CN112413413B - Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology - Google Patents
Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology Download PDFInfo
- Publication number
- CN112413413B CN112413413B CN202011310729.0A CN202011310729A CN112413413B CN 112413413 B CN112413413 B CN 112413413B CN 202011310729 A CN202011310729 A CN 202011310729A CN 112413413 B CN112413413 B CN 112413413B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- original data
- monitoring
- sensor
- time
- 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.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technologies, which comprises the following steps: s1, collecting original data of the pipeline to be tested; s2, decomposing and reconstructing the original data to obtain corresponding low-frequency signals and high-frequency signals; s3, predicting the pipeline parameters at the next moment based on the low-frequency signal; s4, comparing the predicted pipeline parameters with the actually measured parameters to determine the working state of the pipeline; s5, extracting parameter change time based on the high-frequency signal; s6, determining the propagation speed of the pressure wave in the pipeline based on the high-frequency signal and the parameter change time; and S7, when the pipeline works abnormally, positioning the abnormal position by combining the propagation speed, and realizing the monitoring and positioning of the pipeline leakage. The invention can solve the problems of lack of leakage samples in pipeline leakage monitoring, long response time, high false alarm rate and high cost in pipeline leakage monitoring and positioning, and effectively realizes quick, efficient and low-cost pipeline leakage monitoring and pipeline leakage positioning.
Description
Technical Field
The invention belongs to the technical field of pipeline transportation safety monitoring, and particularly relates to a pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technologies.
Background
The long-distance pipeline transportation is used as an economic and efficient transportation mode and is widely applied to oil and gas transportation in the petrochemical industry and tap water transportation of urban water supply systems. The long-distance pipeline is influenced by aging of a pipeline protective layer, medium corrosion, environment and human factors due to long-term operation, and the leakage accident of the pipeline cannot be avoided. And the conditions of fire, explosion, poison and the like caused by leakage of the pipeline network can cause huge economic loss and environmental pollution and threaten the lives and properties of people. Therefore, the need to develop all-weather pipeline leakage monitoring and positioning technology and to incorporate the technology into practical applications is particularly urgent.
The methods for monitoring and positioning leakage of pipelines at home and abroad can be divided into two categories: one is to detect leakage and position by using the changes of physical parameters of the pipeline such as flow, pressure, temperature and the like caused by leakage; another category is the direct detection of fluid leaking out of the pipeline (oil, gas, water) and its environmental impact (e.g. temperature changes, acoustic signatures) in the vicinity of the leak.
With the rapid development of computer technology, modern control theory, signal processing technology and artificial intelligence technology, the first pipeline leakage monitoring and leakage positioning method has great progress, wherein the two methods can well monitor the leakage of the pipeline, but generally have the defects of long response time, high false alarm rate and incapability of accurately positioning the leakage. In recent years, the development and maturity of optical fiber technology and unmanned aerial vehicle technology enable the second class of technology to be applied to practical scenes in a large number, the practical application of optical fiber technology always faces the difficult problems of high construction cost and high operation and maintenance cost of existing pipelines, and the unmanned aerial vehicle technology cannot realize 24-hour uninterrupted monitoring due to the limitation of weather conditions.
Disclosure of Invention
Aiming at the defects in the prior art, the pipeline leakage monitoring and positioning method combining the deep learning and multiple measurement technologies solves the problems of long response time, high false alarm rate and high cost in the existing pipeline leakage monitoring and positioning method.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: the pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technologies comprises the following steps:
s1, collecting original data of the pipeline to be tested;
s2, decomposing and reconstructing the acquired original data by utilizing a wavelet transform technology to obtain a low-frequency signal and a high-frequency signal corresponding to the original data;
s3, predicting the pipeline physical parameters at the next moment through a pipeline physical parameter prediction model based on the low-frequency signals of the original data;
s4, comparing the pipeline physical parameters obtained by the prediction of the pipeline prediction model with the actually measured pipeline physical parameters at the corresponding moment and position, and determining the current pipeline working state;
s5, extracting the modified physical parameter change time based on the high-frequency signal of the original data;
s6, determining the propagation speed of pressure waves in the pipeline based on the high-frequency signals of the original data and the change time of the physical parameters of the pipeline;
and S7, when the working state of the pipeline is abnormal, positioning the abnormal position by combining the propagation speed of pressure waves in the pipeline, and realizing the monitoring and positioning of the pipeline leakage.
Further, in the step S1, the original data of the pipeline to be tested is collected by the pipeline parameter sensors installed in the valve chambers or stations at the upstream and downstream of the pipeline to be tested;
the pipeline parameter sensor comprises a flow sensor, a pressure sensor and a temperature sensor.
Further, the step S2 is specifically:
original data are represented by using the oscillation of the mother wavelet with finite length and fast attenuation, and the original data are decomposed and reconstructed by scaling and translating the mother wavelet, so that a low-frequency signal and a high-frequency signal corresponding to the original data are obtained.
Further, in the step S2:
the mother wavelet ψ (t) needs to satisfy the conditions:
when the original data is decomposed and reconstructed, the scaling and shifting process expression of the mother wavelet is as follows:
in the formula, #s,uAnd (t) is a mother wavelet in the zooming and translating processes, t is time, u is a zooming control parameter, and s is a translating control parameter.
Further, the pipeline physical parameter prediction model in step S3 is a deep learning model that is constructed based on artificial intelligence and that realizes the function of extracting pipeline physical parameters;
the deep learning model comprises a multilayer sensor, a convolutional neural network, a long-term short-term memory network and a hybrid neural network;
and a plurality of pipeline physical parameter prediction models are respectively arranged at the upstream and the downstream of the pipeline to be tested, and each pipeline physical parameter prediction model predicts the pipeline physical parameter at the position at the next moment based on the pipeline physical parameter at the position in the low-frequency signal of the input original data.
Further, the pipeline working state in the step S4 includes a normal state, a manual operation state and an abnormal state; the abnormal state includes a pipe leakage and a pipe theft.
Further, the step S5 is specifically:
s51, determining a plurality of time measurement values when each physical parameter changes based on the high-frequency signals of the original data;
and S52, carrying out statistical analysis on the time measurement values when the same physical parameter changes, and extracting the corresponding physical parameter change time.
Further, the step S6 is specifically:
determining a pressure signal in a high-frequency signal corresponding to original data obtained by a pressure sensor, extracting time information when the pressure signal changes suddenly, namely change time corresponding to a pressure signal parameter, and determining the propagation speed of pressure waves in a pipeline;
the calculation formula of the propagation velocity v is as follows:
where L is the length of the pipe between the upstream and downstream sensors in the pipe, tupTime of passage of pressure wave through upstream sensor location, tdownIs the time at which the pressure wave passes the downstream sensor location.
Further, the step S7 is specifically:
s71, acquiring the time when the negative pressure wave generated when the pipeline is abnormal passes through the positions of the upstream sensor and the downstream sensor of the pipeline by a multi-time measurement technology;
and S72, determining the abnormal position of the pipeline according to the time of the negative pressure wave passing through the positions of the upstream sensor and the downstream sensor of the pipeline based on the propagation velocity of the pressure wave, and realizing the monitoring and positioning of the pipeline leakage.
Further, the step S71 is specifically:
a1, decomposing a negative pressure wave signal generated by pipeline abnormity by using mother wavelets in a wavelet transform technology, and reconstructing a corresponding high-frequency signal;
a2, determining the change time of the negative pressure wave based on the high-frequency signal corresponding to the negative pressure wave, namely the time of passing through the positions of the upstream sensor and the downstream sensor of the pipeline;
in step S72, the positioning formula of the abnormal position of the pipeline is:
wherein X is the distance between the abnormal position of the pipeline and the upstream sensor position, t'upIs the time t 'at which the negative pressure wave passes through the upstream sensor position'downIs the time at which the pressure wave passes the downstream sensor location.
The invention has the beneficial effects that:
(1) the automation level is high, and the workload of operators is greatly reduced;
(2) the response time is short, the response time is less than 10 seconds, the pipeline problem can be found as soon as possible, response countermeasures can be made in time, and economic and environmental losses are reduced;
(3) the method is realized based on an artificial intelligence deep learning technology, and can effectively reduce the false alarm rate and improve the positioning precision and the leakage monitoring sensitivity by accumulating data;
(4) the installation is convenient, the structure of the existing pipeline is not changed, the non-stop installation and the non-stop unloading of the monitoring equipment can be realized, the safe operation of the pipeline is ensured, and the pipeline monitoring device is suitable for single-section pipelines with various lengths;
(5) the application range is wide, and the device can be used for various pipelines for oil transportation, gas transportation, water transportation and the like.
Drawings
Fig. 1 is a flow chart of a method for monitoring and positioning pipeline leakage by combining deep learning and multiple measurement technologies according to the present invention.
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.
Example 1:
as shown in fig. 1, the method for monitoring and locating pipeline leakage by combining deep learning and multiple measurement technologies includes the following steps:
s1, collecting original data of the pipeline to be tested;
s2, decomposing and reconstructing the acquired original data by utilizing a wavelet transform technology to obtain a low-frequency signal and a high-frequency signal corresponding to the original data;
s3, predicting the pipeline physical parameters at the next moment through a pipeline physical parameter prediction model based on the low-frequency signals of the original data;
s4, comparing the pipeline physical parameters obtained by the prediction of the pipeline prediction model with the actually measured pipeline physical parameters at the corresponding moment and position, and determining the current pipeline working state;
s5, extracting the modified physical parameter change time based on the high-frequency signal of the original data;
s6, determining the propagation speed of pressure waves in the pipeline based on the high-frequency signals of the original data and the change time of the physical parameters of the pipeline;
and S7, when the working state of the pipeline is abnormal, positioning the abnormal position by combining the propagation speed of pressure waves in the pipeline, and realizing the monitoring and positioning of the pipeline leakage.
In step S1, acquiring raw data of the pipeline to be tested by pipeline parameter sensors installed in valve chambers or stations upstream and downstream of the pipeline to be tested; the pipeline parameter sensor comprises a flow sensor, a pressure sensor and a temperature sensor. And when the data are acquired, the time synchronization of the upstream acquisition system and the downstream acquisition system is realized by utilizing a global positioning system or a Beidou satellite technology.
In step S2 of this embodiment, the wavelet transform technique (WT) is to use the oscillation of the mother wavelet with finite length and fast attenuation to represent signals, and implement decomposition and reconstruction of the original data by scaling and translating the mother wavelet, so as to obtain the low-frequency signal and the high-frequency signal corresponding to the original data.
The mother wavelet ψ (t) needs to satisfy the conditions:
when the original data is decomposed and reconstructed, the scaling and shifting process expression of the mother wavelet is as follows:
in the formula, #s,u(t) is zooming and panningIn the process, t is time, u is a scaling control parameter, and s is a translation control parameter.
Based on the frequency characteristics of original data signals, the wavelet transformation technology firstly decomposes the original data to obtain signals of a low frequency part and a high frequency part, wherein the signals of the low frequency part are used as signals for removing noise and used for the next deep learning model modeling based on artificial intelligence, and the signals of the high frequency part are used for analyzing time information.
In this embodiment, the pipeline physical parameter prediction model in step S3 is a deep learning model that is constructed based on artificial intelligence and realizes the function of extracting pipeline physical parameters;
the deep learning model comprises a multilayer sensor, a convolutional neural network, a long-term short-term memory network and a hybrid neural network;
the upstream and the downstream of the pipeline to be tested are respectively provided with a plurality of pipeline physical parameter prediction models, and each pipeline physical parameter prediction model predicts the pipeline physical parameter of the position at the next moment based on the pipeline physical parameter of the position in the low-frequency signal of the input original data.
In step S4 of this embodiment, a pipeline state determination model is established by an artificial intelligence technique to compare the predicted parameters with the actual parameters, and the pipeline operating states determined by the pipeline state determination model include a normal state, a manual operating state, and an abnormal state; the abnormal state includes a pipe leakage, a pipe theft, and the like.
Step S5 of this embodiment specifically includes:
s51, determining a plurality of time measurement values when each physical parameter changes based on the high-frequency signals of the original data;
s52, carrying out statistical analysis on the time measurement values when the same physical parameter changes, and extracting the corresponding physical parameter change time;
when the high-frequency signals of the original data are obtained, the original data are decomposed and reconstructed by utilizing mother wavelets comprising 2-10 th-order Daubechies wavelets (db2, db3, … and db10) and 2-10 th-order symlets (sym2, sym3, … and sym10), signals of high-frequency parts of various original data are obtained, time measurement values of a plurality of high-frequency signals corresponding to different processing methods of the same parameter are determined, length measurement is performed on the same object for a plurality of times by using different rulers similarly, and then the plurality of measurement values are processed to obtain data which is closest to a real value; the above statistical analysis methods include averaging, maximum likelihood estimation, and the like.
Step S6 of this embodiment specifically includes:
determining a pressure signal in a high-frequency signal corresponding to original data obtained by a pressure sensor, extracting time information when the pressure signal changes suddenly, namely change time corresponding to a pressure signal parameter, and determining the propagation speed of pressure waves in a pipeline;
the propagation velocity v is calculated as:
where L is the length of the pipe between the upstream and downstream sensors in the pipe, tupTime of passage of pressure wave through upstream sensor location, tdownTime of passage of the pressure wave through the downstream sensor location; the upstream sensor and the downstream sensor comprise various sensors such as temperature, flow rate and pressure, and the sensors are all arranged at the same position on the pipeline, and the process uses the pressure signals collected by the pressure sensors.
In step S7 of this embodiment, when a pipeline leaks or is stolen, a negative pressure wave is generated at the time of the pipeline leakage and the time of the pipeline theft, and the negative pressure wave propagates from the leakage point and the theft point to both ends of the pipeline, and once the pipeline leakage or the pipeline theft occurs, the pipeline state determination model detects the pressure abnormality and starts the pipeline leakage and pipeline theft positioning; based on this, the step S7 is specifically:
s71, acquiring the time when the negative pressure wave generated when the pipeline is abnormal passes through the positions of the upstream sensor and the downstream sensor of the pipeline by a multi-time measurement technology;
when extracting the time information of the negative pressure wave during the transmission, decomposing the negative pressure wave generated by the pipeline leakage or the theft by utilizing a wavelet transform technology according to the data processing method by utilizing a plurality of mother wavelets to reconstruct a corresponding high-frequency signal, and further extracting the time information of the negative pressure wave reaching an upstream sensor and a downstream sensor, namely the time of the pipeline at the upstream sensor and the downstream sensor;
s72, determining the abnormal position of the pipeline according to the time of the negative pressure wave passing through the positions of the upstream sensor and the downstream sensor of the pipeline based on the propagation velocity of the pressure wave, and realizing the monitoring and positioning of pipeline leakage;
the positioning formula of the abnormal position of the pipeline is as follows:
wherein X is the distance between the abnormal position of the pipeline and the upstream sensor position, t'upIs the time t 'at which the negative pressure wave passes through the upstream sensor position'downIs the time at which the pressure wave passes the downstream sensor location.
Claims (8)
1. The pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technologies is characterized by comprising the following steps of:
s1, collecting original data of the pipeline to be tested;
s2, decomposing and reconstructing the acquired original data by utilizing a wavelet transform technology to obtain a low-frequency signal and a high-frequency signal corresponding to the original data;
s3, predicting the pipeline physical parameters at the next moment through a pipeline physical parameter prediction model based on the low-frequency signals of the original data;
s4, comparing the pipeline physical parameters obtained by the prediction of the pipeline physical parameter prediction model with the actually measured pipeline physical parameters at the corresponding moment and position, and determining the current pipeline working state;
s5, extracting the modified physical parameter change time based on the high-frequency signal of the original data;
s6, determining the propagation speed of the pressure wave in the pipeline based on the high-frequency signal of the original data and the corrected physical parameter change time;
s7, when the working state of the pipeline is abnormal, the abnormal position is positioned by combining the propagation speed of pressure waves in the pipeline, and pipeline leakage monitoring and positioning are realized;
the step S2 specifically includes:
original data are represented by using the oscillation of the mother wavelet with finite length and rapid attenuation, and the original data are decomposed and reconstructed by zooming and translating the mother wavelet to obtain a low-frequency signal and a high-frequency signal corresponding to the original data;
the mother wavelet ψ (t) needs to satisfy the conditions:
when the original data is decomposed and reconstructed, the scaling and shifting process expression of the mother wavelet is as follows:
in the formula, #s,uAnd (t) is a mother wavelet in the zooming and translating processes, t is time, u is a zooming control parameter, and s is a translating control parameter.
2. The method for monitoring and locating pipeline leakage according to claim 1, wherein the step S1 is to collect the raw data of the pipeline to be tested by pipeline parameter sensors installed in the valve chambers or stations at the upstream and downstream of the pipeline to be tested;
the pipeline parameter sensor comprises a flow sensor, a pressure sensor and a temperature sensor.
3. The method for monitoring and locating pipeline leakage according to claim 1, wherein the pipeline physical parameter prediction model in step S3 is a deep learning model constructed based on artificial intelligence and having the function of extracting pipeline physical parameters;
the deep learning model comprises a multilayer sensor, a convolutional neural network, a long-term short-term memory network and a hybrid neural network;
the upstream and the downstream of the pipeline to be tested are respectively provided with a plurality of pipeline physical parameter prediction models, and each pipeline physical parameter prediction model predicts the pipeline physical parameters of the corresponding position in the low-frequency signal of the input original data at the next moment based on the pipeline physical parameters of the corresponding position.
4. The method for monitoring and locating pipeline leakage by combining deep learning and multiple measurement technology as claimed in claim 2, wherein the pipeline working state in step S4 includes a normal state, a manual operation state and an abnormal state; the abnormal state includes a pipe leakage and a pipe theft.
5. The method for monitoring and locating pipeline leakage according to claim 1, wherein the step S5 specifically comprises:
s51, determining a plurality of time measurement values when each physical parameter changes based on the high-frequency signals of the original data;
and S52, carrying out statistical analysis on the time measurement values when the same physical parameter changes, and extracting the corresponding physical parameter change time.
6. The method for monitoring and locating pipeline leakage according to claim 1, wherein the step S6 specifically comprises:
determining a pressure signal in a high-frequency signal corresponding to original data obtained by a pressure sensor, extracting time information when the pressure signal changes suddenly, namely change time corresponding to a pressure signal parameter, and determining the propagation speed of pressure waves in a pipeline;
the calculation formula of the propagation velocity v is as follows:
where L is the length of the pipe between the upstream and downstream sensors in the pipe, tupTime of passage of pressure wave through upstream sensor location, tdownIs the time at which the pressure wave passes the downstream sensor location.
7. The method for monitoring and locating pipeline leakage according to claim 6, wherein the step S7 is specifically as follows:
s71, acquiring the time when the negative pressure wave generated when the pipeline is abnormal passes through the positions of the upstream sensor and the downstream sensor of the pipeline by a multi-time measurement technology;
and S72, determining the abnormal position of the pipeline according to the time of the negative pressure wave passing through the positions of the upstream sensor and the downstream sensor of the pipeline based on the propagation velocity of the pressure wave, and realizing the monitoring and positioning of the pipeline leakage.
8. The method for monitoring and locating pipeline leakage according to claim 7, wherein the step S71 is specifically as follows:
a1, decomposing a negative pressure wave signal generated by pipeline abnormity by using mother wavelets in a wavelet transform technology, and reconstructing a corresponding high-frequency signal;
a2, determining the change time of the negative pressure wave based on the high-frequency signal corresponding to the negative pressure wave, namely the time of passing through the positions of the upstream sensor and the downstream sensor of the pipeline;
in step S72, the positioning formula of the abnormal position of the pipeline is:
wherein X is the distance between the abnormal position of the pipeline and the upstream sensor position, t'upIs the time t 'at which the negative pressure wave passes through the upstream sensor position'downThe time at which the negative pressure wave passes the downstream sensor location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011310729.0A CN112413413B (en) | 2020-11-20 | 2020-11-20 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011310729.0A CN112413413B (en) | 2020-11-20 | 2020-11-20 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112413413A CN112413413A (en) | 2021-02-26 |
| CN112413413B true CN112413413B (en) | 2022-03-01 |
Family
ID=74776956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011310729.0A Active CN112413413B (en) | 2020-11-20 | 2020-11-20 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112413413B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160909A (en) * | 2021-04-30 | 2021-07-23 | 苏州华碧微科检测技术有限公司 | Method for rapidly identifying metal corrosion failure |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104595729A (en) * | 2015-01-15 | 2015-05-06 | 中国石油大学(华东) | Oil and gas pipeline leakage positioning method based on sound wave amplitude |
| CN106499957A (en) * | 2016-12-28 | 2017-03-15 | 沈阳工业大学 | A kind of pressure wave signal generator and in-pipeline detector real-time tracking localization method |
| CN107084313A (en) * | 2017-05-16 | 2017-08-22 | 云南大红山管道有限公司 | Ore slurry pipeline leaks positioning alarm system and method |
| CN108662442A (en) * | 2018-08-23 | 2018-10-16 | 辽宁石油化工大学 | The localization method and device of pipe leakage |
| CN108870091A (en) * | 2018-07-19 | 2018-11-23 | 东北大学 | Line leakage system and method based on low-and high-frequency hybrid detection |
| CN108870090A (en) * | 2018-06-22 | 2018-11-23 | 大连理工大学 | Pipeline leakage detection method based on the fusion of least square method supporting vector machine information |
| CN108980628A (en) * | 2018-07-27 | 2018-12-11 | 上海航天动力科技工程有限公司 | A kind of water supply network booster alarm method |
| CN109114431A (en) * | 2018-09-30 | 2019-01-01 | 天津科技大学 | A kind of oil and gas pipeline hydrate monitoring technology |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
| 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 |
| CN110529746A (en) * | 2019-09-05 | 2019-12-03 | 北京化工大学 | Detection method, device and the equipment of pipe leakage |
| CN110751073A (en) * | 2019-10-12 | 2020-02-04 | 武汉理工大学 | Pipeline early damage mode identification method based on distributed optical fiber sensing and deep learning |
| CN111899224A (en) * | 2020-06-30 | 2020-11-06 | 烟台市计量所 | Nuclear power pipeline defect detection system based on deep learning attention mechanism |
-
2020
- 2020-11-20 CN CN202011310729.0A patent/CN112413413B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104595729A (en) * | 2015-01-15 | 2015-05-06 | 中国石油大学(华东) | Oil and gas pipeline leakage positioning method based on sound wave amplitude |
| CN106499957A (en) * | 2016-12-28 | 2017-03-15 | 沈阳工业大学 | A kind of pressure wave signal generator and in-pipeline detector real-time tracking localization method |
| CN107084313A (en) * | 2017-05-16 | 2017-08-22 | 云南大红山管道有限公司 | Ore slurry pipeline leaks positioning alarm system and method |
| CN108870090A (en) * | 2018-06-22 | 2018-11-23 | 大连理工大学 | Pipeline leakage detection method based on the fusion of least square method supporting vector machine information |
| CN108870091A (en) * | 2018-07-19 | 2018-11-23 | 东北大学 | Line leakage system and method based on low-and high-frequency hybrid detection |
| CN108980628A (en) * | 2018-07-27 | 2018-12-11 | 上海航天动力科技工程有限公司 | A kind of water supply network booster alarm method |
| CN108662442A (en) * | 2018-08-23 | 2018-10-16 | 辽宁石油化工大学 | The localization method and device of pipe leakage |
| CN109114431A (en) * | 2018-09-30 | 2019-01-01 | 天津科技大学 | A kind of oil and gas pipeline hydrate monitoring technology |
| 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 |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
| CN110529746A (en) * | 2019-09-05 | 2019-12-03 | 北京化工大学 | Detection method, device and the equipment of pipe leakage |
| CN110751073A (en) * | 2019-10-12 | 2020-02-04 | 武汉理工大学 | Pipeline early damage mode identification method based on distributed optical fiber sensing and deep learning |
| CN111899224A (en) * | 2020-06-30 | 2020-11-06 | 烟台市计量所 | Nuclear power pipeline defect detection system based on deep learning attention mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112413413A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113963514B (en) | Integrated monitoring and early warning system for oil gasification pipeline | |
| Liu et al. | A leak detection method for oil pipeline based on Markov feature and two-stage decision scheme | |
| US9797799B2 (en) | Intelligent adaptive system and method for monitoring leakage of oil pipeline networks based on big data | |
| CN101539241B (en) | Hierarchical multi-source data fusion method for pipeline linkage monitoring network | |
| CN100456010C (en) | Method for detecting leakage of oil gas pipe based on pressure signal knee | |
| Lang et al. | A multiple leaks’ localization method in a pipeline based on change in the sound velocity | |
| CN109470352B (en) | Distributed optical fiber pipeline safety monitoring algorithm based on self-adaptive threshold | |
| CN103994333B (en) | A kind of oil gas pipe network leakage detection method merged based on two-dimensional signal | |
| Yang et al. | Pipeline safety early warning by multifeature-fusion CNN and LightGBM analysis of signals from distributed optical fiber sensors | |
| CN111695465A (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
| CN115935241B (en) | Multi-parameter mutually-fused pipe cleaner real-time positioning method and device | |
| CN112413413B (en) | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology | |
| Pang et al. | An integrated LSTM-AM and SPRT method for fault early detection of forced-oxidation system in wet flue gas desulfurization | |
| Han et al. | Plastic pipeline leak localization based on wavelet packet decomposition and higher order cumulants | |
| CN111365623B (en) | Negative pressure wave inflection point identification method based on linear fitting | |
| CN102168809A (en) | Method and system for detecting leakage of parking apron aviation gasoline pipe network based on pressure and temperature analysis | |
| Li et al. | The application research of internet of things to oil pipeline leak detection | |
| CN111783945A (en) | Long oil transmission pipeline leakage real-time detection system based on transfer learning LSTM | |
| Cai et al. | A data-driven early micro-leakage detection and localization approach of hydraulic systems | |
| Wang et al. | RVFL-based optical fiber intrusion signal recognition with multi-level wavelet decomposition as feature | |
| CN111879479B (en) | Micro-leakage signal monitoring system and method for non-Gaussian noise environment of gas collecting and conveying pipeline | |
| Liu et al. | A non-contacting leak fault diagnosis method for subsea Christmas tree valve based on deep neural network with skip connections | |
| Tylman et al. | Fully automatic AI-based leak detection system | |
| CN113465826B (en) | Gas leakage detection method and device | |
| Obshta et al. | Cyber-Physical System for Diagnostic Along the Controlled Section of the Oil Pipeline |
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 |