Gas pipeline network leakage source positioning method, device and equipment

Abstract

The present application belongs to the technical field of gas safety detection, and discloses a kind of gas pipe network leakage source positioning method, device and equipment.The method includes by real-time acquisition city underground gas pipe network's operation sample data set;According to the principle of statistics based on the operation sample data set determines the leakage occurrence probability of the city underground gas pipe network;When the leakage occurrence probability exceeds preset probability, interpolation analysis is carried out to the operation sample data set, to obtain gas leakage quantity;According to the gas leakage quantity determines the position of gas leakage source, and predicts the spatiotemporal diffusion trend of gas leakage.Through the above mode, the data collected by the valve sensor of city underground pipe network is optimally and unbiasedly interpolated and estimated, and the probability of leakage occurrence of city underground pipe network is judged according to the principle of statistics, the pipeline leakage is judged and positioned, and the leakage quantity is estimated by statistical average value, the spatiotemporal diffusion process of gas leakage is inferred, and the detection efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of gas safety detection technology, and in particular to a method, apparatus and equipment for locating gas pipeline leak sources. Background Technology

[0002] As the "blood vessels" of the city, gas pipeline networks are distributed in ring or branching patterns, forming network topologies and multi-coupled structures. Due to aging facilities, reckless construction, and unauthorized excavation, leaks in urban underground gas pipeline networks are highly likely to occur, potentially leading to major accidents such as poisoning, fires, and explosions, as well as environmental pollution, severely impacting the safe and efficient operation of the gas pipeline network. Given the unique characteristics of urban underground gas pipeline networks, research into leak source location technology is essential.

[0003] Currently, the following are some common methods for locating leak sources in urban gas pipeline networks:

[0004] 1. Direct Observation Method: Experienced plumbers or trained animals walk along the pipeline to directly inspect for leaks by sight, smell, hearing, or other means. The accuracy of this method depends on the experience of the inspectors. However, this method is time-consuming, labor-intensive, has a long inspection cycle, and low accuracy. It can generally only detect a relatively large number of leaks and cannot achieve real-time online pipeline monitoring. It is also unsuitable for the inspection of urban underground pipe networks.

[0005] 2. Spectroscopic Analysis: A helicopter carrying a high-precision infrared camera flies along the pipeline to analyze subtle temperature differences between the transported medium and the surrounding soil to determine if there is a leak, and uses spectral analysis to pinpoint the location. This method is expensive and unsuitable for urban pipe networks.

[0006] 3. Cable Detection Method: Special cables are laid along the pipeline. When leaked substances seep into the cable, its properties change, thus detecting and locating the leak. Currently, commonly used cables include oil-soluble cables, permeable cables, and distributed sensor cables. However, this method involves expensive cables, and the cables must be replaced promptly once contaminated with leaked substances.

[0007] 4. In-pipe detection ball method: A detection ball is placed inside the pipe for detection. A large amount of data is collected using ultrasonic, visual, and magnetic flux leakage technologies, and then comprehensively analyzed to determine the leak point. This method has a long detection cycle and cannot achieve online real-time detection. Furthermore, because the detection ball flows with the medium inside the pipe, it is prone to blockage at bends, valves, and other locations. Therefore, this method is not suitable for leak detection in urban gas pipeline networks with many bends and valves.

[0008] 5. Tracer Detection Method: Radioactive materials are mixed into the medium transported in the pipeline. At the point of leakage, the radioactive tracer flows out of the pipeline with the leaking medium and adheres to the soil. A tracer leak detector is used to detect leaks along the pipeline, recording the radioactivity of the leaked tracer element. The location of the leak can be determined based on the recorded curve. This method cannot perform real-time online detection, and the tracer can cause blockages as it flows with the medium inside the pipe, making it unsuitable for leak detection in urban gas pipeline networks.

[0009] 6. Negative Pressure Wave Method: When a pipeline leaks, the pressure at the leak point C decreases due to the loss of fluid medium, forming a negative pressure wave that propagates upstream and downstream. Pressure sensors are installed at both ends of the pipeline to collect and analyze the negative pressure wave signals generated during the leak, obtaining correlation function curves. This method is weakly effective, or even ineffective, for slowly increasing leaks or minor seepage. Furthermore, due to reflection, diffraction, and interference phenomena at bends, branch points, and other locations during pressure wave propagation, the pressure wave is affected by numerous random waves, leading to false detections and missed detections, making it unsuitable for practical engineering applications.

[0010] 7. Mass Balance Method: Based on the principle of mass conservation, under normal pipeline operation, the difference between the mass of fluid flowing into and out of the pipeline within the same time interval is equal to the change in the mass of the fluid within the pipeline. This method cannot locate leaks, has low sensitivity for detecting small leaks, and its detection accuracy depends on the accuracy of the flow measurement.

[0011] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0012] The main objective of this invention is to provide a method, apparatus, and equipment for locating gas pipeline leak sources, aiming to solve the technical problems of low detection efficiency and accuracy in existing detection methods.

[0013] To achieve the above objectives, the present invention provides a method for locating a gas pipeline leak source, the method comprising the following steps:

[0014] Real-time acquisition of operational sample datasets of urban underground gas pipeline networks;

[0015] Based on statistical principles, the probability of leakage in the city's underground gas pipeline network is determined using the operational sample dataset.

[0016] When the probability of leakage exceeds a preset probability, interpolation analysis is performed on the operational sample dataset to obtain the amount of gas leakage;

[0017] The location of the gas leak source is determined based on the amount of gas leak, and the spatiotemporal diffusion trend of the gas leak is predicted.

[0018] In some embodiments, the real-time acquisition of operational sample datasets of urban underground gas pipeline networks includes:

[0019] Collect basic data on the urban underground gas pipeline network based on on-site surveys and pipeline design drawings.

[0020] Data from gas pipeline sensors is collected by the combustible gas monitoring sensors already installed on the gas valves of the urban underground pipeline network.

[0021] By using histograms to calculate and analyze the distribution patterns of regional changes, and by removing differences in the basic data of the urban underground gas pipeline network and the sensor data of the gas pipeline network, and integrating and unifying them, an operational sample dataset of the urban underground gas pipeline network is obtained.

[0022] In some embodiments, the interpolation analysis of the running sample dataset to obtain the gas leakage amount includes:

[0023] Construct a four-dimensional spatiotemporal rule grid for the target monitoring area;

[0024] The mutation function is determined based on a pre-defined mutation model;

[0025] The amount of gas leakage in each grid cell to be valued in the four-dimensional spatiotemporal rule grid is determined based on the variogram function.

[0026] In some embodiments, constructing a four-dimensional spatiotemporal rule grid of the target monitoring area includes:

[0027] The minimum grid cell is determined based on the temporal and spatial resolutions corresponding to the preset requirements.

[0028] The target detection area is divided into a four-dimensional spatiotemporal regular grid based on the smallest grid unit, and the positions of each sensor in the four-dimensional spatiotemporal regular grid are located. The sensor detection values ​​are used as the detection data of the sample.

[0029] In some embodiments, determining the mutation function based on a preset mutation model includes:

[0030] Distance is used as a variable in the preset mutation model, and the distance includes at least the distance between samples and the distance between a sample and a grid cell;

[0031] Based on the variables, a variogram function is constructed by combining the nugget constant, arch height, sill value, preset range, and model parameters. The model parameters are determined by the Euclidean distance and the difference in gas leakage between the data values ​​of each valve sensor in the pipeline network on the four-dimensional spatiotemporal rule grid.

[0032] In some embodiments, determining the gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal regular grid based on the variogram function includes:

[0033] Determine several nearest neighbor samples in the four-dimensional spatiotemporal regular grid for any grid cell to be valued.

[0034] Calculate the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued, and the semivariogram value corresponding to the distance.

[0035] The weights of the nearest neighbor samples are determined based on the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued and the semivariogram value corresponding to the distance.

[0036] The amount of gas leakage is determined based on the weights and the sensor detection values ​​corresponding to the nearest neighbor samples.

[0037] In some embodiments, determining the location of the gas leak source based on the gas leak amount and predicting the spatiotemporal diffusion trend of the gas leak includes:

[0038] The four-dimensional spatiotemporal rule grid is divided into multiple three-dimensional spatial slices according to time units;

[0039] On each three-dimensional space slice, query the location where the local gas leakage volume exceeds the threshold, and filter out the low-frequency noise extreme points to obtain the location of the gas leakage source;

[0040] The spatiotemporal diffusion trend of gas leaks can be predicted based on the difference in gas leak volume between temporally adjacent three-dimensional spatial slices.

[0041] Furthermore, to achieve the above objectives, the present invention also proposes a gas pipeline leak source locating device, the gas pipeline leak source locating device comprising:

[0042] The data acquisition module is used to acquire operational sample datasets of the urban underground gas pipeline network in real time.

[0043] The judgment module is used to determine the probability of leakage in the urban underground gas pipeline network based on the running sample dataset according to statistical principles.

[0044] The calculation module is used to perform interpolation analysis on the running sample dataset when the probability of leakage exceeds a preset probability, so as to obtain the amount of gas leakage;

[0045] The detection module is used to determine the location of the gas leak source based on the amount of gas leak and to predict the spatiotemporal diffusion trend of the gas leak.

[0046] In some embodiments, the acquisition module is used to acquire basic data of urban underground gas pipeline networks based on on-site surveys and pipeline design drawings of urban underground pipelines;

[0047] Data from gas pipeline sensors is collected by the combustible gas monitoring sensors already installed on the gas valves of the urban underground pipeline network.

[0048] By using histograms to calculate and analyze the distribution patterns of regional changes, and by removing differences in the basic data of the urban underground gas pipeline network and the sensor data of the gas pipeline network, and integrating and unifying them, an operational sample dataset of the urban underground gas pipeline network is obtained.

[0049] Furthermore, to achieve the above objectives, the present invention also proposes a gas pipeline leak source locating device, which includes: a memory, a processor, and a gas pipeline leak source locating program stored in the memory and executable on the processor. The gas pipeline leak source locating program is configured to implement the steps of the gas pipeline leak source locating method described above.

[0050] This invention acquires real-time operational sample datasets of urban underground gas pipeline networks; determines the probability of leakage in the network based on these datasets using statistical principles; when the probability exceeds a preset probability, interpolates the datasets to obtain the gas leakage amount; and determines the location of the gas leak source based on the leakage amount, predicting the spatiotemporal diffusion trend. Through this method, optimal and unbiased interpolation estimation is performed on data collected by valve sensors in the urban underground pipeline network. Based on statistical principles, the probability of leakage in the network is determined, allowing for leak identification and location. Furthermore, the leakage amount is estimated using statistical averages, and the spatiotemporal diffusion process of the gas leak is inferred, thus improving detection efficiency and accuracy. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating the first embodiment of the gas pipeline leak source location method of the present invention;

[0052] Figure 2 This is a schematic diagram of the cross-validation process in the gas pipeline leak source location method of the present invention;

[0053] Figure 3 This is a structural block diagram of the first embodiment of the gas pipeline leak source locating device of the present invention.

[0054] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0055] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0056] This invention provides a method for locating gas pipeline leak sources, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a gas pipeline leak source location method according to the present invention.

[0057] In this embodiment, the method for locating the gas pipeline leak source includes the following steps:

[0058] Step S10: Obtain the operational sample dataset of the urban underground gas pipeline network in real time.

[0059] In this embodiment, the executing entity is a gas pipeline leak source location device. This gas pipeline leak source location device has functions such as data processing, data communication, and program execution. The gas pipeline leak source location device can be a computer terminal device or other network device, or other devices with similar functions. This embodiment does not limit this.

[0060] It should be noted that gas pipelines, acting as the "blood vessels" of cities, are distributed in ring or branching patterns, forming a network topology and multi-coupled structure. Due to aging facilities, reckless construction, and unauthorized excavation, leaks in urban underground gas pipelines are highly likely, potentially leading to major accidents such as poisoning, fires, and explosions, as well as environmental pollution, severely impacting the safe and efficient operation of the gas pipeline network. Given the unique characteristics of urban underground gas pipelines, research into leak source location technology is essential. Current methods, such as direct observation, spectral analysis, cable detection, in-pipe detection spheres, tracer detection, negative pressure wave methods, and mass balance methods, suffer from low detection efficiency and accuracy.

[0061] To address the aforementioned technical issues, this embodiment acquires a real-time operational sample dataset of the urban underground gas pipeline network. Based on statistical principles, it determines the probability of a leak in the urban underground gas pipeline network using this dataset. When the probability of a leak exceeds a preset probability, it performs interpolation analysis on the operational sample dataset to obtain the gas leak amount. Based on the gas leak amount, it determines the location of the gas leak source and predicts the spatiotemporal diffusion trend of the gas leak. Through this method, optimal and unbiased interpolation estimation is performed on the data collected by valve sensors in the urban underground pipeline network. Based on statistical principles, the probability of a leak in the urban underground pipeline network is determined, allowing for the identification and location of pipeline leaks. Furthermore, the leak amount is estimated using statistical averages, and the spatiotemporal diffusion process of the gas leak is inferred, thus improving detection efficiency and accuracy.

[0062] In this specific implementation, the following steps are required: First, a sample dataset of the urban underground gas pipeline network's operation needs to be collected. Specifically, basic data of the urban underground gas pipeline network is collected based on on-site surveys and pipeline design drawings. Gas pipeline network sensor data is collected through combustible gas monitoring sensors installed on the gas valves of the urban underground pipeline network. Histograms are used to calculate and analyze the distribution patterns of regional changes. Differences between the basic data and the sensor data of the urban underground gas pipeline network are then eliminated and integrated to obtain the operational sample dataset of the urban underground gas pipeline network. It should be noted that the basic data of the urban underground gas pipeline network includes spatial coordinates, shape and dimensions, material, topological relationships, ownership information, construction year, and burial depth. Outlier elimination can be achieved through coordinate transformation, attribute information integration, data cleaning, and standardization techniques. After integration and unification, a sample dataset of the real-time operation of the urban underground gas pipeline network can be formed, allowing for unified storage, updates, and management.

[0063] Step S20: Determine the probability of leakage in the urban underground gas pipeline network based on the running sample dataset according to statistical principles.

[0064] Based on statistical principles, historical records of pipeline leaks can be collected, including the specific time, location, cause, pipe materials involved, and service life. Detailed information about the pipeline system, such as total pipe length, layout, and maintenance history, can also be gathered. By analyzing these historical records, the probability of a leak can be obtained. Furthermore, this embodiment can also utilize models such as logistic regression, probabilistic regression models, neural networks, and Bayesian networks for probability prediction.

[0065] Step S30: When the probability of leakage exceeds the preset probability, perform interpolation analysis on the running sample dataset to obtain the amount of gas leakage.

[0066] After obtaining the leakage probability, this embodiment compares the leakage probability with a preset probability. The leakage detection targets urban underground gas pipeline networks with a high probability of leakage. The preset probability can be set according to actual detection needs, and this embodiment does not impose any restrictions on it.

[0067] It should be noted that the gas leak detection in this embodiment is based on the amount of gas leaked, and the leak source is located by measuring the amount of gas leaked.

[0068] Specifically, in this embodiment, a four-dimensional spatiotemporal rule grid needs to be constructed for the target monitoring area. The target monitoring area is the area where gas leak detection and location need to be performed, and the target monitoring area can be selected based on actual needs.

[0069] The segmentation process of the four-dimensional spatiotemporal regular grid involves determining the minimum grid unit based on the temporal and spatial resolutions corresponding to preset requirements. The target detection area is then segmented into a four-dimensional spatiotemporal regular grid based on these minimum grid units. The positions of each sensor within the grid are located, and the sensor detection values ​​are used as the sample detection data. The preset requirements, i.e., detection requirements, include requirements such as detection accuracy. These requirements can be obtained through mapping relationships. The size of the minimum grid unit is determined based on the temporal and spatial resolutions, and the target detection area is segmented into a four-dimensional spatiotemporal regular grid according to this minimum grid unit size. Since there are already installed combustible gas monitoring sensors within the target monitoring area, after the four-dimensional spatiotemporal regular grid segmentation is completed, the positions of these sensors are identified, and their detection values ​​are used as the detection data for subsequent samples.

[0070] Furthermore, after completing the division of the four-dimensional spatiotemporal regular grid, this embodiment needs to determine the mutation function based on a preset mutation model. Specifically, distance is used as a variable in the preset mutation model, and the distance includes at least the distance between samples and the distance between a sample and a grid cell. Based on the variables, the mutation function is constructed by combining the nugget constant, arch height, sill value, preset range, and model parameters. The model parameters are determined by the Euclidean distance between the data values ​​of valve sensors in the pipeline network on the four-dimensional spatiotemporal regular grid and the difference in gas leakage. For example, this system selects a spherical model as the basic mutation model, that is:

[0071]

[0072] Where N is the nugget constant, C is the arch height, N+C is the sill value, a is the preset range, and distance h is used as a variable. The model parameters can be estimated by the Euclidean distance between each pair of valve sensor data values ​​in four-dimensional spacetime and the difference in gas leakage. It should be noted that the spatial correlation of the spherical model gradually declines with the increase of distance, and the spatial correlation disappears when the distance is greater than the radius of the sphere.

[0073] Based on the aforementioned variogram, this embodiment can further determine the gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal regular grid. Specifically, several nearest neighbor samples of any grid cell to be valued are determined in the four-dimensional spatiotemporal regular grid; the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the semivariogram value corresponding to the distance between each nearest neighbor sample and the grid cell to be valued are calculated respectively; the weights of the several nearest neighbor samples are determined according to the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the semivariogram value corresponding to the distance between each nearest neighbor sample and the grid cell to be valued; the gas leakage amount is determined according to the weights and the sensor detection values ​​corresponding to the several nearest neighbor samples. For example, for each grid cell u to be valued: first, find its n nearest neighbor samples in four-dimensional spatiotemporal, and calculate the mean of the nearest neighbor samples, m(u), and the distance h between each sample. ij =d(u i ,u j ) and the corresponding semi-variogram value g(h) ij ), each sample u i Distance h from u i =d(u,u i ), and the semi-variogram value g(h) corresponding to that distance. i The semi-variogram value can be calculated by substituting the distance h into the above function.

[0074] Further solve the following equations:

[0075]

[0076] The weights w of the n nearest sampling points (at the sample location) of the current grid cell u to be valued can be calculated by solving this problem. i Coefficients (i = 1...n).

[0077] The impact of changing the nugget value under isotropic conditions versus changing the anisotropy under the same nugget value on the weights was analyzed, and the weight w was ultimately determined. i .

[0078] Finally, use w i and the detection value Z at the sample i The gas leakage value Z(u) of u is estimated using the Kriging method, that is: The detection value Z at the sample i This can be obtained from the detection data of the above samples.

[0079] Furthermore, to improve detection accuracy, this embodiment can also use k-fold cross-validation to evaluate the interpolation results and verify the effectiveness of the spatiotemporal Kriging interpolation method. The samples are divided into k equal parts, with k-1 parts used as training samples and the remaining part as validation samples, repeated k times. The specific process is as follows: Figure 2 As shown, (1) select the initial variogram model and parameters based on the sample data; (2) delete the first observation Z(x1) from the dataset; (3) use other observations, the initial variogram model, and the kriging method to predict the value Z′(x1) at point x1; (4) put Z(x1) into the dataset and repeat steps ① to ④ until other predicted values ​​Z′(x2), Z′(x3)...Z′(xn) are estimated; (5) compare the calculation errors of the source data Z(x1), Z(x2)...Z(xn) and the predicted data Z′(x1), Z′(x2)...Z′(xn); (6) judge the goodness of the model by statistical results; (7) if the error is large, adjust the parameters and variogram model and repeat steps (1) to (6) until the result is optimal. The parameter adjustment can be, for example, adjusting the above-mentioned nugget constant and arch height parameters. The variogram model adjustment can be to construct a new model formula or adjust the range conditions, etc.

[0080] Step S40: Determine the location of the gas leak source based on the gas leak volume, and predict the spatiotemporal diffusion trend of the gas leak.

[0081] In this embodiment, when locating the gas leak source, the four-dimensional spatiotemporal grid needs to be divided into multiple three-dimensional spatial slices according to time units. This division can be done spatially based on regions. Then, based on the determined gas leak volume, the location of the local maximum gas leak volume is obtained. For example, the location of the largest gas leak volume is selected from the gas leak volumes at various local locations and used as the leak source location. Furthermore, the gas leak volume difference is calculated for each of the divided three-dimensional spatial slices. The velocity can be calculated by dividing the gas leak volume difference by the time interval. For example, the gas leak volume difference corresponding to different interval lengths is calculated by dividing the gas leak volume difference by the interval length. It should be noted that this leakage velocity is a vector; therefore, the spatiotemporal diffusion trend of the gas leak can also be known through this velocity. For example, if the gas leak volume difference between two monitoring points gradually decreases, while the difference between another set of gas leak volume gradually increases, the spatiotemporal diffusion trend can be predicted.

[0082] This embodiment acquires a real-time operational sample dataset of the urban underground gas pipeline network; based on statistical principles, it determines the probability of leakage in the urban underground gas pipeline network based on the operational sample dataset; when the probability of leakage exceeds a preset probability, it performs interpolation analysis on the operational sample dataset to obtain the gas leakage amount; based on the gas leakage amount, it determines the location of the gas leak source and predicts the spatiotemporal diffusion trend of the gas leak. Through the above method, optimal and unbiased interpolation estimation is performed on the data collected by valve sensors in the urban underground pipeline network. Based on statistical principles, the probability of leakage in the urban underground pipeline network is determined, pipeline leaks are identified and located, and the leakage amount is estimated through statistical averages to infer the spatiotemporal diffusion process of the gas leak, thus improving detection efficiency and accuracy.

[0083] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the gas pipeline leak source locating device of the present invention.

[0084] like Figure 3 As shown, the gas pipeline leak source locating device proposed in this embodiment of the invention includes:

[0085] The data acquisition module 10 is used to acquire operational sample datasets of the urban underground gas pipeline network in real time.

[0086] The judgment module 20 is used to determine the probability of leakage in the urban underground gas pipeline network based on the running sample dataset according to statistical principles.

[0087] The calculation module 30 is used to perform interpolation analysis on the running sample dataset when the probability of leakage exceeds a preset probability, so as to obtain the amount of gas leakage.

[0088] The detection module 40 is used to determine the location of the gas leak source based on the amount of gas leak and to predict the spatiotemporal diffusion trend of the gas leak.

[0089] This embodiment acquires a real-time operational sample dataset of the urban underground gas pipeline network; based on statistical principles, it determines the probability of leakage in the urban underground gas pipeline network based on the operational sample dataset; when the probability of leakage exceeds a preset probability, it performs interpolation analysis on the operational sample dataset to obtain the gas leakage amount; based on the gas leakage amount, it determines the location of the gas leak source and predicts the spatiotemporal diffusion trend of the gas leak. Through the above method, optimal and unbiased interpolation estimation is performed on the data collected by valve sensors in the urban underground pipeline network. Based on statistical principles, the probability of leakage in the urban underground pipeline network is determined, pipeline leaks are identified and located, and the leakage amount is estimated through statistical averages to infer the spatiotemporal diffusion process of the gas leak, thus improving detection efficiency and accuracy.

[0090] In some embodiments, the acquisition module 10 is used to acquire basic data of the urban underground gas pipeline network based on the on-site survey and pipeline design drawings of the urban underground pipeline; acquire gas pipeline network sensor data through combustible gas monitoring sensors installed on the gas valves of the urban underground pipeline network; use histogram calculation to analyze the distribution law of regional changes, and remove differences in the basic data of the urban underground gas pipeline network and the gas pipeline network sensor data, and integrate and unify them to obtain an operational sample dataset of the urban underground gas pipeline network.

[0091] In some embodiments, the calculation module 30 is used to construct a four-dimensional spatiotemporal rule grid of the target monitoring area; determine a mutation function based on a preset mutation model; and determine the gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal rule grid according to the mutation function.

[0092] In some embodiments, the calculation module 30 is used to determine the minimum grid cell based on the temporal and spatial resolution corresponding to the preset requirements; to divide the target detection area into a four-dimensional spatiotemporal regular grid according to the minimum grid cell, to locate the position of each sensor in the four-dimensional spatiotemporal regular grid, and to use the sensor detection values ​​as the detection data of the sample.

[0093] In some embodiments, the calculation module 30 is used to use distance as a variable in a preset mutation model, the distance including at least the distance between samples and the distance between a sample and a grid cell; and to construct a mutation function based on the variable by combining nugget constant, arch height, sill value, preset range and model parameters, the model parameters being determined by the Euclidean distance and the difference in gas leakage between the data values ​​of valve sensors in the pipeline network on the four-dimensional spatiotemporal regular grid.

[0094] In some embodiments, the calculation module 30 is configured to determine several nearest neighbor samples of any grid cell to be valued in the four-dimensional spatiotemporal regular grid; calculate the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued and the corresponding semivariogram value; determine the weight of the several nearest neighbor samples based on the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued and the corresponding semivariogram value; and determine the gas leakage amount based on the weight and the sensor detection value corresponding to the several nearest neighbor samples.

[0095] In some embodiments, the detection module 40 is used to divide the four-dimensional spatiotemporal rule grid into multiple three-dimensional spatial slices according to time units; query the location where the local gas leakage volume exceeds a threshold on each three-dimensional spatial slice, and filter out low-frequency noise extreme points to obtain the location of the gas leakage source; and predict the spatiotemporal diffusion trend of gas leakage based on the gas leakage volume difference between temporally adjacent three-dimensional spatial slices.

[0096] This application embodiment also provides a gas pipeline leak source location device, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. The memory is used to store computer programs. When the processor executes the program stored in the memory, it implements the above-mentioned gas pipeline leak source location method.

[0097] The communication bus mentioned in the aforementioned gas pipeline leak source locating equipment can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0098] The communication interface is used for communication between the aforementioned gas pipeline leak source locating equipment and other equipment.

[0099] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0100] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0101] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0102] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0104] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0105] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0106] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0107] In addition, for technical details not described in detail in this embodiment, please refer to the gas pipeline leak source location method provided in any embodiment of the present invention, which will not be repeated here.

[0108] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0109] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0111] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0112] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above method.

Claims

1. A method for locating a gas pipeline leak source, characterized in that, The method for locating gas pipeline leak sources includes: Real-time acquisition of operational sample datasets of urban underground gas pipeline networks; Based on statistical principles, the probability of leakage in the city's underground gas pipeline network is determined using the operational sample dataset. When the probability of leakage exceeds a preset probability, interpolation analysis is performed on the operational sample dataset to obtain the amount of gas leakage; The step of performing interpolation analysis on the operational sample dataset to obtain the gas leakage amount includes: Construct a four-dimensional spatiotemporal rule grid for the target monitoring area; The mutation function is determined based on a pre-defined mutation model; The step of determining the mutation function based on a preset mutation model includes: Distance is used as a variable in the preset mutation model, and the distance includes at least the distance between samples and the distance between a sample and a grid cell; Based on the variables, a variability function is constructed by combining the nugget constant, arch height, sill value, preset range and model parameters. The model parameters are determined by the Euclidean distance and the difference in gas leakage between the data values ​​of valve sensors in the pipeline network on the four-dimensional spatiotemporal rule grid. The gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal rule grid is determined according to the variogram function. The step of determining the gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal rule grid based on the variogram includes: Determine several nearest neighbor samples in the four-dimensional spatiotemporal regular grid for any grid cell to be valued. Calculate the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued, and the semivariogram value corresponding to the distance. The weights of the nearest neighbor samples are determined based on the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued and the semivariogram value corresponding to the distance. The amount of gas leakage is determined based on the weights and the sensor detection values ​​corresponding to the nearest neighbor samples. The location of the gas leak source is determined based on the amount of gas leak, and the spatiotemporal diffusion trend of the gas leak is predicted. The step of determining the location of the gas leak source based on the gas leak volume and predicting the spatiotemporal diffusion trend of the gas leak includes: The four-dimensional spatiotemporal rule grid is divided into multiple three-dimensional spatial slices according to time units; On each three-dimensional space slice, query the location where the local gas leakage volume exceeds the threshold, and filter out the low-frequency noise extreme points to obtain the location of the gas leakage source; The spatiotemporal diffusion trend of gas leaks can be predicted based on the difference in gas leak volume between temporally adjacent three-dimensional spatial slices.

2. The gas pipeline leak source location method as described in claim 1, characterized in that, The real-time acquisition of the operational sample dataset of the urban underground gas pipeline network includes: Collect basic data on the urban underground gas pipeline network based on on-site surveys and pipeline design drawings. Data from gas pipeline sensors is collected by the combustible gas monitoring sensors already installed on the gas valves of the urban underground pipeline network. By using histograms to calculate and analyze the distribution patterns of regional changes, and by removing differences in the basic data of the urban underground gas pipeline network and the sensor data of the gas pipeline network, and integrating and unifying them, an operational sample dataset of the urban underground gas pipeline network is obtained.

3. The gas pipeline leak source location method as described in claim 1, characterized in that, The construction of the four-dimensional spatiotemporal rule grid of the target monitoring area includes: The minimum grid cell is determined based on the temporal and spatial resolutions corresponding to the preset requirements. The target detection area is divided into a four-dimensional spatiotemporal regular grid based on the smallest grid unit, and the positions of each sensor in the four-dimensional spatiotemporal regular grid are located. The sensor detection values ​​are used as the detection data of the sample.

4. A gas pipeline leak source locating device, characterized in that, The gas pipeline leak source locating device includes: The data acquisition module is used to acquire operational sample datasets of the urban underground gas pipeline network in real time. The judgment module is used to determine the probability of leakage in the urban underground gas pipeline network based on the running sample dataset according to statistical principles. The calculation module is used to perform interpolation analysis on the running sample dataset when the probability of leakage exceeds a preset probability, so as to obtain the amount of gas leakage; The computing module is further used to construct a four-dimensional spatiotemporal rule grid of the target monitoring area; The mutation function is determined based on a pre-defined mutation model; The step of determining the mutation function based on the preset mutation model includes using distance as a variable in the preset mutation model, wherein the distance includes at least the distance between samples and the distance between a sample and a grid cell; Based on the variables, a variability function is constructed by combining the nugget constant, arch height, sill value, preset range and model parameters. The model parameters are determined by the Euclidean distance and the difference in gas leakage between the data values ​​of valve sensors in the pipeline network on the four-dimensional spatiotemporal rule grid. The gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal rule grid is determined according to the variogram function. The step of determining the gas leakage amount of each grid cell to be valued in the four-dimensional spatiotemporal rule grid based on the variogram includes: Determine several nearest neighbor samples in the four-dimensional spatiotemporal regular grid for any grid cell to be valued. Calculate the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued, and the semivariogram value corresponding to the distance. The weights of the nearest neighbor samples are determined based on the mean of each nearest neighbor sample, the distance between each nearest neighbor sample, the corresponding semivariogram value, and the distance between each nearest neighbor sample and the grid cell to be valued and the semivariogram value corresponding to the distance. The amount of gas leakage is determined based on the weights and the sensor detection values ​​corresponding to the nearest neighbor samples. The detection module is used to determine the location of the gas leak source based on the amount of gas leak and to predict the spatiotemporal diffusion trend of the gas leak. The detection module is further used to divide the four-dimensional spatiotemporal rule grid into multiple three-dimensional spatial slices according to time units; On each three-dimensional space slice, query the location where the local gas leakage volume exceeds the threshold, and filter out the low-frequency noise extreme points to obtain the location of the gas leakage source; The spatiotemporal diffusion trend of gas leaks can be predicted based on the difference in gas leak volume between temporally adjacent three-dimensional spatial slices.

5. The gas pipeline leak source locating device as described in claim 4, characterized in that, The data acquisition module is used to collect basic data of the urban underground gas pipeline network based on the on-site survey and pipeline design drawings of the urban underground pipelines. Data from gas pipeline sensors is collected by the combustible gas monitoring sensors already installed on the gas valves of the urban underground pipeline network. By using histograms to calculate and analyze the distribution patterns of regional changes, and by removing differences in the basic data of the urban underground gas pipeline network and the sensor data of the gas pipeline network, and integrating and unifying them, an operational sample dataset of the urban underground gas pipeline network is obtained.

6. A gas pipeline leak source locating device, characterized in that, The gas pipeline leak source locating device includes: a memory, a processor, and a gas pipeline leak source locating program stored in the memory and executable on the processor, wherein the gas pipeline leak source locating program is configured to implement the steps of the gas pipeline leak source locating method as described in any one of claims 1 to 3.

Images