CN111828845A - Automatic pipeline leakage detection method based on artificial intelligence - Google Patents
Automatic pipeline leakage detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN111828845A CN111828845A CN202010715658.6A CN202010715658A CN111828845A CN 111828845 A CN111828845 A CN 111828845A CN 202010715658 A CN202010715658 A CN 202010715658A CN 111828845 A CN111828845 A CN 111828845A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- leakage
- pressure value
- data
- value
- 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.)
- Pending
Links
Images
Classifications
-
- 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
Abstract
The invention discloses an artificial intelligence based automatic pipeline leakage detection method which comprises the steps of obtaining historical initial data collected by a pipeline sensor, marking the historical initial data, collecting initial measurement data of a pressure pump, a safety valve and a liquid filling pipe, calculating the current pressure value of a pipeline according to the initial measurement data and the historical initial data, calculating the final pressure value of the pipeline, fitting the periodic motion of the pressure pump, calculating the real pressure value of the pipeline, outputting a data track tracking expected value by adopting an artificial intelligence model, and judging whether the pipeline leaks or not. The invention utilizes the existing sensor in the pipeline system to detect the leakage, does not need to purchase redundant expensive professional equipment, combines an artificial intelligence model, and utilizes the simulation result training detector to detect whether the leakage occurs, thereby greatly reducing a large amount of manpower and capital cost spent on the leakage detection and having strong operability.
Description
Technical Field
The invention relates to the technical field of pipeline leakage detection, in particular to an automatic pipeline leakage detection method based on artificial intelligence.
Background
With the increasing popularity of the internet, artificial intelligence is widely applied to various fields as a product of the internet. For example, when the security inspection is carried out at an airport or a railway station, the prediction and the capture of some dangerous actions can be carried out by utilizing artificial intelligence in combination with a camera and the like, so that an alarm is triggered, and measures are taken in time. For example, the leakage detection can be performed on pipelines such as underground natural gas installed by people by combining artificial intelligence with the existing equipment, and measures can be taken in time to stop loss. Artificial intelligence is being used more and more widely in the present society, and not only can be well utilized in the fields of security inspection, industry, network information security, hacking and the like, but also plays a very important role in promoting the development of the scientific and technological society.
Traditional leak detection has focused primarily on the detection of power transmission lines, but as we develop it has been found that the detection of leaks should not be done solely for saltfish power transmission. In fact, devices containing gas or liquid, such as a water supply circuit or a natural gas transmission pipeline, a carbon dioxide transmission line, and the like, should be subjected to key leak detection. Moreover, the traditional leak detection method mainly depends on human or special equipment, the problem is not very obvious when large-scale leakage is detected, but when small leakage is detected, the traditional detection method consumes manpower resources and funds.
The existing method for detecting the leakage of the pipeline device containing liquid or gas and the like mainly comprises the steps of purchasing professional detection equipment through manual detection in combination with professional sensor equipment arranged beside a pipeline in a special pipeline lead form to analyze sound signals related to the leakage so as to judge whether the leakage occurs or not; and some installation models based on analytical equations describing the installation behaviors are constructed for detection.
The existing leak detection technology has the problems that expensive capital is needed to buy professional equipment, an experiential inspector needs to operate the professional equipment, data reading and inputting are deeply known, the professional equipment needs to be modified according to different scenes, and installation after modification is difficult. In addition, a large number of sensors are needed to be purchased, which is very costly, and the implementation is also very tedious, which is not beneficial to the operation.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an automatic pipeline leakage detection method based on artificial intelligence.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
an automatic pipeline leakage detection method based on artificial intelligence comprises the following steps:
s1, acquiring historical initial data acquired by the pipeline sensor;
s2, marking each measured value in the historical initial data;
s3, acquiring initial measurement data of the pressure pump, the safety valve and the liquid filling pipe;
s4, calculating the current pressure value of the pipeline according to the initial measurement data collected in the step S3 and the historical initial data collected in the step S1;
s5, comparing the current pressure value of the pipeline calculated in the step S4 with the initial pressure value collected in the step S1, and calculating the final pressure value of the pipeline according to the operation torque of the pressure pump;
s6, performing data fitting on the plurality of pipeline final pressure values with different timestamps calculated in the step S5 to obtain the periodic motion of the pressurizing pump;
s7, calculating the real pressure value of the pipeline according to the periodic motion of the pressure pump obtained in the step S6;
s8, performing iterative training on the historical non-leakage and leakage data sets of the pipeline by adopting an artificial intelligence model, and outputting a data track tracking expected value according to the real pressure value of the pipeline calculated in the step S7;
and S9, comparing the expected tracking value of the data track obtained in the step S8 with the non-leakage data, and judging whether the pipeline leaks.
Further, the step S1 is preceded by detecting the operation states of the pressurizing pump and the safety valve device, and checking the detected temperature of the abnormal change of the current and the piping.
Further, the historical initial data collected in step S1 specifically includes: dielectric fluid pressure value, pipeline surface temperature, soil temperature, the gas pressure value in the surge tank, the timestamp of measuring the sample, current value.
Further, the calculation formula of the current pressure value of the pipeline in the step S4 is as follows:
Ptn＝f(xn,xn-1,...,xn-N)*Tn
wherein the content of the first and second substances,
is an instant time tnF is the transfer function of the pipeline pressure, N is the measurement sample number value, TnIs the ratio of the long term temperature difference to the short term temperature difference between the pipeline and the ambient temperature.
Further, the calculation formula of the final pressure value of the pipeline in the step S5 is as follows:
Pn＝Ptn+(Psva-Peva)+(Pspum-Pepum)
wherein, PnTo the final pressure value of the pipeline, PsvaInitial pressure value, P, measured by the sensor for the safety valve at installationevaPressure value, P, of safety valve measured by sensor after leakage of pipelinespumInitial pressure value, P, measured by a sensor at the time of installation of the pressure pumpepumThe pressure value of the booster pump measured by the sensor after the pipeline leaks.
Further, the calculation formula of the real pressure value of the pipeline in the step S7 is as follows:
Pture＝Pn-Ppum+Cpea
wherein, PtureAs the true pressure value of the pipeline, PpumInfluencing the pressure value of the operating cycle of the pressure pump measured for the sensor, CpeaThe resulting pressure change values before and after the instant time are measured for the sensor.
Further, the step S9 specifically includes:
judging whether the difference value between the expected tracking value of the data track obtained in the step S8 and the data which are not leaked is larger than a set threshold value or not; if yes, the pipeline is leaked; otherwise, it indicates that no leakage occurs in the pipeline.
Further, after the step S9 determines that the pipeline has a leak, the leak coefficient of the sample in the training data set used by the artificial intelligence model is calculated.
Further, the leakage coefficient is calculated by dividing the expected tracking value of the data output in step S8 by the non-leakage data of the pipeline history.
Further, the step S9 is followed by: comparing the historical non-leakage and leakage data sets of the pipeline with the leakage rate data set of the pipeline, and calculating the current leakage rate of the pipeline; and then outputting a leakage rate value and carrying out early warning.
The invention has the following beneficial effects:
(1) the invention utilizes the existing sensor in the pipeline system to carry out leakage detection, does not need to purchase redundant expensive professional equipment, greatly reduces a large amount of manpower and capital cost spent on leakage detection, and has strong operability;
(2) the invention combines an artificial intelligence model and utilizes a simulation result training detector to detect whether leakage occurs; meanwhile, the detector only needs to learn the most basic related detection knowledge to identify whether leakage occurs through a small amount of available sensor data in installation, and the expense of engaging a professional detector is greatly reduced.
Drawings
FIG. 1 is a flow chart of the method for automatic leak detection of a pipeline based on artificial intelligence.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
The embodiment of the invention provides an artificial intelligence-based automatic pipeline leak detection method, which comprises the following steps of S1-S9:
s1, acquiring historical initial data acquired by the pipeline sensor;
in this embodiment, in the process of performing installation test on a pipeline system, the operation conditions of equipment such as a booster pump and a safety valve need to be detected first, so that the influence on the later detection value caused by abnormal operation of the equipment when data marking is performed later is avoided.
The detected temperature of the abnormal changes in current and piping, etc., are then checked, as this information may change the confidence level of the determined leakage when later passed to the leakage decision module.
And finally, when the equipment, the temperature and other data are confirmed to be normal, acquiring historical initial data by using a pipeline sensor. Specifically, the collected historical initial data specifically includes: the method comprises the following steps of (1) measuring initial data such as a dielectric fluid pressure value, the temperature of the outer surface of a pipeline read by a sensor, the soil temperature, the gas pressure value in a balance tank, a time stamp of a measured sample, a current value and the like; and the measurement data for all sensors is set to be collected once per minute.
S2, marking each measured value in the historical initial data;
in this embodiment, after the historical initial data is collected in step S1, each initial measurement value in the historical initial data is labeled, and each initial measurement value is set to a unique label, for example, the dielectric fluid pressure value is 1.
S3, acquiring initial measurement data of the pressure pump, the safety valve and the liquid filling pipe;
in the embodiment, the initial data measuring system is formed by three components of the pressurizing pump, the safety valve and the liquid charging pipe, and the initial data of the pressurizing pump, the safety valve and the liquid charging pipe are measured.
S4, calculating the current pressure value of the pipeline according to the initial measurement data collected in the step S3 and the historical initial data collected in the step S1;
in this embodiment, the present invention calculates the instantaneous time t from the initial measurement data collected in step S3 in combination with the temperature and current values of the outer surface of the pipe collected in step S1nThe current pressure value of the pipeline is calculated according to the formula:
Ptn＝f(xn,xn-1,...,xn-N)*Tn
wherein the content of the first and second substances,
is an instant time tnF is the transfer function of the pipeline pressure, N is the measurement sample number value, TnIs the ratio of the long term temperature difference to the short term temperature difference between the pipeline and the ambient temperature.
In order to improve the calculation effect of the pipeline pressure value, the method selects several different transfer functions to calculate the pressure value, and takes the optimal value as the final measurement value of the pipeline model.
S5, comparing the current pressure value of the pipeline calculated in the step S4 with the initial pressure value collected in the step S1, and calculating the final pressure value of the pipeline according to the operation torque of the pressure pump;
in this embodiment, the present invention respectively calculates a plurality of final pressure values of the pipeline at different timestamps, and the calculation formula is expressed as:
Pn＝Ptn+(Psva-Peva)+(Pspum-Pepum)
wherein, PnTo the final pressure value of the pipeline, PsvaInitial pressure value, P, measured by the sensor for the safety valve at installationevaPressure value, P, of safety valve measured by sensor after leakage of pipelinespumInitial pressure value, P, measured by a sensor at the time of installation of the pressure pumpepumThe pressure value of the booster pump measured by the sensor after the pipeline leaks.
S6, performing data fitting on the plurality of pipeline final pressure values with different timestamps calculated in the step S5 to obtain the periodic motion of the pressurizing pump;
in this embodiment, after obtaining the final pressure values of the pipelines with different timestamps calculated in step S5, the present invention combines the final pressure values of the pipelines with data fitting and mathematical law derivation by using a leakage simulator, so as to obtain the periodic behavior of the pressure pump.
S7, calculating the real pressure value of the pipeline according to the periodic motion of the pressure pump obtained in the step S6;
in this embodiment, according to the periodic motion of the pressurizing pump obtained in step S6, the influence of the pressure value measurement result influenced by the operation period of the pressurizing pump measured by the sensor is subtracted, so as to calculate a plurality of new real pressure values of the pipeline as the final output result of the leakage simulator. The calculation formula of the real pressure value of the pipeline is as follows:
Pture＝Pn-Ppum+Cpea
wherein, PtureAs the true pressure value of the pipeline, PpumInfluencing the pressure value of the operating cycle of the pressure pump measured for the sensor, CpeaThe resulting pressure change values before and after the instant time are measured for the sensor.
S8, performing iterative training on the historical non-leakage and leakage data sets of the pipeline by adopting an artificial intelligence model, and outputting a data track tracking expected value according to the real pressure value of the pipeline calculated in the step S7;
in this embodiment, after a plurality of new pipeline real pressure values are obtained through calculation, the plurality of pipeline real pressure values are input to the decision module for processing.
The decision module adopts an artificial intelligence model to carry out iterative training on the historical unleaky and leaky data sets of the pipeline, and specifically adopts a Bayesian algorithm to carry out iterative learning for a plurality of times by combining the historical unleaky and leaky data sets of the pipeline, so as to execute a data tracking task. The invention executes the system data track tracking in the limited time interval, and corrects the control input by using the error information measured in the previous operation or previous operations, so that the repeated task can be better performed in the next operation process. This is repeated until the desired value of the data trace is output over the entire time interval, which may be current or pressure, etc.
And S9, comparing the expected tracking value of the data track obtained in the step S8 with the non-leakage data, and judging whether the pipeline leaks.
In this embodiment, the present invention performs a comparison operation according to the expected tracking value of the data track obtained in step S8 and the non-leakage data, and determines whether a pipeline leaks according to a difference between the expected tracking value of the data track and the non-leakage data.
Specifically, the method judges whether the difference value between the expected data track tracking value and the non-leakage data is larger than a set threshold value; if so, the pipeline is indicated to be leaked, otherwise, the pipeline is indicated to be not leaked.
After the judgment result is obtained, a Boolean value is output to a user to represent whether leakage exists or not, if the Boolean value is false, leakage does not exist, and if the Boolean value is true, leakage occurs.
According to the method, after the pipeline is determined to be leaked, the leakage coefficient of the sample in the training data set adopted by the artificial intelligence model is calculated. The leakage coefficient is calculated by dividing the expected tracking data output in step S8 by the non-leakage data in the pipeline history, and the calculated value may be current or pressure.
Comparing the historical non-leakage and leakage data sets of the pipeline with the leakage rate data set of the pipeline, and calculating the current leakage rate of the pipeline; and then outputting the leakage rate value to a screen of a user, and carrying out early warning to remind the user to process the leakage as soon as possible.
The invention combines artificial intelligence, does not need to purchase redundant expensive professional equipment, utilizes the sensor existing during installation to detect leakage, and has strong system operability. During detection, the new element for detection is a Bayesian network numerical value specification calculation module realized on the basis of software simulation leakage. And then training the detector by using the simulation result to detect whether leakage occurs. Meanwhile, an inspector only needs to learn the most basic related inspection knowledge to identify whether leakage occurs through a small amount of sensor data available in installation.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (10)
1. An automatic pipeline leakage detection method based on artificial intelligence is characterized by comprising the following steps:
s1, acquiring historical initial data acquired by the pipeline sensor;
s2, marking each measured value in the historical initial data;
s3, acquiring initial measurement data of the pressure pump, the safety valve and the liquid filling pipe;
s4, calculating the current pressure value of the pipeline according to the initial measurement data collected in the step S3 and the historical initial data collected in the step S1;
s5, comparing the current pressure value of the pipeline calculated in the step S4 with the initial pressure value collected in the step S1, and calculating the final pressure value of the pipeline according to the operation torque of the pressure pump;
s6, performing data fitting on the plurality of pipeline final pressure values with different timestamps calculated in the step S5 to obtain the periodic motion of the pressurizing pump;
s7, calculating the real pressure value of the pipeline according to the periodic motion of the pressure pump obtained in the step S6;
s8, performing iterative training on the historical non-leakage and leakage data sets of the pipeline by adopting an artificial intelligence model, and outputting a data track tracking expected value according to the real pressure value of the pipeline calculated in the step S7;
and S9, comparing the expected tracking value of the data track obtained in the step S8 with the non-leakage data, and judging whether the pipeline leaks.
2. The method for automatic leak detection of pipes based on artificial intelligence of claim 1, wherein said step S1 is preceded by detecting the operation status of pressurizing pump and safety valve devices and checking the detected temperature of the current and abnormal change of the pipe.
3. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 1 or 2, wherein the historical initial data collected in the step S1 specifically includes: dielectric fluid pressure value, pipeline surface temperature, soil temperature, the gas pressure value in the surge tank, the timestamp of measuring the sample, current value.
4. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 3, wherein the calculation formula of the current pressure value of the pipeline in the step S4 is as follows:
wherein the content of the first and second substances,
is an instant time tnF is the transfer function of the pipeline pressure, N is the measurement sample number value, TnIs the ratio of the long term temperature difference to the short term temperature difference between the pipeline and the ambient temperature.
5. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 4, wherein the final pressure value of the pipeline in the step S5 is calculated by the formula:
Pn＝Ptn+(Psva-Peva)+(Pspum-Pepum)
wherein, PnTo the final pressure value of the pipeline, PsvaInitial pressure value, P, measured by the sensor for the safety valve at installationevaPressure value, P, of safety valve measured by sensor after leakage of pipelinespumIs the initial pressure value measured by the sensor when the booster pump is installed,Pepumthe pressure value of the booster pump measured by the sensor after the pipeline leaks.
6. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 5, wherein the calculation formula of the real pressure value of the pipeline in the step S7 is as follows:
Pture＝Pn-Ppum+Cpea
wherein, PtureAs the true pressure value of the pipeline, PpumInfluencing the pressure value of the operating cycle of the pressure pump measured for the sensor, CpeaThe resulting pressure change values before and after the instant time are measured for the sensor.
7. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 6, wherein the step S9 specifically includes:
judging whether the difference value between the expected tracking value of the data track obtained in the step S8 and the data which are not leaked is larger than a set threshold value or not; if yes, the pipeline is leaked; otherwise, it indicates that no leakage occurs in the pipeline.
8. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 7, wherein the step S9 is implemented by calculating the leakage coefficient of the sample in the training data set used by the artificial intelligence model after determining that the pipeline has the leakage.
9. The method for automatic leak detection of pipelines based on artificial intelligence as claimed in claim 8, wherein said leakage coefficient is calculated by dividing the expected tracking value of the data trace output in step S8 by the historical non-leakage data of the pipeline.
10. The method for automatically detecting the leakage of the pipeline based on the artificial intelligence as claimed in claim 8, further comprising after the step S9: comparing the historical non-leakage and leakage data sets of the pipeline with the leakage rate data set of the pipeline, and calculating the current leakage rate of the pipeline; and then outputting a leakage rate value and carrying out early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010715658.6A CN111828845A (en) | 2020-07-23 | 2020-07-23 | Automatic pipeline leakage detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010715658.6A CN111828845A (en) | 2020-07-23 | 2020-07-23 | Automatic pipeline leakage detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111828845A true CN111828845A (en) | 2020-10-27 |
Family
ID=72925142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010715658.6A Pending CN111828845A (en) | 2020-07-23 | 2020-07-23 | Automatic pipeline leakage detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111828845A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113531403A (en) * | 2021-08-26 | 2021-10-22 | 三门核电有限公司 | Water pipe leakage detection method and device |
| US11953161B1 (en) | 2023-04-18 | 2024-04-09 | Intelcon System C.A. | Monitoring and detecting pipeline leaks and spills |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4280356A (en) * | 1979-07-13 | 1981-07-28 | Shell Oil Company | Pipeline leak detection |
| JPH0763637A (en) * | 1993-08-27 | 1995-03-10 | Nkk Corp | Method for detecting leak of pipe line |
| CN104061445A (en) * | 2014-07-09 | 2014-09-24 | 中国石油大学(华东) | Pipeline leakage detection method based on neural network |
| CN104180166A (en) * | 2014-07-09 | 2014-12-03 | 中国石油大学(华东) | Pipeline leakage detection method based on pipeline pressure data |
| CN108730776A (en) * | 2018-06-22 | 2018-11-02 | 大连理工大学 | A kind of Oil Pipeline Leakage Detection based on the fusion of extreme learning machine information |
| CN110263416A (en) * | 2019-06-17 | 2019-09-20 | 北京讯腾智慧科技股份有限公司 | A kind of gas ductwork leakage detection method and device based on emulation technology |
| CN110375207A (en) * | 2019-07-09 | 2019-10-25 | 安徽理工大学 | A kind of buried fuel gas pipeline leakage artificial intelligence detection system |
-
2020
- 2020-07-23 CN CN202010715658.6A patent/CN111828845A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4280356A (en) * | 1979-07-13 | 1981-07-28 | Shell Oil Company | Pipeline leak detection |
| JPH0763637A (en) * | 1993-08-27 | 1995-03-10 | Nkk Corp | Method for detecting leak of pipe line |
| CN104061445A (en) * | 2014-07-09 | 2014-09-24 | 中国石油大学(华东) | Pipeline leakage detection method based on neural network |
| CN104180166A (en) * | 2014-07-09 | 2014-12-03 | 中国石油大学(华东) | Pipeline leakage detection method based on pipeline pressure data |
| CN108730776A (en) * | 2018-06-22 | 2018-11-02 | 大连理工大学 | A kind of Oil Pipeline Leakage Detection based on the fusion of extreme learning machine information |
| CN110263416A (en) * | 2019-06-17 | 2019-09-20 | 北京讯腾智慧科技股份有限公司 | A kind of gas ductwork leakage detection method and device based on emulation technology |
| CN110375207A (en) * | 2019-07-09 | 2019-10-25 | 安徽理工大学 | A kind of buried fuel gas pipeline leakage artificial intelligence detection system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113531403A (en) * | 2021-08-26 | 2021-10-22 | 三门核电有限公司 | Water pipe leakage detection method and device |
| US11953161B1 (en) | 2023-04-18 | 2024-04-09 | Intelcon System C.A. | Monitoring and detecting pipeline leaks and spills |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Burst detection in district metering areas using deep learning method | |
| Romano et al. | Automated detection of pipe bursts and other events in water distribution systems | |
| Song et al. | Gas leak detection in galvanised steel pipe with internal flow noise using convolutional neural network | |
| CN103968256B (en) | Piping for tank farm leakage detection method | |
| CN111828845A (en) | Automatic pipeline leakage detection method based on artificial intelligence | |
| EP0545450B1 (en) | Statistically detecting leakage of fluid from a conduit | |
| CN113446519B (en) | Method, electronic device and storage medium for determining leakage degree of pipe network | |
| CN112284619B (en) | Oil leakage real-time monitoring device and detection method | |
| CN111365623B (en) | Negative pressure wave inflection point identification method based on linear fitting | |
| CN103678938B (en) | A kind of degradation model consistency check method of space-oriented shape and range of error | |
| Li et al. | Fast detection and localization of multiple leaks in water distribution network jointly driven by simulation and machine learning | |
| Gupta et al. | Leak detection in low-pressure gas distribution networks by probabilistic methods | |
| Romano et al. | Burst detection and location in water distribution systems | |
| Junior et al. | ARX modeling approach to leak detection and diagnosis | |
| CN111157193B (en) | Nuclear power station sealing test method, sealing test device and electronic equipment | |
| Torres et al. | Minimal-order observers for locating leaks in a pipeline with a branch | |
| CN117309067A (en) | Water resource real-time monitoring method, system and electronic equipment | |
| Ostapkowicz et al. | Leak detection in liquid transmission pipelines during transient state related to a change of operating point | |
| JP2765446B2 (en) | Pipeline leak detection method | |
| Tylman et al. | Fully automatic AI-based leak detection system | |
| Ye et al. | Study of burst alarming and data sampling frequency in water distribution networks | |
| US20220196512A1 (en) | Detection of a leakage in a supply grid | |
| EP2956751B1 (en) | Method and monitoring device for monitoring a structure | |
| CN112115654B (en) | Pipeline flow field pressure distribution evaluation method and device integrating measured data | |
| Park et al. | Development of computational algorithms for daily water leak detection in district metered areas based on the principal component analysis |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tang Dan Inventor after: He Rui Inventor after: Wang Yaqiang Inventor after: Zeng Qiong Inventor after: Geng Wei Inventor before: Gao Yan Inventor before: He Rui Inventor before: Zeng Qiong Inventor before: Cai Hongliang Inventor before: Tang Dan |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201027 |