CN111091149B - Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion - Google Patents
Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion Download PDFInfo
- Publication number
- CN111091149B CN111091149B CN201911290691.2A CN201911290691A CN111091149B CN 111091149 B CN111091149 B CN 111091149B CN 201911290691 A CN201911290691 A CN 201911290691A CN 111091149 B CN111091149 B CN 111091149B
- Authority
- CN
- China
- Prior art keywords
- data
- gas leakage
- source
- fusion
- information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a gas leakage detection method, system, equipment, terminal and computer storage medium based on multi-source data fusion, the method comprises: acquiring a data source of a preset service system in gas operation; performing multi-source fusion on the data source of the preset business system in three modes of asset ID, equipment ID and geographic position; preprocessing the multi-source fusion data, and judging gas leakage by adopting a leakage judgment model based on a neural network; the application solves the problem that the data sources of the gas operation multi-service system in the prior art are mutually independent through multi-source data fusion, deep analysis, accurate modeling and reasonable and visual comprehensive display for preventing and predicting gas leakage, and realizes predictive detection and maintenance of gas leakage.
Description
Technical Field
The application relates to the technical field of gas leakage detection, in particular to a gas leakage detection method and system based on multi-source data fusion.
Background
Traditional gas operation is fully divided according to work responsibility and properties, each part of work is implemented by different organizations or departments respectively, even each part of work is supported by an independent information system to form an information island, effective cooperation and communication are difficult, and under the background of a big data era, data collection and collection are required, so that the value of the data can be fused and mined deeply, and the actual work efficiency is guided and optimized.
The gas leakage detection depends on a methane or ethane detection instrument to discover and early warn in time after gas leakage occurs, and the discovery means is realized afterwards. And the occurrence of gas leakage events cannot be well prevented and reduced by depending on massive manual routing inspection. In the past, all departments effectively divide labor and each takes their own role in the operation process, and basically can smoothly meet the requirements of safe production and safe operation, but under the current background of the smart city era based on big data, higher requirements are put forward for urban gas production and operation, and the data value can be more effectively exerted only by effectively fusing data sources of various business systems.
Therefore, a gas leakage detection method, a gas leakage detection system, a gas leakage detection terminal and a computer storage medium based on multi-source data fusion are needed, so that the multi-source data of the gas can be fused, and the predictive detection and maintenance of the gas leakage can be realized.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a gas leakage detection method, a gas leakage detection system, a gas leakage detection terminal and a computer storage medium based on multi-source data fusion, and solves the problems that the data sources of a gas operation multi-service system in the prior art are mutually independent and the like.
In order to solve the technical problem, the application provides a gas leakage detection method based on multi-source data fusion, which comprises the following steps:
acquiring a data source of a preset service system in gas operation;
performing multi-source fusion on the data source of the preset business system in three modes of asset ID, equipment ID and geographic position;
and preprocessing the multi-source fusion data, and judging gas leakage by adopting a leakage judgment model based on a neural network.
Optionally, the data source of the preset service system in the gas operation includes:
the system comprises SCADA system equipment information and production operation information, asset information of an asset management system, GIS system map information, anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information, potentiostat detection information, emergency operation information of an emergency operation system, welding information and leakage detection information of a leakage detection system.
Optionally, the multi-source fusion of the data source of the preset service system through asset ID, device ID and geographic location includes:
associating the production operation information of the SCADA system with the anticorrosive layer detection information, the pipe body anticorrosive detection information, the anticorrosive layer insulation resistance detection information, the stray current detection information, the cathode protection detection information and the drainage device detection information of the anticorrosive detection system by using an equipment identifier UUID; associating the device information of the SCADA system and the asset information of the asset management system by an asset ID; associating the equipment information of the SCADA system with the environment detection information of the anticorrosion detection system and the leakage detection information of the leakage detection system through the longitude and latitude positions of the equipment; the emergency operation information needs to consider the equipment identification and the equipment longitude and latitude position at the same time.
Optionally, the preprocessing is performed on the multi-source fusion data, and a leakage judgment model based on a neural network is adopted to perform gas leakage judgment, including:
the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the drainage current average value in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form.
Optionally, the preprocessing is performed on the multi-source fusion data, and a leakage judgment model based on a neural network is adopted to perform gas leakage judgment, including:
designing a leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are 18-dimensional characteristic vectors, the characteristic vectors are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
and (3) training a leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (4) judging the leakage of the leakage judgment model, preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the leakage judgment model after training, and outputting a result, namely judging the gas leakage.
Optionally, the method further includes: and displaying the multi-source fusion data on a GIS platform in sequence.
In a second aspect, the present application further provides a gas leakage detection system based on multi-source data fusion, including:
the system comprises an acquisition unit, a data processing unit and a data processing unit, wherein the acquisition unit is configured to acquire a data source of a preset service system in gas operation;
the multi-source fusion unit is configured for performing multi-source fusion on the data source of the preset business system in three modes of asset ID, equipment ID and geographic position;
and the judging unit is configured for preprocessing the multi-source fusion data and judging the gas leakage by adopting a leakage judging model based on a neural network.
Optionally, the data source acquired by the acquiring unit includes:
the system comprises SCADA system equipment information and production operation information, asset information of an asset management system, GIS system map information, anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information, potentiostat detection information, emergency operation information of an emergency operation system, welding information and leakage detection information of a leakage detection system.
Optionally, the multi-source fusion unit specifically includes:
associating the production operation information of the SCADA system with the anticorrosive layer detection information, the pipe body anticorrosive detection information, the anticorrosive layer insulation resistance detection information, the stray current detection information, the cathode protection detection information and the drainage device detection information of the anticorrosive detection system by using an equipment identifier UUID; associating the device information of the SCADA system and the asset information of the asset management system by an asset ID; associating the equipment information of the SCADA system with the environment detection information of the anticorrosion detection system and the leakage detection information of the leakage detection system through the longitude and latitude positions of the equipment; the emergency operation information needs to consider the equipment identification and the equipment longitude and latitude position at the same time.
Optionally, the determining unit specifically includes:
the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the drainage current average value in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form.
Optionally, the determining unit specifically includes:
designing a leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are 18-dimensional characteristic vectors, the characteristic vectors are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
and (3) training a leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (4) judging the leakage of the leakage judgment model, preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the leakage judgment model after training, and outputting a result, namely judging the gas leakage.
Optionally, the system further includes:
and the display unit is configured for sequentially displaying the multi-source fusion data on a GIS platform.
In a third aspect, the present application provides a terminal, comprising:
a processor, a memory, wherein,
the memory is used for storing a computer program which,
the processor is used for calling and running the computer program from the memory so as to make the terminal execute the method of the terminal.
In a fourth aspect, the present application provides a computer storage medium having instructions stored thereon, which when executed on a computer, cause the computer to perform the method of the above aspects.
The application solves the problem that the data sources of the gas operation multi-service system in the prior art are mutually independent through multi-source data fusion, deep analysis, accurate modeling and reasonable and visual comprehensive display for preventing and predicting gas leakage, and realizes predictive detection and maintenance of gas leakage.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a gas leakage detection method based on multi-source data fusion provided in an embodiment of the present application;
fig. 2 is a schematic diagram of a specific manner of performing multi-source fusion on a data source provided in an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating an environment detection and device association method according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a leak detection and device association provided by an embodiment of the present application;
FIG. 5 is a schematic view of a gas leakage determination model provided in an embodiment of the present application;
FIG. 6 is a hidden layer activation function graph of a gas leakage determination model provided in an embodiment of the present application;
FIG. 7 is a graph of an output layer function of a gas leakage determination model provided in an embodiment of the present application;
fig. 8 is a detailed model structure diagram of a gas leakage determination model provided in an embodiment of the present application;
FIG. 9 is a comprehensive view of relevant data for gas leakage detection based on multi-source data fusion provided by an embodiment of the present application;
FIG. 10 is a grid-shaped regional risk assessment of a gas leakage detection method based on multi-source data fusion provided by an embodiment of the present application;
FIG. 11 is a schematic structural diagram of a gas leakage detection system based on multi-source data fusion provided in an embodiment of the present application;
fig. 12 is a schematic structural diagram of a gas leakage detection terminal based on multi-source data fusion provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a gas leakage detection method based on multi-source data fusion according to an embodiment of the present application, where the method 100 includes:
s101, acquiring a data source of a preset service system in gas operation;
s102, performing multi-source fusion on the data source of the preset business system in three modes of asset ID, equipment ID and geographic position;
and S103, preprocessing the multi-source fusion data, and judging gas leakage by adopting a leakage judgment model based on a neural network.
Based on the foregoing embodiment, as an optional embodiment, the step S101 of acquiring a data source of a preset service system in gas operation includes:
the system comprises SCADA system equipment information and production operation information, asset information of an asset management system, GIS system map information, anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information, potentiostat detection information, emergency operation information of an emergency operation system, welding information and leakage detection information of a leakage detection system.
Specifically, the data source mainly relates to the data of the following 6 systems:
1) equipment information and production operation information of SCADA system
TABLE 1-1 device information
| Device ID | Character string |
| Asset ID | Character string |
| Device name | Character string |
| Longitude of origin | Floating point type |
| Starting point latitude | Floating point type |
| End point longitude | Floating point type |
| Terminal latitude | Floating point type |
TABLE 1-2 apparatus
2) Asset management system
TABLE 2 asset information for asset management systems
| Asset ID | Character string |
| Asset name | Character string |
| Manufacturer of the product | Character string |
| Model number | Character string |
| Batches of | Character string |
| Time of purchase | Time |
| Number of | Shaping machine |
| Design pressure | Floating point type |
| Length of | Floating point type |
| Material of | Shaping machine |
| Outer diameter | Floating point type |
| Inner diameter | Floating point type |
3) Map information of GIS system
Map information
4) The system comprises anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information and potentiostat detection information.
TABLE 4-1 Environment monitoring information
TABLE 4-2 anticorrosive coating inspection information
| Device ID | Character string |
| Number of damaged spots | Shaping machine |
| Direction of damage point | Floating point type |
| Type of detecting instrument | Character string |
| Detection unit | Character string |
| Time of detection | Time |
TABLE 4-3 tube corrosion detection information
| Device ID | Character string |
| Execution criteria | Character string |
| Color of corrosion products | Shaping machine |
| Corrosion product structure | Shaping machine |
| Compactness of corrosion products | Shaping machine |
| Type of corrosion | Shaping machine |
| Number of corrosion sites | Shaping machine |
| Maximum pit depth | Floating point type |
| Maximum etch pit diameter | Floating point type |
| Cause of corrosion | Shaping machine |
| Detection unit | Character string |
| Time of detection | Time |
TABLE 4-4 anticorrosive layer insulation resistance detection information
TABLE 4-5 stray Current detection information
| Device ID | Character string |
| Execution criteria | Shaping machine |
| Reference type | Floating point type |
| Monitoring duration | Floating point type |
| Data acquisition Interval | Floating point type |
| Type of interference | Shaping machine |
| Rating of evaluation | Shaping machine |
| Detection method | Shaping machine |
| Detection unit | Character string |
| Time of detection | Time |
Tables 4-6 cathodic protection test information
| Device ID | Character string |
| Wiring mode | Shaping machine |
| Execution criteria | Shaping machine |
| Cathodic protection mode | Shaping machine |
| Rate of protection | Floating point type |
| Rate of operation | Floating point type |
| Detection method | Shaping machine |
| Detection unit | Character string |
| Time of detection | Time |
Tables 4-7 drainage device test information
TABLE 4-8 potentiostat detection information
| Test sequence number | Character string |
| Longitude (G) | Floating point type |
| Latitude | Floating point type |
| Potential value | Floating point type |
| Detection unit | Character string |
| Time of detection | Time |
5) Emergency operation information and welding information table 5-1 of emergency operation system
| Leaking device ID | Character string |
| Longitude of ground leakage point | Floating point type |
| Latitude of ground leakage point | Floating point type |
| Leakage site | Character string |
| Cause of leakage | Shaping machine |
| Treatment method | Character string |
| Detection unit | Character string |
| Time of detection | Time |
TABLE 5-2 weld information
| Leaking device ID | Character string |
| Kind of operation | Shaping machine |
| Welder ID | Character string |
| Working time | Time |
| Quality of welding | Shaping machine |
6) Leak detection system
TABLE 6 leak detection information for leak detection systems
| Leak test sequence number | Character string |
| Longitude (G) | Floating point type |
| Latitude | Floating point type |
| Wind direction | Floating point type |
| Wind speed | Floating point type |
| Concentration of methane | Floating point type |
| Ethane concentration | Floating point type |
| Speed of movement | Floating pointModel (III) |
| Direction of movement | Floating point type |
Based on the above embodiment, as an optional embodiment, the step S102 performs multi-source fusion on the data source of the preset business system in three ways, namely, an asset ID, an equipment ID, and a geographic location, and includes:
associating the production operation information of the SCADA system with the anticorrosive layer detection information, the pipe body anticorrosive detection information, the anticorrosive layer insulation resistance detection information, the stray current detection information, the cathode protection detection information and the drainage device detection information of the anticorrosive detection system by using an equipment identifier UUID; associating the device information of the SCADA system and the asset information of the asset management system by an asset ID; associating the equipment information of the SCADA system with the environment detection information of the anticorrosion detection system and the leakage detection information of the leakage detection system through the longitude and latitude positions of the equipment; the emergency operation information needs to consider the equipment identification and the equipment longitude and latitude position at the same time.
Specifically, as shown in fig. 2, fig. 2 is a schematic diagram of a specific manner of performing multi-source fusion on a data source provided in the embodiment of the present application, and as can be seen from fig. 2, all data are associated with operating equipment, and mainly include pipelines, valves, and the like. The SCADA system information and most of anticorrosion detection information are associated by an equipment identifier UUID; the device information and the asset information are associated by an asset ID; the environment detection, the leakage detection and the small part of anticorrosion detection are associated with the equipment information through longitude and latitude position information; the emergency operation information needs to consider the equipment identification and the longitude and latitude at the same time.
It should be noted that, during emergency operation, the specific device is involved, and needs to be associated with the device identification information; and the surrounding situations of the emergency disposal position, such as geological environment situations, leakage detection situations and the like, are also involved, so that the equipment identification and the longitude and latitude position need to be considered simultaneously.
As shown in fig. 3, the environment detection mainly uses a detection point as a circle center, and associates a range with an apparatus position, where R is a radius; as shown in fig. 4, the leakage detection information is also based on the geographical location information, and the detection coverage (provided by the detection device) can be calculated according to the leakage detection data, and then according to whether the device location information is within the range; the emergency operation information relates to the positioning of the ground leakage point and the positioning of the equipment leakage point, so that the information correlation relates to the geographic position and the equipment information.
In summary, the three ways of asset ID, device ID and geographic location can be used to effectively associate and fuse 6 pieces of system information together, so as to provide a data base for further analysis.
Based on the foregoing embodiment, as an optional embodiment, the step S103 preprocesses the multi-source fusion data, and performs gas leakage determination by using a leakage determination model based on a neural network, including:
the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the drainage current average value in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form.
Specifically, as shown in table 7, the following 14 types of input data are mainly included:
table 7 leak determination model input data
| Material for pipeline | Shaping machine |
| Design pressure | Floating point type |
| Operating pressure | Floating point type |
| Outer diameter | Floating point type |
| Inner diameter | Floating point type |
| Type of soil | Shaping machine |
| Resistivity of soil | Floating point type |
| Stray direct current | Floating point type |
| Alternating stray current | Floating point type |
| Temperature of | Floating point type |
| Insulation resistance value of anticorrosive coating | Floating point type |
| Cathodic protection rate | Floating point type |
| Rate of cathode operation | Floating point type |
| Average value of current drainage | Floating point type |
The data types mainly include integer types and floating point types, wherein the integer types identify categories, and one-hot mode conversion is carried out before input to a vector form.
There are mainly 2 kinds of pipe materials, so the materials are expressed as vectors of 1 × 2 form, and each number represents one material: [10] represents a steel pipe; [01] represents a PE pipe;
there are mainly 4 types of soil, which are expressed as vectors in the form of 1 × 4, and each number represents one material: [1000] represents sandy soil; [0100] representing loam; [0010] representing clay; [0001] represents others;
the other data are represented in simple numerical form, constituting the input data in the form of a 1 × 18 vector, as shown in table 8:
table 8 input data vector form
Based on the foregoing embodiment, as an optional embodiment, the step S103 preprocesses the multi-source fusion data, and performs gas leakage determination by using a leakage determination model based on a neural network, including:
designing a leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are 18-dimensional characteristic vectors, the characteristic vectors are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
and (3) training a leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (4) judging the leakage of the leakage judgment model, preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the leakage judgment model after training, and outputting a result, namely judging the gas leakage.
Specifically, as shown in fig. 5, the model input data is the preprocessed 18-dimensional feature vector, which belongs to fewer feature dimensions compared with other data forms (such as graphics, natural language, and the like), and then passes through the multilayer fully-connected hidden layer, the final output layer is a single neuron structure, and the model output data is used for predicting the possibility that the pipeline may be corroded: in the range of 0-100%, with corrosion detection and leakage detection as reference data. If severe corrosion occurs, the likelihood of a gas leak detection occurring within a certain time is very high, and preventive detection and maintenance need to be scheduled in order to achieve a reduction in the occurrence of leak events.
The model mainly adopts a deep learning model based on a neural network, and the task is essentially classified into two categories because the task is mainly to judge the possibility of corrosion according to the conditions of a pipe body, operation, environment and the like.
The hidden layer is of a multi-layer full-connection structure, a plurality of short structures are added for considering low-level features and high-level features, the low-level features are directly communicated to the output layer, and the output layer integrates the output features of the hidden layers to judge corrosion risks. Since the input is of a numerical type, a network does not need to be particularly deep, and according to practical project experience, the hidden layer depth can be considered to be 4-10 layers, and the hidden layer width can be considered to be 36-48. The hidden layer activation function adopts a TANH function to increase the nonlinear characteristics and the fitting capability of the model, and the TANH function is as follows:
fig. 6 is a graph of the hidden layer activation function of the gas leakage determination model, and as shown in fig. 6, the y-range of the function TANH is (-1, +1), and the x-range is (+ ∞, - ∞), which is an S-type saturation function.
The activation function of a single neuron of an output layer is SIGMOID, and the formula is as follows:
fig. 7 is a graph of an output layer function of the gas leakage determination model, and as shown in fig. 7, the y-range of the function SIGMOID is (0, 1), and the x-range is (+ ∞, - ∞). The output in the model represents 0% -100% corrosion risk degree, 0 (0%) represents that the predicted corrosion risk is extremely low, and 1 (100%) represents that the predicted corrosion risk is extremely high. This function is also an S-shaped saturation function.
Fig. 8 is a detailed model of the gas leakage determination model, and as shown in fig. 8, the number of hidden layers of the gas leakage determination model is 4, and the width of the hidden layer is 32, both of which can be adjusted according to actual data and business conditions.
In addition, historical data before 2019 and 7 months are adopted in the task model training, new data after 2019 and 7 months are adopted in verification data, and meanwhile, the judgment result and the manual confirmation result of the existing system are compared for evaluation so as to verify the performance of the model. Model performance can be continuously optimized through both data accumulation and model algorithm adjustment.
Based on the foregoing embodiment, as an optional embodiment, the method 100 further includes: and displaying the multi-source fusion data on a GIS platform in sequence.
Specifically, the gas leakage detection relates to various data types and mass data, and the data are displayed as a unified whole, so that management personnel can conveniently master and arrange the whole situation, and follow-up derivative services can be further developed. The leakage detection big data display mainly relates to the following data types:
1) map data: mainly refers to geographical data such as road surfaces, buildings, mountains, water bodies, and the like.
2) And (3) detecting data: mainly gas concentration detection data, soil detection related data, cathodic protection related data and the like
3) Pipe network data: mainly refers to the relevant number of the gas operation pipe network, such as the position of a pipe section, the material of the pipe section, the operation pressure and the like.
4) And (3) analysis results: mainly refers to the leakage risk assessment of the gas pipeline section at present, and other more analysis results may be available in the future.
5) And (3) integrating the regional leakage risk assessment results: regional risks are assessed primarily based on the risk profile of the segment in a region.
The data are sequentially overlapped on the GIS platform according to the sequence, and the complete appearance of the relevant data of the leakage detection can be comprehensively displayed, as shown in figure 9.
The map information layer is provided by a GIS platform, comprises basic geographic information such as streets, buildings and the like, mainly provides reference for users, has reference significance for other dimensional data (such as detection data and pipe network data), does not participate in subsequent analysis, and does not influence analysis results; the detection information layer mainly contains various environmental detection data, so that the detection information layer is further divided into a plurality of sublayers, such as soil detection information, negative protection detection information and gas leakage detection information; the pipe network data layer is based on pipe network data, and comprises basic pipe network information (position, material, size), pipe network operation data (operation pressure and the like), and pipe network detection data (corrosion detection and the like); the analysis result layer is also based on a pipe network, and the pipe network leakage risk condition is evaluated by the analysis method, the environment detection information and the pipe network data; the area analysis layer evaluates the risk level in a certain area on the basis of the leakage risk of the pipe network, the area is generally divided averagely according to a certain size, for example, a designated area is divided according to the size of 1 kilometer x 1 kilometer, the area forms a batch of grids, and then the risk condition of the grid area is determined according to the number of high-risk pipelines in each grid. Thereby forming a grid-shaped regional risk assessment as shown in fig. 10.
Referring to fig. 11, fig. 11 is a schematic structural diagram of a gas leakage detection system based on multi-source data fusion according to an embodiment of the present application, where the system 1100 includes:
an obtaining unit 1101 configured to obtain a data source of a preset service system in gas operation;
the multi-source fusion unit 1102 is configured to perform multi-source fusion on the data source of the preset business system through asset ID, equipment ID and geographic position;
and the judging unit 1103 is configured to preprocess the multi-source fusion data and judge gas leakage by using a leakage judging model based on a neural network.
Based on the foregoing embodiment, as an optional embodiment, the data source acquired by the acquiring unit 1101 includes:
the system comprises SCADA system equipment information and production operation information, asset information of an asset management system, GIS system map information, anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information, potentiostat detection information, emergency operation information of an emergency operation system, welding information and leakage detection information of a leakage detection system.
Based on the foregoing embodiment, as an optional embodiment, the multi-source fusion unit 1102 specifically includes:
associating the production operation information of the SCADA system with the anticorrosive layer detection information, the pipe body anticorrosive detection information, the anticorrosive layer insulation resistance detection information, the stray current detection information, the cathode protection detection information and the drainage device detection information of the anticorrosive detection system by using an equipment identifier UUID; associating the device information of the SCADA system and the asset information of the asset management system by an asset ID; associating the equipment information of the SCADA system with the environment detection information of the anticorrosion detection system and the leakage detection information of the leakage detection system through the longitude and latitude positions of the equipment; the emergency operation information needs to consider the equipment identification and the equipment longitude and latitude position at the same time.
Based on the foregoing embodiment, as an optional embodiment, the determining unit 1103 specifically includes:
the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the drainage current average value in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form.
Based on the foregoing embodiment, as an optional embodiment, the determining unit 1103 specifically includes:
designing a leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are 18-dimensional characteristic vectors, the characteristic vectors are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
and (3) training a leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (4) judging the leakage of the leakage judgment model, preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the leakage judgment model after training, and outputting a result, namely judging the gas leakage.
Based on the foregoing embodiment, as an optional embodiment, the system 1100 further includes:
and the display unit is configured for sequentially displaying the multi-source fusion data on a GIS platform.
Referring to fig. 12, fig. 12 is a schematic structural diagram of a terminal 1200 according to an embodiment of the present disclosure, and the terminal system 300 may be used to execute a gas leakage detection method based on multi-source data fusion according to the embodiment of the present disclosure.
The terminal system 1200 may include: a processor 1201, a memory 1202, and a communication unit 1203. The components communicate via one or more buses, and those skilled in the art will appreciate that the architecture of the servers shown in the figures is not intended to be limiting, and may be a bus architecture, a star architecture, a combination of more or less components than those shown, or a different arrangement of components.
The memory 1202 may be used for storing instructions executed by the processor 1201, and the memory 1202 may be implemented by any type of volatile or non-volatile storage terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The execution instructions in memory 1202, when executed by processor 1201, enable terminal 1200 to perform some or all of the steps in the method embodiments described below.
The processor 1201 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by operating or executing software programs and/or modules stored in the memory 1202 and calling data stored in the memory. The processor may be composed of an Integrated Circuit (IC), for example, a single packaged IC, or a plurality of packaged ICs connected with the same or different functions. For example, the processor 1201 may include only a Central Processing Unit (CPU). In the embodiment of the present invention, the CPU may be a single operation core, or may include multiple operation cores.
A communication unit 1203 is configured to establish a communication channel so that the storage terminal can communicate with other terminals. And receiving user data sent by other terminals or sending the user data to other terminals.
The present application also provides a computer storage medium, wherein the computer storage medium may store a program, and the program may include some or all of the steps in the embodiments provided by the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system provided by the embodiment, the description is relatively simple because the system corresponds to the method provided by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (6)
1. A gas leakage detection method based on multi-source data fusion is characterized by comprising the following steps:
acquiring a data source of a preset service system in gas operation;
and performing multi-source fusion on the data source of the preset service system in three modes of asset ID, equipment ID and geographic position:
preprocessing the multi-source fusion data, and judging gas leakage by adopting a gas leakage judging model based on a neural network: the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the average value of drainage current in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form;
designing a gas leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are multisource fusion data in a 1 x 18 vector form, the multisource fusion data are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
training a gas leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (3) judging the leakage of the gas leakage judging model: preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the trained leakage judgment model, and outputting a result, namely judging the gas leakage;
the gas leakage judgment model is a deep learning model based on a neural network, the number of hidden layers of the gas leakage judgment model is 4-10, the width of the hidden layers is 36-38, the activation function of the hidden layers adopts a TANH function, the activation function of a single neuron of an output layer is SIGMOID, and the output represents 0% -100% corrosion risk degree.
2. The gas leakage detection method based on multi-source data fusion of claim 1, wherein the data source of the preset business system in gas operation comprises:
the system comprises SCADA system equipment information and production operation information, asset information of an asset management system, GIS system map information, anticorrosion detection system environment detection information, anticorrosion layer detection information, pipe anticorrosion detection information, anticorrosion layer insulation resistance detection information, stray current detection information, cathode protection detection information, drainage device detection information, potentiostat detection information, emergency operation information of an emergency operation system, welding information and leakage detection information of a leakage detection system.
3. The gas leakage detection method based on multi-source data fusion of claim 1, further comprising: and displaying the multi-source fusion data on a GIS platform in sequence.
4. The utility model provides a gas leakage detection system based on multisource data fusion which characterized in that includes:
the system comprises an acquisition unit, a data processing unit and a data processing unit, wherein the acquisition unit is configured to acquire a data source of a preset service system in gas operation;
the multi-source fusion unit is configured for performing multi-source fusion on the data source of the preset business system in three modes of asset ID, equipment ID and geographic position;
the judgment unit is configured to preprocess the multi-source fusion data and judge the gas leakage by adopting a leakage judgment model based on a neural network: the design pressure, the operating pressure, the outer diameter, the inner diameter, the soil resistivity, the direct current stray current, the alternating current stray current, the temperature, the anticorrosive layer insulation resistance value, the cathodic protection rate, the cathodic operation rate and the average value of drainage current in the floating point type data are expressed in a simple numerical form, the pipeline data in the integer type data are expressed into a vector in a 1 x 2 form, the soil data in the integer type data are expressed into a vector in a 1 x 4 form, and the multi-source fusion data are combined to form a 1 x 18 vector form;
designing a gas leakage judgment model: the corrosion risk prediction method is characterized by comprising a preset multilayer neural network, wherein input data are multisource fusion data in a 1 x 18 vector form, the multisource fusion data are connected with a hidden layer through the multilayer neural network, and finally an output layer is of a single neuron structure and used for predicting corrosion risk degree;
training a gas leakage judgment model: preprocessing historical data before preset time to serve as a plurality of training sample data, and inputting the training sample data into the preset multilayer neural network to obtain a leakage judgment model after training is completed;
and (3) judging the leakage of the gas leakage judging model: preprocessing new data after preset time to be used as test sample data, inputting the test sample data into the trained leakage judgment model, and outputting a result, namely judging the gas leakage;
the gas leakage judgment model is a deep learning model based on a neural network, the number of hidden layers of the gas leakage judgment model is 4-10, the width of the hidden layers is 36-38, the activation function of the hidden layers adopts a TANH function, the activation function of a single neuron of an output layer is SIGMOID, and the output represents 0% -100% corrosion risk degree.
5. A terminal, comprising:
a processor;
a memory for storing instructions for execution by the processor;
wherein the processor is configured to perform the method of any one of claims 1-3.
6. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911290691.2A CN111091149B (en) | 2019-12-16 | 2019-12-16 | Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911290691.2A CN111091149B (en) | 2019-12-16 | 2019-12-16 | Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111091149A CN111091149A (en) | 2020-05-01 |
| CN111091149B true CN111091149B (en) | 2021-07-30 |
Family
ID=70395732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911290691.2A Active CN111091149B (en) | 2019-12-16 | 2019-12-16 | Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091149B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115512520B (en) * | 2022-11-21 | 2023-04-07 | 成都秦川物联网科技股份有限公司 | Gas use safety early warning method based on intelligent gas and Internet of things system |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101539241B (en) * | 2009-05-07 | 2012-07-04 | 北京航空航天大学 | Hierarchical multi-source data fusion method for pipeline linkage monitoring network |
| US9091613B2 (en) * | 2012-06-27 | 2015-07-28 | General Monitors, Inc. | Multi-spectral ultrasonic gas leak detector |
| CN106676541B (en) * | 2017-01-09 | 2019-02-01 | 国网浙江省电力公司电力科学研究院 | A kind of metallic conduit stray current corrosion means of defence |
| CN109595464A (en) * | 2017-10-03 | 2019-04-09 | 香港中华煤气有限公司 | Gas leakage detection system |
| CN207676463U (en) * | 2017-12-29 | 2018-07-31 | 欧莱克（唐山）科技有限公司 | A kind of gas leakage detecting system |
| CN109186895B (en) * | 2018-08-08 | 2020-10-20 | 太原理工大学 | Distributed passive gas transmission pipeline leakage multi-parameter fusion early warning detection device and method |
| CN109255490B (en) * | 2018-09-28 | 2022-03-22 | 西安建筑科技大学 | KPCA-BAS-GRNN-based buried pipeline external corrosion rate prediction method |
| CN110107815B (en) * | 2018-11-08 | 2021-04-06 | 清华大学合肥公共安全研究院 | Gas pipeline leakage detection method and device |
| CN109917720A (en) * | 2019-04-04 | 2019-06-21 | 中国石油化工股份有限公司 | In-service steel pipe stray electrical current prison detection and cathodic protection power control and method |
| CN110242865B (en) * | 2019-07-09 | 2020-05-08 | 北京讯腾智慧科技股份有限公司 | Gas leakage detection and judgment method and system easy for continuous optimization |
| CN110398320B (en) * | 2019-07-09 | 2020-11-20 | 北京讯腾智慧科技股份有限公司 | Gas leakage detection positioning method and system easy for continuous optimization |
-
2019
- 2019-12-16 CN CN201911290691.2A patent/CN111091149B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111091149A (en) | 2020-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ji et al. | Probabilistic physical modelling of corroded cast iron pipes for lifetime prediction | |
| Behzadian et al. | Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks | |
| WO2015129031A1 (en) | Water-leak detection system and water-leak detection method | |
| Babaei et al. | Risk assessment of agricultural water conveyance and delivery systems by fuzzy fault tree analysis method | |
| CN107766415B (en) | The inefficient industrial land method for quickly identifying in cities and towns based on electricity consumption data | |
| CN111612301A (en) | Weight self-adjustment-based gas buried pipeline leakage risk assessment method and device | |
| El-Abbasy et al. | Integrated performance assessment model for water distribution networks | |
| CN115899595A (en) | Intelligent gas pipeline corrosion prevention optimization method, internet of things system and storage medium | |
| Dawood et al. | Pressure data-driven model for failure prediction of PVC pipelines | |
| CN111091149B (en) | Gas leakage detection method, system, terminal and computer storage medium based on multi-source data fusion | |
| Martínez García et al. | Pressure-based analysis of water main failures in California | |
| Dawood et al. | Ensemble intelligent systems for predicting water network condition index | |
| El-Abbasy et al. | Simulation-based deterioration patterns of water pipelines | |
| Li et al. | Review on intelligent pipeline technologies: A life cycle perspective | |
| CN116090322A (en) | Intelligent decision visualization system for pipeline integrity | |
| Chen et al. | Optimizing inspection routes in pipeline networks | |
| Kizilöz | Prediction of daily failure rate using the serial triple diagram model and artificial neural network | |
| CN116778328A (en) | Gas pipeline high-consequence area identification system and method based on remote sensing image | |
| Bogárdi et al. | A Spatial probabilistic model of pipeline failures | |
| CN114723218B (en) | Oil and gas pipeline geological disaster evaluation method based on information quantity-neural network | |
| Jian et al. | Anomaly detection and classification in water distribution networks integrated with hourly nodal water demand forecasting models and feature extraction technique | |
| Fan et al. | Machine learning-assisted optimal schedule of underground water pipe inspection | |
| Zamenian et al. | Systematic approach for asset management of urban water pipeline infrastructure systems | |
| CN110705018B (en) | Water supply pipeline pipe burst positioning method based on hot line work order and pipeline health assessment | |
| Bogo et al. | Statistical parametric and non-parametric control charts for monitoring residential water consumption |
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 |