Gas pipe network risk assessment system and method based on big data

Abstract

The invention discloses a gas pipe network risk assessment system and method based on big data, and belongs to the technical field of gas pipe network risk assessment, and the method comprises the steps: obtaining a magnetic flux leakage signal of a gas pipe network through a magnetic flux leakage detector, and converting the magnetic flux leakage signal into a voltage signal; the processed data are subjected to visualization processing, magnetic flux leakage detection data are generated, and the magnetic flux leakage detection data comprise a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn according to data acquired by the magnetic flux leakage detector on the surface of the gas pipe network, and the defect image is converted into a grayscale image through a mapping relation; dividing the magnetic flux leakage detection data of the gas pipe network into normal data and defect area data; and querying an alarm threshold value from a preset database, and if the jump value reaches the alarm threshold value, generating an alarm instruction and executing the alarm instruction. According to the invention, when an oil and gas leakage accident occurs, fault early warning can be timely sent out, so that an emergency plan can be rapidly started, and accident handling and rescue work can be carried out.

Description

Technical Field

[0001] The present application relates to the technical field of gas pipeline network risk assessment, and in particular to a gas pipeline network risk assessment system and method based on big data. Background Art

[0002] As one of the most important energy sources today, oil and gas resources are transported by road, rail, water, air and pipeline. Pipeline transportation is the most important mode of transportation for oil and gas resources. With the development of oil fields in my country, the status of oil and gas pipeline transportation in the development of my country's national economy has become increasingly prominent. In recent years, my country has made remarkable achievements in the construction of oil and gas pipelines and formed a relatively complete oil and gas pipeline transportation network. The diameter of oil and gas pipelines has been continuously increased, the transportation capacity has been greatly improved, and the transportation distance has also increased rapidly.

[0003] However, as the gas transmission time increases, oil and gas pipelines are prone to damage and defects due to aging, corrosion, wear and tear, etc. If these damages and defects are not discovered and repaired in time, they may lead to oil and gas leakage accidents. Oil and gas leakage accidents will not only affect the normal production of oil fields, but also cause serious pollution to the ground environment. Although my country has established a relatively complete oil and gas pipeline safety supervision system, there are still some deficiencies in the actual implementation process. Some regions do not pay enough attention to the safety supervision of oil and gas pipelines, and the supervision is insufficient, resulting in some safety hazards not being discovered and rectified in time. Summary of the invention

[0004] In order to issue fault warnings in a timely manner when oil and gas leakage accidents occur, so as to quickly initiate emergency plans and carry out accident handling and rescue work, this application provides a gas pipeline network risk assessment system and method based on big data.

[0005] The gas pipeline network risk assessment system and method based on big data provided in this application adopts the following technical solutions:

[0006] In the first aspect, the present application provides a gas pipeline network risk assessment method based on big data, comprising the following steps:

[0007] Acquire the magnetic leakage signal of the gas pipeline network through a magnetic leakage detector, and convert the magnetic leakage signal into a voltage signal;

[0008] Amplifying the converted voltage signal through an amplifier circuit;

[0009] The amplified voltage signal is converted into a digital signal by an analog-to-digital converter;

[0010] Processing the converted digital signal using a field programmable gate array;

[0011] The processed data is visualized to generate magnetic flux leakage detection data, wherein the magnetic flux leakage detection data includes a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn according to the data collected by the magnetic flux leakage detector on the surface of the gas pipeline network, and is converted into a grayscale image through a mapping relationship;

[0012] The magnetic flux leakage detection data of the gas pipeline network is divided into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and becomes jerky, and the grayscale difference of the defect image produces a jump value;

[0013] The alarm threshold is queried from a preset database, and if the jump value reaches the alarm threshold, an alarm instruction is generated and executed.

[0014] Furthermore, the steps of generating and executing an alarm instruction specifically include:

[0015] Retrieving crack information according to the defect image and defect area data, the crack information including a plurality of crack data, the crack data including crack area and crack depth;

[0016] Assign a specific crack identifier to each crack data;

[0017] Obtaining preset area division levels and depth division levels from a preset database;

[0018] According to the crack area and the area classification grade, a damage area grade is obtained;

[0019] According to the crack depth and the depth classification level, a damage depth level is obtained;

[0020] The crack damage level is calculated according to the damage area level and the damage depth level, and the crack damage level is divided into slight cracks, medium cracks, and severe cracks;

[0021] If the crack damage level is a slight crack or a medium crack, the crack data and a crack specific identifier corresponding to the crack data are pushed to a terminal of an operation and maintenance user;

[0022] If the crack damage level is a severe crack, the crack data and a crack specific identifier corresponding to the crack data are pushed to terminals of an operation and maintenance user and a management user.

[0023] Furthermore, after the step of calculating the crack damage level, the method further includes:

[0024] Obtain crack location information;

[0025] Calculating the number of cracks per unit area according to the crack position information;

[0026] Obtaining a crack quantity threshold from a preset database;

[0027] If the number of cracks per unit area reaches a crack number threshold, a level increase instruction is generated and executed, and the level increase instruction is used to increase the original crack damage level by one level.

[0028] Furthermore, after the step of calculating the crack damage level, the method further includes:

[0029] Query gas pipeline network data from the preset database;

[0030] According to the crack location information and the gas network line data, the crack distribution location type is obtained, and the crack distribution location type includes key parts, secondary parts, and any parts;

[0031] If the crack distribution location type is a critical part, executing the step of generating and executing the level improvement instruction;

[0032] If the crack distribution location type is any part, a level reduction instruction is generated and executed, and the level reduction instruction is used to reduce the original crack damage level by one level.

[0033] Furthermore, after the step of calculating the crack damage level, the method further includes:

[0034] Acquiring crack shape data according to the defect image;

[0035] Classifying the crack shapes according to the crack shape data, wherein the crack shapes include irregular cracks and regular cracks;

[0036] If the crack shape is a regular-shaped crack, the step of generating and executing the level-enhancing instruction is executed.

[0037] Furthermore, after the step of calculating the crack damage level, the method further includes:

[0038] If the crack damage level is a severe crack, determining the damaged pipeline identifier according to the crack location information;

[0039] According to the damaged pipeline identifier, a transmission suspension instruction is generated and executed, and the transmission suspension instruction is used to suspend the gas transmission work of the damaged pipeline.

[0040] Furthermore, after the step of generating and executing the alarm instruction, the method further includes:

[0041] According to the gas pipeline network line data, retrieve the damaged gas transmission line where the damaged pipeline mark is located;

[0042] Obtaining a pre-failure gas transmission time corresponding to the damaged gas transmission line;

[0043] According to the pre-failure gas transmission time, obtain an available gas pipeline network that is idle during the pre-failure gas transmission time;

[0044] Based on the available gas pipeline network, an alternative gas transmission line is generated and pushed to the user's smart terminal.

[0045] Furthermore, the step of visualizing the processed data to generate magnetic flux leakage detection data specifically includes:

[0046] Map the digital signal to the pixels of the image and convert the digital signal into image data;

[0047] According to the image data, a window of s×s is taken, and in the window, the central pixel F(j, k) is used as the reference point to make s-1 pentagons, s-1 hexagons, and 1 square with a side length of s-2, for a total of nine masks;

[0048] Calculate the mean a of each mask i and variance k i ;

[0049]

[0050] Where i = 1, 2…s; Q is the number of pixels corresponding to each mask; m, n are the displacements of the pixels in the mask relative to the center pixel (j, k). On this basis, according to k i Sort and take the minimum variance k imin The gray level mean a of the corresponding mask i As the smoothed output G(j, k) of F(j, k) (in areas with sharp edges, the variance must be larger than that in flat areas), this method is used to perform mask operations on each pixel (the two edge rows can be extended to zero or symmetrically), thereby completing the smoothing filtering of the full-frame image and obtaining the defect image of the selected area.

[0051] In the second aspect, this application provides a gas pipeline network risk assessment system based on big data, including:

[0052] A magnetic leakage signal conversion module, used to obtain a magnetic leakage signal of the gas pipe network through a magnetic leakage detector, and convert the magnetic leakage signal into a voltage signal;

[0053] A voltage signal amplification module, used for amplifying the converted voltage signal through an amplification circuit;

[0054] A voltage signal conversion module, used for converting the amplified voltage signal into a digital signal through an analog-to-digital converter;

[0055] A digital signal processing module, used for processing the converted digital signal using a field programmable gate array;

[0056] A visualization processing module is used to perform visualization processing on the processed data to generate magnetic flux leakage detection data, wherein the magnetic flux leakage detection data includes a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn based on the data collected by the magnetic flux leakage detector on the surface of the gas pipe network, and is converted into a grayscale image through a mapping relationship;

[0057] The defect area retrieval module is used to divide the magnetic flux leakage detection data of the gas pipeline network into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and changes, and the grayscale difference of the defect image produces a jump value;

[0058] The alarm module is used to query the alarm threshold from a preset database, and if the jump value reaches the alarm threshold, an alarm instruction is generated and executed.

[0059] In a third aspect, the present application provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned big data-based gas pipeline network risk assessment method.

[0060] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the above-mentioned big data-based gas pipeline network risk assessment method.

[0061] In summary, compared with the prior art, the above technical solution has the following beneficial effects:

[0062] The gas pipeline network risk assessment system and method based on big data described in this application can capture the leakage magnetic signals on the surface of the gas pipeline network with high precision using a leakage magnetic detector. These signals are a direct reflection of the pipeline status (such as corrosion, cracks, etc.). The leakage magnetic signal is converted into a voltage signal and amplified by an amplifier circuit to ensure the strength and clarity of the signal, providing a reliable basis for subsequent processing. An analog-to-digital converter is used to convert the analog voltage signal into a digital signal for computer processing and analysis. A field programmable gate array (FPGA) is introduced to process digital signals in real time. The high-speed parallel processing capability of the FPGA makes signal processing faster and more efficient.

[0063] The processed data is visualized to generate magnetic flux leakage detection data, including magnetic flux leakage curves and defect images. These intuitive data representations help operators quickly understand the pipeline status. The defect image is converted into a grayscale image through a mapping relationship, making the defect location and degree clear at a glance. The magnetic flux leakage detection data is divided into normal data and defect area data. Through comparative analysis, potential defects on the pipeline can be accurately identified. Through the preset database query alarm threshold, when the jump value reaches or exceeds the threshold, the alarm instruction is automatically generated and executed, realizing real-time monitoring and early warning of the pipeline status. Once the alarm instruction is generated, the emergency response mechanism can be triggered immediately, including notifying relevant personnel, starting backup pipelines, closing valves, etc., to minimize the impact of the fault on the operation of the gas pipeline network. This method improves the efficiency and accuracy of emergency response and helps to ensure the safe and stable operation of the gas pipeline network. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of a gas pipeline network risk assessment method based on big data in an embodiment of the present application.

[0065] Figure 2 It is a flow chart of obtaining the damage depth level according to the crack depth and depth classification level in the embodiment of the present application.

[0066] Figure 3 It is a schematic diagram of the process of obtaining crack location information in an embodiment of the present application.

[0067] Figure 4 It is a schematic diagram of the process of querying gas network line data from a preset database in an embodiment of the present application.

[0068] Figure 5 It is a schematic diagram of the process of obtaining crack shape data based on the defect image in an embodiment of the present application.

[0069] Figure 6 It is a schematic diagram of a process for generating alternative gas transmission lines based on gas pipeline network line data in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The present application is further described in detail below in conjunction with all the accompanying drawings.

[0071] The present application embodiment discloses a gas pipeline network risk assessment method based on big data, referring to Figure 1 , the gas pipeline network risk assessment methods based on big data include:

[0072] S101. Acquire a magnetic leakage signal of a gas pipeline network through a magnetic leakage detector, and convert the magnetic leakage signal into a voltage signal.

[0073] Specifically, the monitoring and early warning system uses a magnetic flux leakage detector to scan along the gas pipeline network. The magnetic field generated by the strong magnet in the detector will change due to the thickness of the pipeline wall and the presence of defects, thereby generating a magnetic flux leakage signal. After obtaining the magnetic flux leakage signal of the gas pipeline network, the monitoring and early warning system converts the detected magnetic flux leakage signal into a voltage signal through a sensor for subsequent processing.

[0074] S102, amplifying the converted voltage signal through an amplifier circuit.

[0075] Specifically, the monitoring and early warning system amplifies the converted voltage signal through an amplification circuit to improve the strength and clarity of the signal, thereby enhancing the strength of the voltage signal and providing a better foundation for subsequent digital signal conversion.

[0076] S103 , converting the amplified voltage signal into a digital signal through an analog-to-digital converter.

[0077] Specifically, the monitoring and early warning system uses an analog-to-digital converter (ADC) to convert the amplified voltage signal into a digital signal for computer processing, converting the continuous voltage signal into a discrete digital signal for computer storage, analysis and processing.

[0078] S104: Process the converted digital signal using a field programmable gate array (FPGA).

[0079] Specifically, the monitoring and early warning system uses a field programmable gate array (FPGA) to perform real-time processing on the converted digital signal, including filtering, denoising, data compression and other steps, which improves the quality and reliability of the digital signal and provides a better data source for subsequent data visualization.

[0080] S105: Visualize the processed data to generate magnetic flux leakage detection data.

[0081] Specifically, a digital signal is a continuous signal represented by numbers, while an image is a two-dimensional array composed of pixels. Therefore, converting a digital signal into image data is essentially mapping the digital signal onto the pixels of the image. The monitoring and early warning system visualizes the processed data and generates magnetic flux leakage detection data, which includes magnetic flux leakage curves and defect images; wherein the defect image is a curve drawn based on the data collected by the magnetic flux leakage detector on the surface of the gas pipeline network, and is converted into a grayscale image through a mapping relationship.

[0082] In this embodiment, Python is used for processing. First, the digital signal is read using an appropriate file format, such as CSV, MAT, etc. Then, the image is generated using the functions provided by the image processing library (such as PIL, OpenCV) or the time series processing library (such as pyts). Finally, the generated image is saved in the database for viewing. The monitoring and early warning system provides intuitive magnetic flux leakage detection data, which is convenient for operators to observe and analyze the location and extent of pipeline defects. Since converting digital signals into image data is a prior art, it will not be explained in detail here.

[0083] S106, dividing the magnetic flux leakage detection data of the gas pipeline network into normal data and defect area data.

[0084] Specifically, the monitoring and early warning system divides the magnetic flux leakage detection data of the gas pipeline network into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and becomes jerky, and the grayscale difference of the defect image produces a jump value; it successfully distinguishes normal data from defect area data, providing a basis for subsequent alarms and emergency processing.

[0085] S107, querying the alarm threshold from a preset database, and if the jump value reaches the alarm threshold, generating and executing an alarm instruction.

[0086] Specifically, the monitoring and early warning system queries the alarm threshold from the preset database, which is pre-set by the user based on historical data and pipeline characteristics. If the grayscale difference jump value of the defect image reaches the alarm threshold, an alarm instruction is generated and corresponding emergency measures are executed, such as pushing the defect area data to the user's smart terminal. Through the steps of magnetic flux leakage detection, signal processing, data visualization, data analysis and alarm, intelligent monitoring and early warning and efficient emergency handling of the gas pipeline network are realized, which improves the speed and accuracy of emergency response.

[0087] In another embodiment, S105 specifically includes the following sub-steps:

[0088] Map the digital signal to the pixels of the image and convert the digital signal into image data;

[0089] According to the image data, a window of s×s is taken, and in the window, the central pixel F(j, k) is used as the reference point to make s-1 pentagons, s-1 hexagons, and 1 square with a side length of s-2, for a total of nine masks;

[0090] Calculate the mean a of each mask i and variance k i ;

[0091]

[0092] Where i = 1, 2…s; Q is the number of pixels corresponding to each mask; m, n are the displacements of the pixels in the mask relative to the center pixel (j, k). On this basis, according to k i Sort and take the minimum variance k imin The gray level mean a of the corresponding mask i As the smoothed output G(j, k) of F(j, k) (in areas with sharp edges, the variance must be larger than that in flat areas), this method is used to perform mask operations on each pixel (the two edge rows can be extended to zero or symmetrically), thereby completing the smoothing filtering of the full-frame image and obtaining the defect image of the selected area.

[0093] Specifically, the monitoring and early warning system maps digital signals (usually one-dimensional) to pixels of a two-dimensional image, and the grayscale value or color value of each pixel is determined by the corresponding digital signal value. Thus, a two-dimensional image is obtained, which contains the information of the original digital signal. The image's texture, brightness and other characteristics reflect the changing rules of the digital signal.

[0094] First, the monitoring and early warning system makes a mask. In the s×s window, with the central pixel F(j, k) as the reference point, s-1 pentagonal masks are made (these pentagons are centered around the central pixel and the size gradually changes); s-1 hexagonal masks are made (they are also centered around the central pixel and the size gradually changes); and a square mask with a side length of s-2 is made (this square mask is slightly smaller than the s×s window). The specific shape and size of the mask can be adjusted as needed. The diversity of the mask helps capture image features of different directions and scales. Pentagonal and hexagonal masks can capture more edge and corner information.

[0095] Then, the monitoring and early warning system calculates the mean value a of each mask i and variance k i For each mask, the monitoring and early warning system calculates the mean value a of the pixels in its coverage area i and variance k i . Mean a i It reflects the average brightness or grayscale value of the pixels in the mask area, and the variance k i It reflects the discreteness or fluctuation of pixel values ​​in the mask area. i and variance k i Provides statistical information about the image features within the mask region, the variance k i The size of can help determine whether the region contains sharp edges or noise.

[0096] The monitoring and early warning system selects the mask mean corresponding to the minimum variance as the smoothed output. i Sort by size and select the minimum variance kimin The gray level mean a of the corresponding mask i As the smooth output G(j, k) of the central pixel F(j, k). The mask corresponding to the minimum variance usually means that the pixel values ​​in the area are relatively stable, without sharp edges or noise. Therefore, choosing the mean of this mask as the smooth output can retain the main features of the image while removing noise and sharp edges.

[0097] Finally, the monitoring and early warning system performs a mask operation on each pixel and repeats the above mask operation for each pixel in the image (except the two edge rows which can be processed by zero extension or symmetrical extension) to obtain the smoothing filtering result of the entire image. The smoothing filtering effect of the image will be reflected in the grayscale value of each pixel. Sharp edges and noise will be effectively removed while retaining the main structure and features of the image.

[0098] The monitoring and early warning system obtains defect images of the selected area. In the smoothed and filtered image, the defect area is identified by comparing pixel values ​​or applying threshold segmentation and other methods. The defect area can include abnormal features such as cracks, scratches, spots, etc. The final defect image will highlight the abnormal area in the image, which is helpful for subsequent defect detection, classification and identification operations.

[0099] In another embodiment, referring to Figure 2 , S107 specifically includes the following sub-steps:

[0100] S107.11. Retrieve crack information based on the defect image and defect area data.

[0101] Specifically, the monitoring and early warning system uses image processing algorithms (such as edge detection, image segmentation, etc.) to identify and extract crack information based on defect images and defect area data. Crack information includes several crack data, each of which contains two key parameters: crack area and crack depth. Thus, crack information is successfully extracted from defect images, providing basic data for subsequent crack damage level assessment.

[0102] In this embodiment, the monitoring and early warning system uses edge detection algorithms (such as Canny, Sobel, etc.) to detect edge information in the image, and cracks usually appear as obvious edges. Then the monitoring and early warning system further processes the image using morphological operations (such as expansion, corrosion, opening operation, closing operation, etc.) to highlight the crack features and remove noise. Finally, the crack region is segmented, and the monitoring and early warning system separates the crack region from the background through methods such as threshold segmentation and region growing.

[0103] The monitoring and early warning system establishes a mathematical model between crack depth and image features based on the imaging characteristics of the cracks, and then extracts depth-related features from the processed crack images, such as crack width, shape, grayscale changes, etc. Finally, the extracted features are input into the established mathematical model to calculate the crack depth.

[0104] S107.12. Assign a specific crack identifier to each crack data.

[0105] Specifically, the monitoring and early warning system assigns a unique crack-specific identifier to each crack data so that each crack can be accurately tracked and identified in subsequent processing. This achieves unique identification of crack data and improves the efficiency and accuracy of data management.

[0106] S107.13. Obtain preset area division levels and depth division levels from a preset database.

[0107] Specifically, the standards for the crack area classification and crack depth classification are read from the preset database. These standards are preset by the user and can be freely edited based on industry standards, actual needs, empirical data or experimental data. The area and depth classification standards required for evaluating the crack damage level are obtained, providing a basis for subsequent calculations.

[0108] S107.14. According to the crack area and the area classification grade, the damage area grade is obtained.

[0109] Specifically, the monitoring and early warning system classifies the crack area into the corresponding damage area grade according to the crack area and the area classification standard.

[0110] S107.15. According to the crack depth and the depth classification level, the damage depth level is obtained.

[0111] Specifically, the monitoring and early warning system classifies the crack depth into the corresponding damage depth level according to the crack depth and depth classification standard. The crack area and crack depth are successfully classified into corresponding levels, which provides a basis for the calculation of crack damage level.

[0112] S107.16. Calculate the crack damage grade based on the damage area grade and the damage depth grade.

[0113] Specifically, the monitoring and early warning system calculates the crack damage level based on the damage area level and damage depth level, combined with the preset crack damage level assessment model or rules. The crack damage level is divided into three levels: slight cracks, medium cracks, and severe cracks. For example, when the sum of the damage area level and the damage depth level is 1-2, the crack damage level is slight cracks; when the sum of the damage area level and the damage depth level is 3-5, the crack damage level is medium cracks; when the sum of the damage area level and the damage depth level is greater than 5, the crack damage level is severe cracks. This achieves a quantitative assessment of the degree of crack damage and provides a basis for subsequent treatment measures.

[0114] S107.17. If the crack damage level is a slight crack or a medium crack, the crack data and the crack specific identifier corresponding to the crack data are pushed to the terminal of the operation and maintenance user.

[0115] Specifically, if the crack damage level is a slight crack or a medium crack, the crack data and a crack-specific identifier corresponding to the crack data are pushed to a terminal of an operation and maintenance user.

[0116] S107.18. If the crack damage level is a severe crack, the crack data and a crack specific identifier corresponding to the crack data are pushed to the terminals of the operation and maintenance user and the management user.

[0117] If the crack damage level is a serious crack, the crack data and the crack specific identifier corresponding to the crack data are pushed to the terminals of the operation and maintenance user and the management user so that emergency treatment measures can be taken in time. This realizes the timely transmission and notification of crack information, increases the attention of operation and maintenance personnel and management personnel to pipeline safety, and promotes the implementation of timely and effective treatment measures.

[0118] Reference Figure 3 Further, after S107.16, as another implementation, the embodiment of the present application may further include the following steps:

[0119] S107.21. Obtain crack location information.

[0120] Specifically, the monitoring and early warning system uses a magnetic flux leakage detector or other high-precision detection equipment to obtain crack information (such as crack area and crack depth) and record the specific location of each crack on the pipeline. The location information may include the longitude and latitude coordinates of the crack, the distance relative to the starting point of the pipeline, or a specific marking point on the pipeline. The monitoring and early warning system obtains the precise location information of each crack, which provides a basis for the subsequent calculation of the number of cracks per unit area.

[0121] S107.22. Calculate the number of cracks per unit area based on the crack position information.

[0122] Specifically, the monitoring and early warning system divides the pipeline into several small areas (such as every 1 meter, every 10 square meters, etc.) based on the crack location information obtained, counts the number of cracks in each small area, and calculates the number of cracks per unit area (such as every square meter, every meter of pipeline length). The monitoring and early warning system obtains the number of cracks per unit area in different areas of the pipeline, providing an important basis for evaluating the overall damage status of the pipeline.

[0123] S107.23. Obtain a crack quantity threshold from a preset database.

[0124] Specifically, the monitoring and early warning system obtains the crack number threshold from the preset database. The crack number threshold is pre-set in the database by the user based on factors such as pipeline type, material, and use environment. For example, the crack number threshold varies depending on the different parts of the gas pipeline network (such as elbows, tees, straight pipe sections, etc.). After the user enters the crack number threshold corresponding to different parts of the gas pipeline network, the monitoring and early warning system can extract the areas where different parts of the gas pipeline network are located and assign corresponding crack number thresholds to them. The monitoring and early warning system obtains the crack number threshold used to determine whether the crack damage level needs to be increased, providing a basis for subsequent decision-making.

[0125] S107.24. If the number of cracks per unit area reaches the crack number threshold, a level increase instruction is generated and executed.

[0126] Specifically, if the number of cracks per unit area in a small area reaches or exceeds the preset crack number threshold, the monitoring and early warning system will automatically generate a level increase instruction, which is used to increase the original crack damage level by one level (such as from slight cracks to medium cracks, or from medium cracks to severe cracks). After the monitoring and early warning system executes the instruction, it will update the crack damage level information and notify the relevant operation and maintenance personnel and management personnel. By increasing the crack damage level, the attention paid to the pipeline damage condition is enhanced, prompting the operation and maintenance personnel to take more active and effective maintenance measures. The accuracy and efficiency of pipeline safety management are improved, which helps to reduce safety accidents and property losses caused by pipeline damage.

[0127] S107.25. If the crack damage level is a severe crack, determine the damaged pipeline identification based on the crack location information.

[0128] Specifically, the monitoring and early warning system determines the specific identification of the damaged pipeline based on the previously obtained crack location information, combined with the pipeline's geographic layout map and pipeline identification system. Pipeline identification usually includes key information such as the pipeline's name, number, diameter, material, etc., which helps to quickly identify the damaged pipeline. The specific identification of the damaged pipeline was successfully determined, providing an accurate target for the subsequent generation and execution of the transportation suspension instruction.

[0129] S107.26. Generate and execute a transportation suspension instruction based on the damaged pipeline identifier.

[0130] Specifically, the monitoring and early warning system automatically generates a transmission suspension instruction based on the damaged pipeline identification. The instruction should include the specific information of the damaged pipeline, the reason for suspension (i.e., serious cracks), the time of suspension, and possible recovery plans or suggestions. The transmission suspension instruction is sent to the relevant control center and operators to ensure that they can receive and execute the instruction in time. According to the instruction, the operator suspends the gas transmission work of the damaged pipeline by closing the pipeline valve, adjusting the working status of the pump station, etc.

[0131] The generation and execution of the transmission suspension instruction ensured that the damaged pipeline could quickly stop gas transmission after serious cracks were detected, thus avoiding possible safety accidents such as leakage and explosion. By suspending gas transmission, the necessary time and safe environment were provided for subsequent maintenance and inspection work. The operators took prompt action according to the instructions, which reflected the efficiency and accuracy of emergency response.

[0132] Among them, as another implementation, S107.25 to S107.26 of the embodiment of the present application are optional.

[0133] Reference Figure 4 Further, after S107.16, as another implementation, the embodiment of the present application may further include the following steps:

[0134] S107.31. Query the gas network line data from the preset database.

[0135] Specifically, the monitoring and early warning system queries the line data of the gas pipeline network from the preset database. The data includes the direction of the pipeline, the transportation route of the pipeline, the location of the pipeline, key parts (such as elbows, tees, valves, near pump stations, etc.), secondary parts (such as the middle section of the pipeline, non-critical connection points, etc.) and detailed location information of any part. The database is maintained by the user himself, the pipeline operator or the relevant management department, and is updated regularly to ensure the accuracy and completeness of the data. The monitoring and early warning system obtains detailed line data of the gas pipeline network, which provides a basis for the subsequent determination of the type of crack distribution location.

[0136] S107.32. Determine the crack distribution location type based on the crack location information and gas pipeline line data.

[0137] Specifically, the monitoring and early warning system compares the calculated crack location information with the queried gas pipeline line data, and divides the crack distribution location types into key locations, secondary locations, and random locations based on the comparison results. Key locations refer to areas in the pipeline that are susceptible to stress concentration, corrosion, or other potential damage, such as elbows and tees; secondary locations refer to areas in the pipeline that are relatively safe and not easily damaged; random locations refer to areas in the gas pipeline network that will not have a practical impact on gas transmission, thereby accurately determining the crack distribution location type and providing a basis for subsequent adjustments to the crack damage level.

[0138] S107.33. If the crack distribution location type is a critical part, execute the step of generating a level improvement instruction and executing it.

[0139] Specifically, if the crack distribution location type is a critical part, which means that the cracks in this part are likely to cause substantial damage to the pipeline, the monitoring and early warning system will execute the steps of generating and executing level increase instructions, raising the original crack damage level by one level to reflect the potential threat of cracks to pipeline safety.

[0140] S107.34. If the crack distribution location type is any part, a level reduction instruction is generated and executed, and the level reduction instruction is used to reduce the original crack damage level by one level.

[0141] Specifically, if the crack distribution location type is any part, and the crack damage level is not directly caused by serious defects (such as corrosion perforation, crack extension, etc.), the monitoring and early warning system will generate and execute a level reduction instruction. This means that the original crack damage level will be reduced by one level to reflect that the actual impact of the crack on pipeline safety is small.

[0142] Reference Figure 5 Further, after S107.16, as another implementation, the embodiment of the present application may further include the following steps:

[0143] S107.41. Obtain crack shape data based on the defect image.

[0144] Specifically, the monitoring and early warning system uses image processing technology (such as edge detection, morphological processing, etc.) to process defect images and extract the contour information of the crack. Based on the extracted contour information, the shape parameters of the crack, such as length, width, curvature, etc., are calculated. These parameters will be used for subsequent shape classification. Accurately obtaining the shape data of the crack provides a basis for subsequent shape classification.

[0145] S107.42. Classify the crack shapes according to the crack shape data, wherein the crack shapes include irregular cracks and regular cracks.

[0146] Specifically, the monitoring and early warning system classifies the crack shapes according to the shape parameters of the cracks using machine learning algorithms (such as support vector machines, decision trees, etc.) or rule-based methods. The classification results include two categories: irregular cracks and regular cracks. Irregular cracks refer to cracks with complex shapes that are difficult to describe with simple geometric shapes; regular cracks refer to cracks with relatively simple shapes that can be approximately described with geometric shapes (such as straight lines, circles, etc.). This achieves effective classification of crack shapes and provides a basis for subsequent treatment strategies.

[0147] S107.43. If the crack shape is a regular-shaped crack, execute the step of generating and executing the level-enhancing instruction.

[0148] Specifically, if the crack shape is classified as a regular-shaped crack, the monitoring and early warning system will execute the steps of generating and executing the level-up instruction. This is because regular-shaped cracks tend to expand more easily and pose a greater threat to structural safety, so the processing priority needs to be increased. By increasing the processing priority, it is ensured that regular-shaped cracks can be processed in a timely and effective manner, reducing potential safety risks. This improves the efficiency of operation and maintenance and avoids greater losses caused by untimely processing.

[0149] Reference Figure 6 After S107, an alternative gas transmission line is generated according to the gas pipeline network line data, which specifically includes the following steps:

[0150] S201. According to the gas pipeline network line data, retrieve the damaged gas transmission line where the damaged pipeline identifier is located.

[0151] Specifically, the monitoring and early warning system can quickly locate the gas transmission line where the damaged pipeline is located based on the damaged pipeline identification and the gas pipeline network line data. The damaged gas transmission line data usually includes key information such as the starting point, end point, passing stations, and pipeline capacity of the pipeline. Accurately obtaining the information of the damaged gas transmission line provides a basis for the subsequent search for alternative gas transmission lines.

[0152] S202: Obtain the pre-failure gas transmission time corresponding to the damaged gas transmission line.

[0153] Specifically, the monitoring and early warning system calculates the pre-failure gas transmission time from the current moment to the expected complete failure (such as leakage, breakage, etc.) based on the flow rate, flow velocity and pipeline capacity of the damaged gas transmission line. The pre-failure gas transmission time takes into account factors such as the current operating status of the pipeline, historical failure data and possible maintenance measures. The available time of the damaged gas transmission line before failure is obtained, providing a time window for formulating alternative plans.

[0154] S203: According to the pre-failure gas transmission time, obtain an available gas pipeline network that is idle during the pre-failure gas transmission time.

[0155] Specifically, the monitoring and early warning system selects other gas pipelines that are idle or can adjust flow during the predicted fault gas transmission time according to the overall layout and operation status of the gas pipeline system. The idle gas pipelines that can be used should meet the requirements of capacity, flow rate and connection conditions to ensure that they can replace the damaged lines. The determination of the available gas pipeline resources provides a material basis for the construction of alternative gas transmission lines.

[0156] S204: Generate alternative gas transmission lines based on the available gas pipeline network and push them to the user's smart terminal.

[0157] Specifically, the monitoring and early warning system combines the resources of the available gas pipeline network to generate one or more alternative gas transmission line plans. The alternative gas transmission line plan should list in detail the new gas transmission path, required time, estimated cost, possible risk points and other information. The generated alternative gas transmission line plan is pushed to relevant users. A feasible alternative gas transmission line plan is provided to provide decision support for users. Pushing through smart terminals ensures the timeliness and accuracy of information and improves the efficiency of emergency response.

[0158] Based on the above method, the embodiment of the present application also discloses a gas pipeline network risk assessment system based on big data. The gas pipeline network risk assessment system based on big data includes:

[0159] The magnetic leakage signal conversion module is used to obtain the magnetic leakage signal of the gas pipeline network through the magnetic leakage detector and convert the magnetic leakage signal into a voltage signal.

[0160] The voltage signal amplification module is used to amplify the converted voltage signal through an amplification circuit.

[0161] The voltage signal conversion module is used to convert the amplified voltage signal into a digital signal through an analog-to-digital converter.

[0162] The digital signal processing module is used to process the converted digital signal using a field programmable gate array (FPGA).

[0163] A visualization processing module is used to visualize the processed data and generate magnetic flux leakage detection data, wherein the magnetic flux leakage detection data includes a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn based on the data collected by the magnetic flux leakage detector on the surface of the gas pipeline network, and is converted into a grayscale image through a mapping relationship.

[0164] The defect area retrieval module is used to divide the magnetic flux leakage detection data of the gas pipeline network into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and becomes jerky, and the grayscale difference of the defect image produces a jump value.

[0165] The alarm module is used to query the alarm threshold from a preset database, and if the jump value reaches the alarm threshold, an alarm instruction is generated and executed.

[0166] An embodiment of the present application also discloses an intelligent terminal, which includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the above-mentioned big data-based gas pipeline risk assessment method.

[0167] The embodiment of the present application also discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned gas pipeline network risk assessment method based on big data, and the computer-readable storage medium includes, for example, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0168] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A gas pipeline network risk assessment method based on big data, characterized in that: The following steps are involved: Acquire the magnetic leakage signal of the gas pipeline network through a magnetic leakage detector, and convert the magnetic leakage signal into a voltage signal; Amplifying the converted voltage signal through an amplifier circuit; The amplified voltage signal is converted into a digital signal by an analog-to-digital converter; Processing the converted digital signal using a field programmable gate array; The processed data is visualized to generate magnetic flux leakage detection data, wherein the magnetic flux leakage detection data includes a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn according to the data collected by the magnetic flux leakage detector on the surface of the gas pipeline network, and is converted into a grayscale image through a mapping relationship; The magnetic flux leakage detection data of the gas pipeline network is divided into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and becomes jerky, and the grayscale difference of the defect image produces a jump value; The alarm threshold is queried from a preset database, and if the jump value reaches the alarm threshold, an alarm instruction is generated and executed.

2. The gas pipeline network risk assessment method based on big data according to claim 1 is characterized in that: The steps of generating and executing an alarm instruction specifically include: Retrieving crack information according to the defect image and defect area data, the crack information including a plurality of crack data, the crack data including crack area and crack depth; Assign a specific crack identifier to each crack data; Obtaining preset area division levels and depth division levels from a preset database; According to the crack area and the area classification grade, a damage area grade is obtained; According to the crack depth and the depth classification level, a damage depth level is obtained; The crack damage level is calculated according to the damage area level and the damage depth level, and the crack damage level is divided into slight cracks, medium cracks, and severe cracks; If the crack damage level is a slight crack or a medium crack, the crack data and a crack specific identifier corresponding to the crack data are pushed to a terminal of an operation and maintenance user; If the crack damage level is a severe crack, the crack data and a crack specific identifier corresponding to the crack data are pushed to terminals of an operation and maintenance user and a management user.

3. The gas pipeline network risk assessment method based on big data according to claim 2 is characterized in that: After the step of calculating the crack damage level, the method further includes: Obtain crack location information; Calculating the number of cracks per unit area according to the crack position information; Obtaining a crack quantity threshold from a preset database; If the number of cracks per unit area reaches a crack number threshold, a level increase instruction is generated and executed, and the level increase instruction is used to increase the original crack damage level by one level.

4. The gas pipeline network risk assessment method based on big data according to claim 3 is characterized in that: After the step of calculating the crack damage level, the method further includes: Query gas pipeline network data from the preset database; According to the crack location information and the gas network line data, the crack distribution location type is obtained, and the crack distribution location type includes key parts, secondary parts, and any parts; If the crack distribution location type is a critical part, executing the step of generating and executing the level improvement instruction; If the crack distribution location type is any part, a level reduction instruction is generated and executed, and the level reduction instruction is used to reduce the original crack damage level by one level.

5. The gas pipeline network risk assessment method based on big data according to claim 3 is characterized in that: After the step of calculating the crack damage level, the method further includes: Acquiring crack shape data according to the defect image; Classifying the crack shapes according to the crack shape data, wherein the crack shapes include irregular cracks and regular cracks; If the crack shape is a regular-shaped crack, the step of generating and executing the level-enhancing instruction is executed.

6. The gas pipeline network risk assessment method based on big data according to claim 3 is characterized in that: After the step of calculating the crack damage level, the method further includes: If the crack damage level is a severe crack, determining the damaged pipeline identifier according to the crack location information; According to the damaged pipeline identifier, a transmission suspension instruction is generated and executed, and the transmission suspension instruction is used to suspend the gas transmission work of the damaged pipeline.

7. The gas pipeline network risk assessment method based on big data according to claim 4 is characterized in that: After the step of generating and executing the alarm instruction, the method further includes: According to the gas pipeline network line data, retrieve the damaged gas transmission line where the damaged pipeline mark is located; Obtaining a pre-failure gas transmission time corresponding to the damaged gas transmission line; According to the pre-failure gas transmission time, obtain an available gas pipeline network that is idle during the pre-failure gas transmission time; Based on the available gas pipeline network, an alternative gas transmission line is generated and pushed to the user's smart terminal.

8. The gas pipeline network risk assessment method based on big data according to claim 1 is characterized in that: The step of visualizing the processed data to generate magnetic flux leakage detection data specifically includes: Map the digital signal to the pixels of the image and convert the digital signal into image data; According to the image data, a window of s×s is taken, and in the window, the central pixel F(j, k) is used as the reference point to make s-1 pentagons, s-1 hexagons, and 1 square with a side length of s-2, for a total of nine masks; Calculate the mean a of each mask i and variance k i ; Where i = 1, 2…s; Q is the number of pixels corresponding to each mask; m, n are the displacements of the pixels in the mask relative to the center pixel (j, k). On this basis, according to k i Sort and take the minimum variance k imin The gray level mean a of the corresponding mask i As the smoothed output G(j, k) of F(j, k), this method is used to perform mask operation on each pixel to complete the smoothing filtering of the full-frame image and obtain the defect image of the selected area.

9. The gas pipeline network risk assessment system based on big data is characterized by: include: A magnetic leakage signal conversion module, used to obtain a magnetic leakage signal of the gas pipe network through a magnetic leakage detector, and convert the magnetic leakage signal into a voltage signal; A voltage signal amplification module, used for amplifying the converted voltage signal through an amplification circuit; A voltage signal conversion module, used for converting the amplified voltage signal into a digital signal through an analog-to-digital converter; A digital signal processing module, used for processing the converted digital signal using a field programmable gate array; A visualization processing module is used to perform visualization processing on the processed data to generate magnetic flux leakage detection data, wherein the magnetic flux leakage detection data includes a magnetic flux leakage curve and a defect image; wherein the defect image is a curve drawn based on the data collected by the magnetic flux leakage detector on the surface of the gas pipe network, and is converted into a grayscale image through a mapping relationship; The defect area retrieval module is used to divide the magnetic flux leakage detection data of the gas pipeline network into normal data and defect area data; in the normal area, the magnetic flux leakage signal changes little, the magnetic flux leakage curve is smooth, and the grayscale difference of the defect image remains stable; at the defect, the magnetic flux leakage detection data curve is affected by the edge field effect and changes, and the grayscale difference of the defect image produces a jump value; The alarm module is used to query the alarm threshold from a preset database, and if the jump value reaches the alarm threshold, an alarm instruction is generated and executed.

Images