN117763934A (en) | Micro pipe gallery gas monitoring method and system based on deep learning | |
| CN112177661B (en) | Accurate monitoring and abnormity early warning system and method for local ventilation parameters of coal mine | |
| CN116105802A (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| KR20110125047A (en) | Method for analyzing sensor data of variety facilities using rule-engine | |
| CN103487365A (en) | Real-time evaluation system and method for influences of corrosive gas on equipment in data center | |
| CN111141326A (en) | Miniature utility tunnel health monitoring system based on coupling analysis of multiple physical fields | |
| CN115437304A (en) | Remote fault diagnosis system and method for flue gas emission system | |
| CN113743015B (en) | Fire scene data acquisition method, medium and electronic equipment | |
| CN111103414A (en) | Intelligent river channel supervision system | |
| CN114239215A (en) | Intelligent pipeline on-line monitoring system | |
| CN117574301B (en) | Portable intelligent environment detection equipment data analysis system based on multiple sensors | |
| CN210802549U (en) | Monitoring system of miniature comprehensive pipe gallery | |
| CN213580659U (en) | Intelligent poison gas detection system based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |