CN116228770B - Method and system for identifying and monitoring pipeline leakage - Google Patents
Method and system for identifying and monitoring pipeline leakage Download PDFInfo
- Publication number
- CN116228770B CN116228770B CN202310512089.9A CN202310512089A CN116228770B CN 116228770 B CN116228770 B CN 116228770B CN 202310512089 A CN202310512089 A CN 202310512089A CN 116228770 B CN116228770 B CN 116228770B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- leakage
- application
- semantic segmentation
- monitoring
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/002—Investigating fluid-tightness of structures by using thermal means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Abstract
The application relates to the technical field of monitoring data processing, and provides a method and a system for identifying and monitoring pipeline leakage. The method comprises the following steps: performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results; performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions; calculating and comparing based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information; detecting the target pipeline based on a distributed detection sensing network to obtain pipeline leakage characteristic monitoring information; and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information. By adopting the method, the comprehensiveness of pipeline monitoring can be improved, the accuracy of monitoring and identifying can be increased, the efficiency of monitoring and identifying leakage can be improved, and the technical effect of timely treating the problem of pipeline leakage can be further realized.
Description
Technical Field
The application relates to the technical field of monitoring data processing, in particular to a method and a system for identifying and monitoring pipeline leakage.
Background
In the process of oil, gas and water transportation of buried pipelines in high-temperature and high-pressure production of large petrochemical industry, material media conveyed in the pipelines can be leaked due to the influence of factors such as corrosion, scraping, vibration, season and underground change. If the pipeline is not maintained and treated in time, leakage is increased, so that materials are lost, and the environment is polluted; if the materials volatilize toxic, inflammable and explosive gases, fire, explosion, poisoning and personal injury accidents can be caused, so that production cannot be performed, and the enterprise is caused to stop production in an unscheduled way. For the leakage accident of public engineering pipeline, the water, fuel gas and steam are stopped, which brings inconvenience to the life of the users.
Therefore, the real-time monitoring of the operation pipeline and the timely maintenance and treatment of the leakage problem of the pipeline are extremely important, and the method is a key for ensuring the safety, stability, long period, full load, optimizing continuous production, saving energy, reducing environmental pollution and guaranteeing the life of people. However, the monitoring mode of the pipeline in the prior art is not comprehensive enough, and the monitoring and identifying accuracy is low, so that the problem of pipeline leakage cannot be treated in time.
Disclosure of Invention
Based on the above, it is necessary to provide a method and a system for identifying and monitoring pipeline leakage, which can improve the comprehensiveness of pipeline monitoring, increase the accuracy of monitoring and identifying, improve the efficiency of identifying and monitoring leakage, and further realize timely treatment of pipeline leakage.
A method of identifying and monitoring a pipe leak, the method comprising: the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set; performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results; performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions; obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information; determining a distributed detection sensing network according to the pipeline distribution environment structure; detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information; and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
An identification monitoring system for pipe leaks, the system comprising: the visual detection module is used for monitoring the target pipeline in real time through the visual detection device to obtain a multi-angle pipeline application image information set; the semantic segmentation module is used for carrying out semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results; the application distribution analysis module is used for carrying out application distribution analysis based on the plurality of pipeline characteristic semantic segmentation results to obtain pipeline application distribution proportion; the application calculation comparison module is used for obtaining pipeline application standards, and calculating and comparing based on the pipeline application distribution proportion and the pipeline application standards to obtain pipeline application leakage monitoring information; the detection sensing network determining module is used for determining a distributed detection sensing network according to the pipeline distribution environment structure; the sensing network detection module is used for detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information; and the identification monitoring result generation module is used for generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set;
performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions;
obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information;
determining a distributed detection sensing network according to the pipeline distribution environment structure;
detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set;
performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions;
obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information;
determining a distributed detection sensing network according to the pipeline distribution environment structure;
detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
The identification monitoring method and the system for the pipeline leakage solve the technical problems that the pipeline leakage problem cannot be treated in time due to the fact that the pipeline monitoring mode is not comprehensive enough and the monitoring identification accuracy is low in the prior art, and achieve the technical effects of improving the pipeline monitoring comprehensiveness, increasing the monitoring identification accuracy, improving the leakage monitoring identification efficiency and further realizing timely treatment of the pipeline leakage problem by combining the visual detection and detection sensing network mode.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a flow chart of a method for identifying and monitoring a pipe leak according to one embodiment;
FIG. 2 is a flow chart of obtaining semantic segmentation results of a plurality of pipeline features in a method for identifying and monitoring pipeline leakage according to an embodiment;
FIG. 3 is a block diagram of an identification monitoring system for pipe leaks in one embodiment;
fig. 4 is an internal structural diagram of a computer device in one embodiment.
Reference numerals illustrate: the system comprises a visual detection module 11, a semantic segmentation module 12, an application distribution analysis module 13, an application calculation comparison module 14, a detection sensing network determination module 15, a sensing network detection module 16 and a recognition monitoring result generation module 17.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the present application provides a method for identifying and monitoring a pipe leakage, the method comprising:
step S100: the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set;
specifically, in the process of oil, gas and water transportation of buried pipelines in high-temperature and high-pressure production of large petrochemical industry, material media conveyed in the pipelines can be leaked due to the influence of factors such as corrosion, scraping, vibration, seasonal and underground changes. If the pipeline is not maintained and treated in time, leakage is increased, so that materials are lost, and the environment is polluted; if the materials volatilize toxic, inflammable and explosive gases, fire, explosion, poisoning and personal injury accidents can be caused, so that production cannot be performed, and the enterprise is caused to stop production in an unscheduled way. For the leakage accident of public engineering pipeline, the water, fuel gas and steam are stopped, which brings inconvenience to the life of the users. Therefore, the real-time monitoring of the operation pipeline and the timely maintenance and treatment of the leakage problem of the pipeline are extremely important, and the method is a key for ensuring the safety, stability, long period, full load, optimizing continuous production, saving energy, reducing environmental pollution and guaranteeing the life of people.
The target pipeline is monitored in real time through the visual detection device, wherein the visual detection device is high-precision industrial visual detection equipment, namely an industrial image pickup device, can continuously operate for a long time, is suitable for different application environments, and is high in precision, speed and efficiency. The multi-angle pipeline application image information set is obtained by shooting the pipeline to be monitored through the visual detection device in a multi-angle mode, namely, the image information of the pipeline in the application environment comprises pipeline and pipeline contact pieces, and medium images such as soil, walls, protection (temperature) layers and the like around the pipeline, and an image data foundation is provided for subsequent pipeline leakage monitoring and identification.
Step S200: performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
in one embodiment, as shown in fig. 2, the obtaining a plurality of pipeline feature semantic segmentation results, step S200 of the present application further includes:
step S210: acquiring a multi-angle pipeline application image database through a data mining technology;
step S220: performing data enhancement on the multi-angle pipeline application image database to obtain an expanded multi-angle pipeline application image database;
step S230: using the extended multi-angle pipeline application image database as training sample data, and performing semantic segmentation training on the training sample data by using a full convolution neural network structure to obtain a pipeline semantic segmentation model;
step S240: and carrying out semantic segmentation on the multi-angle pipeline application image information set based on the pipeline semantic segmentation model to obtain a model output result, wherein the model output result comprises a plurality of pipeline characteristic semantic segmentation results.
In one embodiment, the obtaining the pipeline semantic segmentation model, step S230 of the present application further includes:
step S231: performing pipeline image segmentation on the image information in the extended multi-angle pipeline application image database to obtain a plurality of pipeline application image segmentation result sets;
step S232: constructing a network encoder and a network decoder based on the full convolutional neural network structure;
step S233: dividing the extended multi-angle pipeline application image database and the multiple pipeline application image segmentation result sets to obtain a data training set, a data verification set and a data test set;
step S234: and performing supervised training on the network encoder and the network decoder by adopting the data training set, and verifying and testing the encoder and the decoder by adopting the data verification set and the data testing set until the model accuracy meets the preset requirement, so as to obtain the pipeline semantic segmentation model.
In one embodiment, the obtaining the extended multi-angle pipeline application image database further includes:
step S221: obtaining image data enhancement type information, wherein the image data enhancement type information comprises rotation, overturn, contrast, brightness, chromaticity adjustment, image blurring and scaling;
step S222: determining application image conversion parameters according to the image data enhancement type information;
step S223: and carrying out data amplification output on the multi-angle pipeline application image database based on the application image conversion parameters to obtain the extended multi-angle pipeline application image database.
Specifically, semantic segmentation is performed on the multi-angle pipeline application image information set, a multi-angle pipeline application image database is firstly obtained through a data mining technology, the multi-angle pipeline application image database is multi-angle images of various types of pipelines in different application environments, and pipeline image data samples are added through obtaining massive images. In order to increase the multi-condition image data volume, the multi-angle pipeline application image database is subjected to data enhancement, and specifically image data enhancement type information is set and acquired, wherein the image data enhancement type information comprises rotation, overturning, contrast, brightness, chromaticity adjustment, image blurring, scaling and the like. And determining application image conversion parameters according to the image data enhancement type information, wherein the application image conversion parameters are image data change matrixes corresponding to conversion types, and the corresponding conversion matrixes are different from different data conversion types. And carrying out data amplification output on the multi-angle pipeline application image database based on the application image conversion parameters, namely expanding the image database through a conversion type matrix to obtain an expanded multi-angle pipeline application image database, wherein the amplified image labels are kept unchanged, and the variety of pipeline image data is enriched.
And using the extended multi-angle pipeline application image database as training sample data, performing semantic segmentation training on the training sample data by using a full convolution neural network structure, and firstly performing pipeline image segmentation on the image information in the extended multi-angle pipeline application image database so as to enable the pipeline self structural area, soil, leakage liquid, protective layer medium and other areas in the segmented image information to obtain a plurality of pipeline application image segmentation result sets corresponding to the segmented image in the image database. Based on the full convolutional neural network structure, a network encoder and a network decoder are constructed, both of which are contained in the deep learning network structure. Dividing the extended multi-angle pipeline application image database and the multiple pipeline application image segmentation result sets, wherein the division proportion can be set by self, and the optimal proportion is 6:2:2, and a data training set, a data verification set and a data test set are obtained through division.
And performing supervised training on the network encoder and the network decoder by adopting the data training set, and after model training is completed, verifying and testing the encoder and the decoder by using the data verification set and the data test set until the model accuracy meets the preset requirement, wherein the accuracy preset requirement can be set by itself, and when the model training accuracy reaches the requirement standard, determining a pipeline semantic segmentation model for performing semantic segmentation on the pipeline image. And carrying out semantic segmentation on the multi-angle pipeline application image information set based on the pipeline semantic segmentation model to obtain a model output result, wherein the model output result comprises a plurality of pipeline characteristic semantic segmentation results, namely semantic segmentation results of the pipeline image to be monitored. And pipeline monitoring image processing is carried out through the high-precision semantic segmentation model, so that the image semantic segmentation accuracy and segmentation efficiency are improved, the complexity and information quantity of the monitoring image are reduced, and the pipeline monitoring result processing efficiency is further improved.
Step S300: performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions;
step S400: obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information;
step S500: determining a distributed detection sensing network according to the pipeline distribution environment structure;
specifically, application distribution analysis is performed based on the plurality of pipeline feature semantic segmentation results, that is, region distribution proportion calculation is performed on the image semantic segmentation results, including pipeline region area, contact medium region area, leakage liquid region area and the like, so as to obtain pipeline application distribution proportion. And obtaining a pipeline application standard, wherein the pipeline application standard is a pipeline application safety structure area distribution standard, calculating and comparing based on the pipeline application distribution proportion and the pipeline application standard, and exemplarily, the structural area is changed due to liquid leakage on the surface of the pipeline, the liquid distribution proportion is increased, and if the liquid distribution proportion exceeds the safety application standard, the leakage area proportion is marked to be used as pipeline application leakage monitoring information.
In addition, in order to strengthen the comprehensiveness and the monitoring accuracy of pipeline monitoring and leak colorless gas monitoring, a sensor network is arranged to monitor the pipeline in all directions. Firstly, determining a distribution structure of a pipeline application area, and then determining a distributed detection sensing network according to a pipeline distribution environment structure, wherein the distributed detection sensing network comprises a plurality of types of sensor groups, and comprehensively monitoring the pipeline through the sensor groups. According to the distribution environment structure, the distribution positions, the intervals and the directions of the sensors are divided, so that the monitoring of all-dimensional pipeline leakage is realized.
Step S600: detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
in one embodiment, the obtaining the monitoring information of the leakage characteristic of the pipeline, the step S600 of the present application further includes:
step S610: the distributed detection sensing network is arranged and comprises an infrared sensor, a stress sensor and a vibration sensor;
step S620: respectively acquiring infrared thermal image information, stress sensing signals and vibration sensing signals based on the distributed detection sensing network;
step S630: analyzing the infrared thermal image information, the stress sensing signal and the vibration sensing signal to respectively obtain a pipeline heat distribution characteristic, a stress change characteristic and a pipeline vibration characteristic;
step S640: and carrying out feature fusion on the heat distribution feature, the stress change feature and the vibration feature of the pipeline to generate the monitoring information of the leakage feature of the pipeline.
In one embodiment, the obtaining the heat distribution characteristic of the pipe, step S630 of the present application further includes:
step S631: preprocessing the infrared thermal image information to obtain standard infrared thermal image information;
step S632: obtaining pipeline infrared heat distribution information according to the standard infrared heat image information;
step S633: extracting the characteristics of the infrared heat distribution information of the pipeline to obtain infrared heat image characteristic information;
step S634: and determining the pipeline heat distribution characteristic based on the infrared thermal image characteristic information.
Specifically, the distributed detection sensing network is arranged according to a pipeline distribution environment structure, and comprises an infrared sensor, a stress sensor, a vibration sensor and the like. And detecting the target pipeline based on the distributed detection sensing network, and respectively acquiring infrared thermal image information, stress sensing signals and vibration sensing signals of pipeline monitoring based on monitoring of an infrared sensor, a stress sensor and a vibration sensor in the distributed detection sensing network. Analyzing the infrared thermal image information, the stress sensing signal and the vibration sensing signal, wherein the infrared thermal image analysis process is to pre-process the infrared thermal image information, including denoising, image enhancement and other processes, so as to obtain standard infrared thermal image information with clearer images. And obtaining pipeline infrared heat distribution information, namely pipeline surface temperature heat distribution information, according to the standard infrared heat image information. And extracting the characteristics of the infrared heat distribution information of the pipeline, namely extracting the heat characteristic points to obtain the infrared heat image characteristic information, wherein the infrared heat image characteristic information comprises infrared characteristic information such as local heating, point heating, overall heating, temperature gradient and the like. And determining pipeline heat distribution characteristics, namely pipeline operation temperature change and temperature gradient distribution characteristics, based on the infrared heat image characteristic information.
And analyzing the stress sensing signal and the vibration sensing signal in sequence to respectively obtain the stress change characteristics of the target pipeline, wherein local stress change of the pipeline caused by pipeline leakage and pipeline vibration characteristics are used for representing leakage noise information of the pipeline. And then carrying out feature fusion on the pipeline heat distribution feature, the stress change feature and the pipeline vibration feature to generate pipeline leakage feature monitoring information obtained by detecting and fusing the pipeline leakage feature by the sensing network, namely, the leakage monitoring auxiliary feature of the sensing network. The distributed detection sensor network is distributed to conduct all-dimensional monitoring on the pipeline, so that the comprehensiveness of pipeline monitoring is improved, and the accuracy of pipeline leakage monitoring and identification is further improved.
Step S700: and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
In one embodiment, the applying step S700 further includes:
step S710: performing visual modeling on the target pipeline to obtain a three-dimensional model of the target pipeline;
step S720: positioning the leakage position based on the pipeline leakage identification monitoring result and the target pipeline three-dimensional model to obtain pipeline leakage position information;
step S730: determining a pipeline leakage loss coefficient according to the pipeline leakage identification monitoring result;
step S740: and performing early warning operation and maintenance management and control on the target pipeline according to the pipeline leakage position information and the pipeline leakage loss coefficient.
Specifically, based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information, a pipeline leakage identification monitoring result is generated in a combined mode, wherein the pipeline leakage identification monitoring result comprises a pipeline leakage identification result, a leakage area, a leakage degree and the like, and the comprehensiveness and the accuracy of the pipeline leakage monitoring result are improved. In order to accurately position and operate and maintain the pipeline leakage position, visual modeling is carried out on the target pipeline, namely, space visual three-dimensional modeling is carried out on the pipeline application distribution structure, a target pipeline three-dimensional model is obtained, pipeline distribution information is visually displayed, and pipeline leakage positioning is facilitated.
And positioning the leakage position based on the pipeline leakage identification monitoring result and the target pipeline three-dimensional model, and performing position mapping marking on the pipeline three-dimensional model through the leakage identification result to obtain pipeline leakage position information. And determining a pipeline leakage loss coefficient according to the pipeline leakage identification monitoring result, wherein the pipeline leakage loss coefficient is the pipeline leakage severity, and the larger the coefficient is, the larger the pipeline leakage degree is. And according to the pipeline leakage position information and the pipeline leakage loss coefficient, a personalized operation and maintenance scheme is formulated, and an operation and maintenance person performs early warning operation and maintenance management and control on the target pipeline based on the personalized operation and maintenance scheme. The leakage problem of the pipeline is timely treated, the operation and maintenance efficiency of the pipeline is improved, and the operation safety and stability of the pipeline are ensured.
In one embodiment, as shown in FIG. 3, there is provided an identification monitoring system for pipe leaks, comprising: the system comprises a visual detection module 11, a semantic segmentation module 12, an application distribution analysis module 13, an application calculation comparison module 14, a detection sensing network determination module 15, a sensing network detection module 16 and a recognition monitoring result generation module 17, wherein:
the visual detection module 11 is used for monitoring the target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set;
the semantic segmentation module 12 is used for carrying out semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
an application distribution analysis module 13, configured to perform application distribution analysis based on the multiple pipeline feature semantic segmentation results, to obtain a pipeline application distribution proportion;
an application calculation and comparison module 14, configured to obtain a pipeline application standard, and perform calculation and comparison based on the pipeline application distribution ratio and the pipeline application standard to obtain pipeline application leakage monitoring information;
the detection sensing network determining module 15 is used for determining a distributed detection sensing network according to the pipeline distribution environment structure;
the sensing network detection module 16 is used for detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
the identification monitoring result generating module 17 is configured to generate a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
In one embodiment, the system further comprises:
the application image database acquisition unit is used for acquiring a multi-angle pipeline application image database through a data mining technology;
the data enhancement unit is used for enhancing the data of the multi-angle pipeline application image database to obtain an expanded multi-angle pipeline application image database;
the semantic segmentation training unit is used for taking the extended multi-angle pipeline application image database as training sample data, and carrying out semantic segmentation training on the training sample data by using a full convolution neural network structure to obtain a pipeline semantic segmentation model;
the semantic segmentation result output unit is used for carrying out semantic segmentation on the multi-angle pipeline application image information set based on the pipeline semantic segmentation model to obtain a model output result, wherein the model output result comprises a plurality of pipeline characteristic semantic segmentation results.
In one embodiment, the system further comprises:
the pipeline image segmentation unit is used for carrying out pipeline image segmentation on the image information in the extended multi-angle pipeline application image database to obtain a plurality of pipeline application image segmentation result sets;
the encoder and decoder constructing unit is used for constructing a network encoder and a network decoder based on the full convolution neural network structure;
the data set dividing unit is used for dividing the extended multi-angle pipeline application image database and the plurality of pipeline application image segmentation result sets to obtain a data training set, a data verification set and a data test set;
and the model supervision and training unit is used for performing supervision and training on the network encoder and the network decoder by adopting the data training set, verifying and testing the encoder and the decoder by adopting the data verification set and the data testing set until the model accuracy meets the preset requirement, and obtaining the pipeline semantic segmentation model.
In one embodiment, the system further comprises:
a data enhancement type acquisition unit for acquiring image data enhancement type information including rotation, inversion, contrast, brightness, chromaticity adjustment, image blurring, and scaling;
a conversion parameter determining unit for determining an application image conversion parameter according to the image data enhancement type information;
and the data amplification output unit is used for carrying out data amplification output on the multi-angle pipeline application image database based on the application image conversion parameters to obtain the extended multi-angle pipeline application image database.
In one embodiment, the system further comprises:
the detection sensing network setting unit is used for setting the distributed detection sensing network, and the distributed detection sensing network comprises an infrared sensor, a stress sensor and a vibration sensor;
the signal detection acquisition unit is used for respectively acquiring infrared thermal image information, stress sensing signals and vibration sensing signals based on the distributed detection sensing network;
the signal analysis unit is used for analyzing the infrared thermal image information, the stress sensing signal and the vibration sensing signal to respectively obtain pipeline heat distribution characteristics, stress change characteristics and pipeline vibration characteristics;
and the characteristic fusion unit is used for carrying out characteristic fusion on the heat distribution characteristic, the stress change characteristic and the pipeline vibration characteristic of the pipeline to generate the pipeline leakage characteristic monitoring information.
In one embodiment, the system further comprises:
the image preprocessing unit is used for preprocessing the infrared thermal image information to obtain standard infrared thermal image information;
the infrared heat distribution obtaining unit is used for obtaining pipeline infrared heat distribution information according to the standard infrared heat image information;
the characteristic extraction unit is used for carrying out characteristic extraction on the infrared heat distribution information of the pipeline to obtain infrared heat image characteristic information;
and the heat separation characteristic determining unit is used for determining the heat distribution characteristic of the pipeline based on the infrared heat image characteristic information.
In one embodiment, the system further comprises:
the visual modeling unit is used for performing visual modeling on the target pipeline to obtain a three-dimensional model of the target pipeline;
the leakage position positioning unit is used for positioning the leakage position based on the pipeline leakage identification monitoring result and the target pipeline three-dimensional model to obtain pipeline leakage position information;
the leakage loss coefficient determining unit is used for determining a pipeline leakage loss coefficient according to the pipeline leakage identification monitoring result;
and the early warning operation and maintenance control unit is used for carrying out early warning operation and maintenance control on the target pipeline according to the pipeline leakage position information and the pipeline leakage loss coefficient.
For a specific embodiment of a system for identifying and monitoring a pipe leakage, reference may be made to the above embodiment of a method for identifying and monitoring a pipe leakage, which is not described herein. The above-mentioned various modules in the device for identifying and monitoring pipe leakage can be implemented in whole or in part by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing news data, time attenuation factors and other data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of identifying and monitoring for pipe leaks.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of: the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set; performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results; performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions; obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information; determining a distributed detection sensing network according to the pipeline distribution environment structure; detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information; and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set; performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results; performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results to obtain pipeline application distribution proportions; obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information; determining a distributed detection sensing network according to the pipeline distribution environment structure; detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information; and generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information. The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (6)
1. A method for identifying and monitoring a pipe leak, the method comprising:
the method comprises the steps of monitoring a target pipeline in real time through a visual detection device to obtain a multi-angle pipeline application image information set;
performing semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
performing application distribution analysis based on the plurality of pipeline feature semantic segmentation results, and performing region distribution proportion calculation on the image semantic segmentation results, wherein the region distribution proportion calculation comprises pipeline region areas, contact medium region areas and leakage liquid region areas, so as to obtain pipeline application distribution proportion;
obtaining a pipeline application standard, and performing calculation and comparison based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information, wherein the pipeline application standard is a pipeline application safety structure area distribution standard;
according to the pipeline distribution environment structure, dividing the distribution positions, intervals and directions of the sensors to determine a distributed detection sensing network;
detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
generating a pipeline leakage identification monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information, wherein the pipeline leakage identification monitoring result comprises a pipeline leakage identification result, a leakage area and a leakage degree;
wherein the obtaining the pipeline leakage characteristic monitoring information comprises:
the distributed detection sensing network is arranged and comprises an infrared sensor, a stress sensor and a vibration sensor;
respectively acquiring infrared thermal image information, stress sensing signals and vibration sensing signals based on the distributed detection sensing network;
analyzing the infrared thermal image information, the stress sensing signal and the vibration sensing signal to respectively obtain a pipeline heat distribution characteristic, a stress change characteristic and a pipeline vibration characteristic;
performing feature fusion on the heat distribution feature, the stress variation feature and the vibration feature of the pipeline to generate the monitoring information of the leakage feature of the pipeline;
the obtaining a plurality of pipeline feature semantic segmentation results comprises:
acquiring a multi-angle pipeline application image database through a data mining technology;
performing data enhancement on the multi-angle pipeline application image database to obtain an expanded multi-angle pipeline application image database;
using the extended multi-angle pipeline application image database as training sample data, and performing semantic segmentation training on the training sample data by using a full convolution neural network structure to obtain a pipeline semantic segmentation model;
performing semantic segmentation on the multi-angle pipeline application image information set based on the pipeline semantic segmentation model to obtain a model output result, wherein the model output result comprises a plurality of pipeline feature semantic segmentation results;
the obtaining the pipeline semantic segmentation model comprises the following steps:
performing pipeline image segmentation on the image information in the extended multi-angle pipeline application image database to obtain a plurality of pipeline application image segmentation result sets;
constructing a network encoder and a network decoder based on the full convolutional neural network structure;
dividing the extended multi-angle pipeline application image database and the multiple pipeline application image segmentation result sets to obtain a data training set, a data verification set and a data test set;
performing supervised training on the network encoder and the network decoder by adopting the data training set, and verifying and testing the encoder and the decoder by adopting the data verification set and the data test set until the accuracy of the model meets the preset requirement, so as to obtain the pipeline semantic segmentation model;
performing visual modeling on the target pipeline to obtain a three-dimensional model of the target pipeline;
positioning the leakage position based on the pipeline leakage identification monitoring result and the target pipeline three-dimensional model to obtain pipeline leakage position information;
determining a pipeline leakage loss coefficient according to the pipeline leakage identification monitoring result, wherein the pipeline leakage loss coefficient is the pipeline leakage severity;
and performing early warning operation and maintenance management and control on the target pipeline according to the pipeline leakage position information and the pipeline leakage loss coefficient.
2. The method of claim 1, wherein the obtaining an extended multi-angle pipe application image database comprises:
obtaining image data enhancement type information, wherein the image data enhancement type information comprises rotation, overturn, contrast, brightness, chromaticity adjustment, image blurring and scaling;
determining application image conversion parameters according to the image data enhancement type information;
and carrying out data amplification output on the multi-angle pipeline application image database based on the application image conversion parameters to obtain the extended multi-angle pipeline application image database.
3. The method of claim 2, wherein the obtaining a conduit heat distribution profile comprises:
preprocessing the infrared thermal image information to obtain standard infrared thermal image information;
obtaining pipeline infrared heat distribution information according to the standard infrared heat image information;
extracting the characteristics of the infrared heat distribution information of the pipeline to obtain infrared heat image characteristic information;
and determining the pipeline heat distribution characteristic based on the infrared thermal image characteristic information.
4. An identification monitoring system for a pipe leak, the system comprising:
the visual detection module is used for monitoring the target pipeline in real time through the visual detection device to obtain a multi-angle pipeline application image information set;
the semantic segmentation module is used for carrying out semantic segmentation on the multi-angle pipeline application image information set to obtain a plurality of pipeline feature semantic segmentation results;
the application distribution analysis module is used for carrying out application distribution analysis based on the plurality of pipeline feature semantic segmentation results, carrying out region distribution proportion calculation on the image semantic segmentation results, and obtaining pipeline application distribution proportion, wherein the region distribution proportion comprises pipeline region area, contact medium region area and leakage liquid region area;
the application calculation comparison module is used for obtaining a pipeline application standard, calculating and comparing based on the pipeline application distribution proportion and the pipeline application standard to obtain pipeline application leakage monitoring information, wherein the pipeline application standard is a pipeline application safety structure area distribution standard;
the detection sensing network determining module is used for dividing the distribution positions, the intervals and the directions of the sensors according to the pipeline distribution environment structure to determine a distributed detection sensing network;
the sensing network detection module is used for detecting the target pipeline based on the distributed detection sensing network to obtain pipeline leakage characteristic monitoring information;
the identifying and monitoring result generating module is used for generating a pipeline leakage identifying and monitoring result based on the pipeline application leakage monitoring information and the pipeline leakage characteristic monitoring information, wherein the pipeline leakage identifying and monitoring result comprises a pipeline leakage identifying result, a leakage area and a leakage degree;
the sensing network detection module comprises:
the detection sensing network setting unit is used for setting the distributed detection sensing network, and the distributed detection sensing network comprises an infrared sensor, a stress sensor and a vibration sensor;
the signal detection acquisition unit is used for respectively acquiring infrared thermal image information, stress sensing signals and vibration sensing signals based on the distributed detection sensing network;
the signal analysis unit is used for analyzing the infrared thermal image information, the stress sensing signal and the vibration sensing signal to respectively obtain pipeline heat distribution characteristics, stress change characteristics and pipeline vibration characteristics;
the characteristic fusion unit is used for carrying out characteristic fusion on the heat distribution characteristic, the stress variation characteristic and the pipeline vibration characteristic of the pipeline to generate the pipeline leakage characteristic monitoring information;
the semantic segmentation module comprises:
the application image database acquisition unit is used for acquiring a multi-angle pipeline application image database through a data mining technology;
the data enhancement unit is used for enhancing the data of the multi-angle pipeline application image database to obtain an expanded multi-angle pipeline application image database;
the semantic segmentation training unit is used for taking the extended multi-angle pipeline application image database as training sample data, and carrying out semantic segmentation training on the training sample data by using a full convolution neural network structure to obtain a pipeline semantic segmentation model;
the semantic segmentation result output unit is used for carrying out semantic segmentation on the multi-angle pipeline application image information set based on the pipeline semantic segmentation model to obtain a model output result, wherein the model output result comprises a plurality of pipeline characteristic semantic segmentation results;
the semantic segmentation training unit comprises:
the pipeline image segmentation unit is used for carrying out pipeline image segmentation on the image information in the extended multi-angle pipeline application image database to obtain a plurality of pipeline application image segmentation result sets;
the encoder and decoder constructing unit is used for constructing a network encoder and a network decoder based on the full convolution neural network structure;
the data set dividing unit is used for dividing the extended multi-angle pipeline application image database and the plurality of pipeline application image segmentation result sets to obtain a data training set, a data verification set and a data test set;
the model supervision and training unit is used for performing supervision and training on the network encoder and the network decoder by adopting the data training set, verifying and testing the encoder and the decoder by adopting the data verification set and the data testing set until the model accuracy meets the preset requirement, and obtaining the pipeline semantic segmentation model;
the visual modeling unit is used for performing visual modeling on the target pipeline to obtain a three-dimensional model of the target pipeline;
the leakage position positioning unit is used for positioning the leakage position based on the pipeline leakage identification monitoring result and the target pipeline three-dimensional model to obtain pipeline leakage position information;
the leakage loss coefficient determining unit is used for determining a pipeline leakage loss coefficient according to the pipeline leakage identification monitoring result, wherein the pipeline leakage loss coefficient is the pipeline leakage severity;
and the early warning operation and maintenance control unit is used for carrying out early warning operation and maintenance control on the target pipeline according to the pipeline leakage position information and the pipeline leakage loss coefficient.
5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 3 when the computer program is executed.
6. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310512089.9A CN116228770B (en) | 2023-05-09 | 2023-05-09 | Method and system for identifying and monitoring pipeline leakage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310512089.9A CN116228770B (en) | 2023-05-09 | 2023-05-09 | Method and system for identifying and monitoring pipeline leakage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116228770A CN116228770A (en) | 2023-06-06 |
| CN116228770B true CN116228770B (en) | 2023-09-01 |
Family
ID=86569932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310512089.9A Active CN116228770B (en) | 2023-05-09 | 2023-05-09 | Method and system for identifying and monitoring pipeline leakage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116228770B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117523501B (en) * | 2024-01-04 | 2024-03-15 | 四川省铁路建设有限公司 | Control method and system for pipeline inspection robot |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN209325429U (en) * | 2019-01-22 | 2019-08-30 | 新疆美特智能安全工程股份有限公司 | A kind of oil-gas pipeline leakage positioning system based on optical fiber |
| CN111141460A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN111536429A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Decision fusion-based oil and gas pipeline early warning system and method |
| CN114509214A (en) * | 2022-02-14 | 2022-05-17 | 深圳市玄羽科技有限公司 | Monitoring system and method integrating multiple sensors |
| CN114581440A (en) * | 2022-05-05 | 2022-06-03 | 中用科技有限公司 | Method for rapidly positioning leakage point based on image recognition |
| CN114636113A (en) * | 2022-02-22 | 2022-06-17 | 中国特种设备检测研究院 | Oil depot pipeline leakage detection method |
| CN114998366A (en) * | 2022-05-24 | 2022-09-02 | 苏州微清医疗器械有限公司 | Method and system for segmenting and integrating eyeground sugar net image focus |
| CN115239725A (en) * | 2022-09-22 | 2022-10-25 | 张家港大裕橡胶制品有限公司 | Visual monitoring method and system for rubber dipping coating of rubber glove |
| CN115546112A (en) * | 2022-09-14 | 2022-12-30 | 国能神皖池州发电有限责任公司 | Detection method and device for pipeline steam leakage, electronic equipment and storage medium |
| CN115751203A (en) * | 2022-12-05 | 2023-03-07 | 南通中油燃气有限责任公司 | Natural gas pipeline leakage monitoring system based on thermal infrared imager |
| CN115823508A (en) * | 2022-12-21 | 2023-03-21 | 辽宁石油化工大学 | Air-ground integrated pipe network safety monitoring method and system |
| CN116007755A (en) * | 2022-11-24 | 2023-04-25 | 大唐珲春发电厂 | Cable safety monitoring and early warning method and system based on infrared imaging technology |
| CN116052061A (en) * | 2023-02-21 | 2023-05-02 | 嘉洋智慧安全科技(北京)股份有限公司 | Event monitoring method, event monitoring device, electronic equipment and storage medium |
-
2023
- 2023-05-09 CN CN202310512089.9A patent/CN116228770B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN209325429U (en) * | 2019-01-22 | 2019-08-30 | 新疆美特智能安全工程股份有限公司 | A kind of oil-gas pipeline leakage positioning system based on optical fiber |
| CN111141460A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN111536429A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Decision fusion-based oil and gas pipeline early warning system and method |
| CN114509214A (en) * | 2022-02-14 | 2022-05-17 | 深圳市玄羽科技有限公司 | Monitoring system and method integrating multiple sensors |
| CN114636113A (en) * | 2022-02-22 | 2022-06-17 | 中国特种设备检测研究院 | Oil depot pipeline leakage detection method |
| CN114581440A (en) * | 2022-05-05 | 2022-06-03 | 中用科技有限公司 | Method for rapidly positioning leakage point based on image recognition |
| CN114998366A (en) * | 2022-05-24 | 2022-09-02 | 苏州微清医疗器械有限公司 | Method and system for segmenting and integrating eyeground sugar net image focus |
| CN115546112A (en) * | 2022-09-14 | 2022-12-30 | 国能神皖池州发电有限责任公司 | Detection method and device for pipeline steam leakage, electronic equipment and storage medium |
| CN115239725A (en) * | 2022-09-22 | 2022-10-25 | 张家港大裕橡胶制品有限公司 | Visual monitoring method and system for rubber dipping coating of rubber glove |
| CN116007755A (en) * | 2022-11-24 | 2023-04-25 | 大唐珲春发电厂 | Cable safety monitoring and early warning method and system based on infrared imaging technology |
| CN115751203A (en) * | 2022-12-05 | 2023-03-07 | 南通中油燃气有限责任公司 | Natural gas pipeline leakage monitoring system based on thermal infrared imager |
| CN115823508A (en) * | 2022-12-21 | 2023-03-21 | 辽宁石油化工大学 | Air-ground integrated pipe network safety monitoring method and system |
| CN116052061A (en) * | 2023-02-21 | 2023-05-02 | 嘉洋智慧安全科技(北京)股份有限公司 | Event monitoring method, event monitoring device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116228770A (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kumar et al. | Deep learning–based automated detection of sewer defects in CCTV videos | |
| CN116228770B (en) | Method and system for identifying and monitoring pipeline leakage | |
| Zhou et al. | A pipeline leak detection and localization approach based on ensemble TL1DCNN | |
| Pasupuleti et al. | Air quality prediction of data log by machine learning | |
| CN111275333B (en) | Pollution data processing method and device | |
| WO2021034910A1 (en) | System and method for cyber-physical inspection and monitoring of nonmetalic structures | |
| CN109115877B (en) | Curvature modal damage identification method based on DIC technology | |
| Hallaji et al. | Predictive maintenance of pumps in civil infrastructure: State-of-the-art, challenges and future directions | |
| CN111814740B (en) | Pointer instrument reading identification method, device, computer equipment and storage medium | |
| Xu et al. | A residual strain energy based damage localisation method for offshore platforms under environmental variations | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN114511243A (en) | Method and system for dynamically evaluating fire risk based on Internet of things monitoring | |
| CN115751203A (en) | Natural gas pipeline leakage monitoring system based on thermal infrared imager | |
| CN113124328A (en) | Natural gas pipeline leakage detection method and system | |
| Guerra et al. | A data-driven approach for condition monitoring of reciprocating compressor valves | |
| CN114387332B (en) | Pipeline thickness measuring method and device | |
| CN114926707A (en) | Pipeline defect identification method, processor and pipeline defect identification device | |
| CN113295212B (en) | Landslide overall stability safety early warning system applying multi-monitoring point synergistic effect | |
| CN114034334A (en) | Method for identifying pollution source and flow of karst pipeline | |
| Giglioni et al. | Deep autoencoders for unsupervised damage detection with application to the Z24 benchmark bridge | |
| CN111828845A (en) | Automatic pipeline leakage detection method based on artificial intelligence | |
| Loboda et al. | A generalized fault classification for gas turbine diagnostics at steady states and transients | |
| Kothari et al. | An efficient scheme for water leakage detection using support vector machines (SVM)-Zig | |
| CN110321770B (en) | Pipeline monitoring method, device, equipment and storage medium | |
| Mysiuk et al. | Detection of Surface Defects Inside Concrete Pipelines Using Trained Model on JetRacer Kit |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230919 Address after: 300452 No. 26, Bohai 33rd Road, Lingang Economic Zone, Binhai New Area, Tianjin Patentee after: HELI TECH ENERGY Co.,Ltd. Address before: 300000 902-b, building 5, No. 158, Xisan Road, Tianjin pilot free trade zone (Airport Economic Zone), Binhai New Area, Tianjin (trust No. 652 of Tianjin xinzhijia business secretary Co., Ltd.) Patentee before: Deep blue (Tianjin) Intelligent Manufacturing Co.,Ltd. |