A method, device and system for judging pipeline leakage
By constructing a statistical function of the pipeline leakage point area, combining the leakage detection data and error terms, the problem of misjudgment of pipeline leakage detection in the existing technology is solved, and more accurate leakage judgment is achieved.
Patent Information
- Application Number
- CN202210472302.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-29
- Publication Date
- 2025-06-24
- Estimated Expiration
- 2042-04-29
AI Technical Summary
There is a possibility of misjudgment in existing pipeline leak detection methods, especially when the actual pipeline system is very noisy and full of uncertainty, the measured transient data and theoretical models cannot match perfectly.
By obtaining multiple sets of pipeline leakage detection data, calculating the maximum area of the leakage point, determining the error term, generating pipeline leakage detection sample data, building an empirical distribution model, performing resampling, generating a leakage point area statistical function, and finally determining whether there is a leakage in the pipeline.
It realizes accurate judgment of whether there is leakage in the pipeline, reduces the misjudgment rate, and by constructing an accurate leakage point area statistical function, it can more effectively reflect the probability characteristics of pipeline leakage.
Smart Images
Figure CN114896877B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to pipeline detection technology, and in particular, to a pipeline leakage judgment method, device and system. Background Art
[0002] Leakage is a major problem in urban water supply systems. According to reports, the direct cost caused by leakage problems reaches $39 billion annually.
[0003] Currently, it is possible to determine whether a pipeline is leaking based on transient analysis methods. This method introduces an active fluid transient wave by creating a rapid perturbation flow (such as quickly closing or opening a valve). The transient wave propagates along the pipeline system. When there is a leak, the transient wave interacts with the leak location, and the transient signal after the interaction is measured by a hydrophone, and then the leak is estimated by matching the measured transient signal with its theoretical model. Since the actual pipeline system is very noisy and full of uncertainties, the measured transient data and the related theoretical model can never be perfectly matched. Therefore, the above method has the possibility of misjudgment. Summary of the Invention
[0004] The present invention provides a pipeline leakage judgment method, device and system to achieve the purpose of accurately judging whether there is a leak in the pipeline.
[0005] In a first aspect, embodiments of the present invention provide a pipeline leakage judgment method, including:
[0006] Obtain multiple groups of pipeline leakage detection data, and calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data;
[0007] Determine error terms corresponding to each group of the pipeline leakage detection data according to the pipeline leakage detection data;
[0008] Obtain a pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error terms;
[0009] Generate an empirical distribution model according to the pipeline leakage detection sample data, and resample the pipeline leakage detection sample data based on the empirical distribution model to generate pipeline leakage detection resampled sample data;
[0010] Generate a pipeline leakage point area statistical value based on the pipeline leakage detection resampled sample data, and generate a pipeline leakage point area statistical function according to the pipeline leakage point area statistical value;
[0011] Determine whether the pipeline is leaking according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function.
[0012] Optionally, determining whether the pipeline leaks according to the maximum pipeline leak point area and the pipeline leak point area statistical function includes:
[0013] Determining the pipeline leak point area detection values included in the pipeline leak point area statistical function;
[0014] If the maximum pipeline leak point area is greater than the pipeline leak point area detection value, it is determined that the pipeline leaks; otherwise, it is determined that the pipeline does not leak.
[0015] Optionally, calculating the maximum pipeline leak point area according to the pipeline leak detection data includes:
[0016] Obtaining the length data of the pipeline, based on the length data, setting a number of virtual leak points at equal intervals on the pipeline, respectively calculating the virtual leak point areas of each virtual leak point, and taking the maximum value of the virtual leak point areas as the maximum pipeline leak point area.
[0017] Optionally, resampling the pipeline leak detection sample data by using the bootstrap method.
[0018] Optionally, determining the pipeline leak point area detection value includes:
[0019] Obtaining a significance parameter, determining the percentile corresponding to the pipeline leak point area statistical function according to the significance parameter, and taking the percentile as the pipeline leak point area detection value.
[0020] Optionally, determining the error terms corresponding to each group of the pipeline leak detection data according to the pipeline leak detection data includes:
[0021] Determining the average pipeline leak detection value according to the pipeline leak detection data, and determining the error terms according to the pipeline leak detection data and the average pipeline leak detection value.
[0022] Optionally, obtaining at least seven groups of the pipeline leak detection data.
[0023] In a second aspect, an embodiment of the present invention further provides a pipeline leak judgment device, including a pipeline leak judgment unit, and the pipeline leak judgment unit is used for:
[0024] Obtaining multiple groups of pipeline leak detection data, and calculating the maximum pipeline leak point area according to the pipeline leak detection data;
[0025] Determining the error terms corresponding to each group of the pipeline leak detection data according to the pipeline leak detection data;
[0026] Obtain a pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error term;
[0027] Generate an empirical distribution model according to the pipeline leakage detection sample data, and based on the empirical distribution model, resample the pipeline leakage detection sample data to generate pipeline leakage detection resampled sample data;
[0028] Generate a pipeline leakage point area statistical value based on the pipeline leakage detection resampled sample data, and generate a pipeline leakage point area statistical function according to the pipeline leakage point area statistical value;
[0029] Determine whether the pipeline leaks according to the maximum pipeline leakage point area and the pipeline leakage point area statistical function.
[0030] In a third aspect, an embodiment of the present invention further provides a pipeline leakage judgment system, including a controller, and the controller is configured with an executable program, and when the executable program runs, it implements the pipeline leakage judgment method described in the embodiment of the present invention.
[0031] Optionally, it further includes a controllable valve and at least one transient wave sampling sensor;
[0032] The controllable valve and the transient wave sampling sensor are arranged on the pipeline, the controllable valve is used to generate a transient wave, and the sampling data of the transient wave sampling sensor is used as pipeline leakage detection data.
[0033] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes a pipeline leakage judgment method, which mainly includes: determining the maximum pipeline leakage point area, and taking the pipeline position corresponding to the maximum pipeline leakage point area as a hypothetical leakage point; determining the pipeline leakage point area statistical function, and determining whether the hypothetical leakage point is a real leakage point according to the maximum pipeline leakage point area and the pipeline leakage point area statistical function. Among them, when constructing the pipeline leakage point area statistical function, first generate an empirical distribution model according to a small amount of pipeline leakage detection sample data, and then expand the capacity of the sample data by resampling, so as to obtain a more accurate pipeline leakage point area statistical function that can reflect the probability characteristics of pipeline leakage. Based on this pipeline leakage point area statistical function, the purpose of accurately judging whether the pipeline leaks can be finally achieved. Description of the Drawings
[0034] Figure 1 is the flow chart of the pipeline leakage judgment method in the embodiment;
[0035] Figure 2 is the flow chart of a leakage judgment method in the embodiment;
[0036] Figure 3It is the histogram of the area of the pipeline leakage point in the embodiment;
[0037] Figure 4 It is the block diagram of the electronic device structure in the embodiment. Detailed implementation manners
[0038] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. In addition, it should be noted that for the convenience of description, only parts related to the present invention rather than all structures are shown in the drawings.
[0039] Embodiment 1
[0040] Figure 1 It is the flowchart of the pipeline leakage judgment method in the embodiment. Refer to Figure 1 , the pipeline leakage judgment method includes:
[0041] S101. Obtain multiple groups of pipeline leakage detection data, and calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data.
[0042] Exemplarily, in this embodiment, it is determined whether the pipeline leaks based on the pipeline leakage detection signal. The pipeline leakage detection signal can be generated by means of a switching device (such as a controllable valve). The pipeline leakage detection signal can propagate in the pipeline, and the signal obtained by the sensor installed on the pipeline after propagating through the pipeline is used as the pipeline leakage detection data.
[0043] Exemplarily, in this embodiment, any method in the prior art can be used to determine the virtual leakage points of the pipeline, and then determine the areas of the respective virtual leakage points. The maximum value of the areas is used as the maximum value of the pipeline leakage point area.
[0044] Exemplarily, in an implementable solution, calculating the maximum value of the pipeline leakage point area according to the pipeline leakage detection data includes:
[0045] Obtain the length data of the pipeline. Based on the length data, set a number of virtual leakage points at equal intervals on the pipeline, calculate the virtual leakage point areas of each virtual leakage point respectively, and use the maximum value of the virtual leakage point areas as the maximum value of the pipeline leakage point area.
[0046] Specifically, in the above solution, the inverse transient analysis (ITA, inverse transient analysis) method can be used to determine the maximum value of the pipeline leakage point area;
[0047] When using the quasi-inverse transient analysis method, set K points at equal intervals along the length direction of the pipeline, use each point as a virtual leakage point, and calculate the areas of the virtual leakage points respectively.
[0048] Exemplarily, to meet the accuracy requirements of subsequent calculations, in this embodiment, at least seven groups of pipeline leakage detection data are obtained.
[0049] S102. Determine the error term corresponding to each group of pipeline leakage detection data according to the pipeline leakage detection data.
[0050] Exemplarily, in this embodiment, it is assumed that a total of N groups of pipeline leakage detection data are obtained, and each group of pipeline leakage detection data is represented by the following formula:
[0051] h n = h mod + e n , n = 1, …, N
[0052] In the above formula, h mod represents the theoretical transient model of the pipeline leakage detection signal, and e n represents the random error term.
[0053] In this embodiment, the error term corresponding to each group of pipeline leakage detection data is e n . When determining this error term, the obtained pipeline leakage detection data is averaged, and each error term is calculated based on the average value, that is, this error term is determined in the following manner:
[0054]
[0055]
[0056] In the above formula, h n is the obtained pipeline leakage detection data, and N is the number of groups of pipeline leakage detection data.
[0057] S103. Obtain a pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error term.
[0058] Exemplarily, in this embodiment, it is assumed that the pipeline leakage detection sample is represented by the following formula:
[0059]
[0060] In the above formula, is the pipeline model, and e n is the error term determined in step S102.
[0061] Exemplarily, in this embodiment, it is assumed that the pipeline model is a known term, which represents the theoretical transient model of the pipeline leakage detection signal when the pipeline has no leakage.
[0062] Exemplarily, the theoretical transient model It may or may not include the uncertainty u, where, for a pipeline, the uncertainty u is a fixed value.
[0063] Exemplarily, a theoretical transient model is set When not including the uncertainty u, the theoretical transient model can be determined in the following manner
[0064] Obtain the basic information of the pipeline, including pipeline length, wall thickness, boundary conditions, flow velocity, etc., and determine the above-mentioned theoretical transient model through numerical simulation (MOC, Method Of Characteristics)
[0065] Exemplarily, a theoretical transient model is set When including the uncertainty u, the theoretical transient model can be determined in the following manner
[0066] After the pipeline system is built and there is no leakage in the pipeline, perform a transient test, or obtain a reference signal through regular pipeline condition monitoring, and represent the theoretical transient model using a mathematical expression corresponding to the reference signal
[0067] Exemplarily, take the value corresponding to the pipeline leakage detection sample as the pipeline leakage detection sample data, where the number of pipeline leakage detection sample data is the same as the number of pipeline leakage detection data, which is N.
[0068] S104. Generate an empirical distribution model based on the pipeline leakage detection sample data, and resample the pipeline leakage detection sample data based on the empirical distribution model to generate pipeline leakage detection resampled sample data.
[0069] Exemplarily, N pipeline leakage detection sample data are obtained in step S103 Then determining the empirical distribution model includes:
[0070] Determine the class interval through the pipeline leakage detection sample data, determine the segmented distribution interval of the empirical distribution model according to the class interval, and determine the pipeline leakage detection sample data falling into each segmented distribution interval;
[0071] Construct an empirical distribution model according to the segmented distribution interval and the pipeline leakage detection sample data falling into each segmented distribution interval.
[0072] Exemplarily, the empirical distribution model is defined as a discrete distribution. In this discrete distribution function, each has a probability of 1 / N, and when N approaches infinity, it converges with probability 1. Set the empirical distribution model as Then the distribution model can be expressed by the following formula:
[0073]
[0074] In the above formula, N is the number of pipeline leakage detection sample data , and K i is the number of pipeline leakage detection sample data falling into the corresponding segmented distribution interval.
[0075] In this step, after constructing the empirical distribution model, based on the empirical distribution model (including the segmented distribution interval and the corresponding probability), resampling is performed on the pipeline leakage detection sample data to generate pipeline leakage detection resampled sample data.
[0076] Exemplarily, in this embodiment, the resampling is sampling with replacement, that is, a pipeline leakage detection sample data can be repeatedly sampled more than once.
[0077] In this embodiment, the specific method of resampling is not limited. In one possible implementation, the bootstrap method can be used to resample the pipeline leakage detection sample data.
[0078] Combined with the content described in steps S102 to S104, the construction method of the empirical distribution model proposed based on this embodiment can avoid the following problems:
[0079] When directly determining the distribution function based on the pipeline leakage detection data h n , it is necessary to know the distribution of the random error e n . Due to the complexity of the random error e n in terms of high dimension and interdependence (that is, in addition to environmental noise, the randomness of the random error also comes from the generation of transient waves and pump noise), it is difficult to model and analyze the random error e n ;
[0080] The sample size of the pipeline leakage detection data h n is very limited (because it takes several minutes for the transient wave generated during one test to completely disappear, and the next test cannot be started before that. Frequent multiple tests have the risk of causing pipeline structure fatigue and may cause interruption of water supply services), making it difficult to numerically approximate the distribution of the random error e n .
[0081] S105. Based on the pipeline leakage detection resampled sample data, generate a pipeline leakage point area statistical value, and generate a pipeline leakage point area statistical function according to the pipeline leakage point area statistical value.
[0082] Exemplarily, in this step, the pipeline leakage detection resampled sample data is denoted as which contains m pipeline leakage detection resampled sample data, that is:
[0083]
[0084] In this step, the method for calculating the area of the pipeline leakage point based on the resampled sample data for pipeline leakage detection is the same as that described in step S101, that is, based on the resampled sample data for pipeline leakage detection, the area of each virtual leakage point is calculated separately.
[0085] Exemplarily, in this step, the set of the areas of each calculated virtual leakage point is used as the statistical value of the pipeline leakage point area.
[0086] Exemplarily, in this step, the pipeline leakage point area statistical function is a form of distribution function (such as the empirical distribution function), and the method for determining the above distribution function is not specifically limited in this embodiment.
[0087] S106. Determine whether the pipeline leaks according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function.
[0088] Exemplarily, in this embodiment, based on the pipeline leakage point area statistical function, it can be determined whether the pipeline leaks through statistical methods such as hypothesis testing (including one-sided hypothesis testing and two-sided hypothesis reduction).
[0089] For example, on the premise of a given significance level, the original hypothesis is set as:
[0090]
[0091] In the above formula is the maximum value of the area of the virtual leakage point determined based on the pipeline leakage point area statistical function at a given significance level;
[0092] If the maximum value S of the pipeline leakage point area max satisfies the above conditions, the original hypothesis is accepted, that is, the pipeline does not leak, otherwise the original hypothesis is rejected, that is, the pipeline leaks.
[0093] This embodiment proposes a pipeline leakage judgment method, which mainly includes: determining the maximum value of the pipeline leakage point area, and taking the pipeline position corresponding to the maximum value of the pipeline leakage point area as the assumed leakage point; determining the pipeline leakage point area statistical function, and determining whether the assumed leakage point is a real leakage point according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function. Among them, when constructing the pipeline leakage point area statistical function, first generate an empirical distribution model according to a small amount of pipeline leakage detection sample data, and then expand the capacity of the sample data by resampling, so as to obtain a more accurate pipeline leakage point area statistical function that can reflect the probability characteristics of pipeline leakage. Based on this pipeline leakage point area statistical function, the purpose of accurately judging whether the pipeline leaks can be finally achieved.
[0094] Figure 2 It is a flowchart of a leakage judgment method in an embodiment. Refer to Figure 2 , based on the content recorded in step S106, in an implementable solution, determining whether there is a leakage in the pipeline according to the maximum pipeline leakage point area and the pipeline leakage point area statistical function includes:
[0095] S1061. Determine the pipeline leakage point area detection value included in the pipeline leakage point area statistical function.
[0096] Exemplarily, in this solution, the bootstrap method is used to resample the pipeline leakage detection sample data to obtain the pipeline leakage detection resampled sample data;
[0097] Determine the maximum pipeline sample leakage point area according to the pipeline leakage detection resampled sample data, and determine the pipeline leakage point area statistical function according to the maximum pipeline sample leakage point area.
[0098] Exemplarily, when setting the resampling by the bootstrap method, repeat the resampling for B rounds, and the number of new sample data extracted in each round is m, then the pipeline leakage detection resampled sample data is That is:
[0099]
[0100]
[0101] For each item The area of the set virtual leakage point can be calculated, and the maximum value among them is recorded as a maximum pipeline sample leakage point area, that is:
[0102]
[0103] In the above formula, k represents the number of areas of the virtual leakage points.
[0104] Through the above operations, a total of B maximum pipeline sample leakage point areas can be obtained, and the numerical set containing B maximum pipeline sample leakage point areas is denoted as S V* , that is:
[0105]
[0106] In this embodiment, the numerical set S V* is sorted in ascending order, and the sorted data set is used as the pipeline leakage point area statistical function.
[0107] Exemplarily, in this solution, the pipeline leakage point area detection value is used to represent the maximum pipeline sample leakage point area that meets the set conditions in the pipeline leakage point area statistical function.
[0108] Specifically, in this solution, determining the detection value of the pipeline leakage point area includes:
[0109] Obtain the significance parameter, determine the percentile corresponding to the pipeline leakage point area statistical function according to the significance parameter, and use the percentile as the detection value of the pipeline leakage point area.
[0110] For example, if the significance parameter a is set to 0.05, then determine the (1 - a) percentile in the pipeline leakage point area statistical function, that is, use the maximum value of the pipeline sample leakage point area at the 95% position in the pipeline leakage point area statistical function as the detection value of the pipeline leakage point area.
[0111] S1062. If the maximum value of the pipeline leakage point area is greater than the detection value of the pipeline leakage point area, it is determined that the pipeline has leaked; otherwise, it is determined that the pipeline has not leaked.
[0112] Exemplarily, in this solution, the null hypothesis is set as:
[0113] H0: The pipeline has no leakage
[0114] Set the detection value of the pipeline leakage point area as Set the maximum value of the pipeline leakage point area as S max , then if it satisfies The null hypothesis is accepted; otherwise, the null hypothesis is rejected.
[0115] Figure 3 is the statistical histogram of the pipeline leakage point area in the embodiment. Refer to Figure 3 , Figure 3 In the shown solution, the number of groups of pipeline leakage detection data is 9. It is set to use the bootstrap method for resampling, and the number of new resampled samples is 1000.
[0116] Figure 3 In, the abscissa represents the maximum value of the pipeline sample leakage point area, the ordinate represents the quantity, the dotted line in the figure represents the detection value of the pipeline leakage point area, and the circle represents the maximum value of the pipeline leakage point area.
[0117] Specifically, Figure 3 In (a), (b), (c), and (d) parts respectively represent the statistical histograms of the pipeline leakage point area under 40% leakage, 20% leakage, 10% leakage, and no leakage. The pipeline leakage point area statistical functions corresponding to each histogram are determined separately.
[0118] Exemplarily, it is set that when the ratio of the leakage point flow rate to the main pipeline flow rate is 40%, it is 40% leakage; when it is 20%, it is 20% leakage; when it is 10%, it is 10% leakage; and when it is 0%, it is no leakage.
[0119] Combined withFigure 3 , in the first three cases, the maximum value of the pipeline leakage point area is greater than the detected value of the pipeline leakage point area. In the fourth case, the maximum value of the pipeline leakage point area is less than the detected value of the pipeline leakage point area. Based on this, this solution can accurately determine whether there is a leakage in the pipeline under a given significance level.
[0120] Exemplarily, as an implementable solution, it is also possible to determine whether there is a leakage in the pipeline in the following way:
[0121] Obtain multiple sets of pipeline leakage detection data, calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data, and take the pipeline position corresponding to the maximum value of the pipeline leakage point area as the leakage point.
[0122] Exemplarily, in this solution, the set of pipeline leakage detection data is set as h, and h is represented by the following formula:
[0123] h = {h i , i = 1,...N}
[0124] In the above formula, N is the number of groups of pipeline leakage detection data. Generally, N < 10.
[0125] When judging whether there is a leakage in the pipeline through the pipeline leakage detection data, along the length direction of the pipeline, the pipeline is discretized into K points, and the leakage magnitudes of the K points are calculated respectively and denoted as S. S is represented by the following formula:
[0126] S = {S i , i = 1,...K, S i ≥0}
[0127] In this solution, the null hypothesis in the hypothesis test is set as:
[0128] H0: S = 0
[0129] If the leakage magnitude of each point is 0, the null hypothesis is accepted, that is, it is judged that there is no leakage in the pipeline. Otherwise, the pipeline position corresponding to the maximum value of the pipeline leakage point area is taken as the leakage point.
[0130] There are certain defects in the above method, and it cannot accurately judge whether there is a leakage in the pipeline in some cases. The reason is:
[0131] Generally, the general form of pipeline leakage detection data can be represented by the following formula:
[0132] h = h mod +u+e
[0133] In the above formula, h modLet \(h\) represent the theoretical model, \(u\) represent the model error, and \(e\) represent the random error. Due to the existence of uncertain factors, the measured data (pipeline leakage detection data) does not exactly match the above formula;
[0134] When calculating the leakage size of discrete points on the pipeline, it is mainly based on the theoretical model \(h\) mod After the calculation is completed, therefore, based on the level of uncertainty of the model error and the random error, in some cases, even if the pipeline has no leakage, the leakage size \(S\) may still have a positive value.
[0135] Embodiment 2
[0136] This embodiment proposes a pipeline leakage judgment device, including a pipeline leakage judgment unit, and the pipeline leakage judgment unit is used for:
[0137] Obtain multiple groups of pipeline leakage detection data, and calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data;
[0138] Determine the error term corresponding to each group of pipeline leakage detection data according to the pipeline leakage detection data;
[0139] Obtain the pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error term;
[0140] Generate an empirical distribution model according to the pipeline leakage detection sample data, and based on the empirical distribution model, resample the pipeline leakage detection sample data to generate pipeline leakage detection resampled sample data;
[0141] Generate a pipeline leakage point area statistical value based on the pipeline leakage detection resampled sample data, and generate a pipeline leakage point area statistical function according to the pipeline leakage point area statistical value;
[0142] Determine whether the pipeline has a leakage according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function.
[0143] In this embodiment, the pipeline leakage judgment unit can determine whether the pipeline has a leakage in any one of the ways described in Embodiment 1, and its specific process and beneficial effects will not be elaborated here.
[0144] Embodiment 3
[0145] This embodiment proposes a pipeline leakage judgment system, including a controller, and the controller is configured with an executable program. When the executable program runs, it implements any one of the pipeline leakage judgment methods described in Embodiment 1.
[0146] It also includes a controllable valve and at least one transient wave sampling sensor. The controllable valve and the transient wave sampling sensor are arranged on the pipeline. The controllable valve is used to generate a transient wave, and the sampling data of the transient wave sampling sensor is used as the pipeline leakage detection data.
[0147] Exemplarily, the transient wave is generated by suddenly closing a controllable valve configured on the pipeline, where the valve closing time of the controllable valve is less than 0.05 seconds.
[0148] Exemplarily, in an implementable embodiment, the pipeline leakage judgment method may also be stored in an electronic device, and the electronic device includes:
[0149] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute any one of the pipeline leakage judgment methods described in Embodiment 1.
[0150] Figure 4 The structural schematic diagram of the electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.
[0151] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Wherein, the memory stores a computer program executable by the at least one processor, and the processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.
[0152] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0153] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the pipeline leakage judgment method.
[0154] In some embodiments, the pipeline leakage judgment method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the pipeline leakage judgment method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the pipeline leakage judgment method by any other suitable means (e.g., by means of firmware).
[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs, the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a dedicated or general-purpose programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.
[0156] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0157] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0158] In order to provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, speech input, or tactile input).
[0159] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.
[0160] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact via a communication network. The client-server relationship is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.
[0161] Note that the above are only the preferred embodiments of the present invention and the applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, it can also include more other equivalent embodiments, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for judging pipeline leakage, characterized in that, Including: Obtain multiple sets of pipeline leakage detection data, and calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data; Determine the error terms corresponding to each set of the pipeline leakage detection data according to the pipeline leakage detection data; Obtain a pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error terms; Generate an empirical distribution model according to the pipeline leakage detection sample data, and resample the pipeline leakage detection sample data based on the empirical distribution model to generate pipeline leakage detection resampled sample data; Generate a pipeline leakage point area statistical value based on the pipeline leakage detection resampled sample data, and generate a pipeline leakage point area statistical function according to the pipeline leakage point area statistical value; Determine whether the pipeline leaks according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function; The distribution model is represented by the following formula: In the above formula, N is the pipeline leakage detection sample data quantity, and K i is the quantity of pipeline leakage detection sample data falling into the corresponding segmented distribution interval, representing the segmented distribution interval of the empirical distribution model; Determining whether the pipeline leaks according to the maximum value of the pipeline leakage point area and the pipeline leakage point area statistical function includes: Determine the pipeline leakage point area detection values included in the pipeline leakage point area statistical function; If the maximum value of the pipeline leakage point area is greater than the pipeline leakage point area detection value, it is determined that the pipeline leaks, otherwise it is determined that the pipeline does not leak.
2. The pipeline leakage judgment method according to claim 1, wherein Calculating the maximum value of the pipeline leakage point area according to the pipeline leakage detection data includes: Obtain the length data of the pipeline, and based on the length data, set a number of virtual leakage points at equal intervals on the pipeline, calculate the virtual leakage point area of each virtual leakage point respectively, and use the maximum value of the virtual leakage point areas as the maximum value of the pipeline leakage point area.
3. The pipeline leakage judgment method according to claim 1, characterized in that Resample the pipeline leakage detection sample data by using the bootstrap method.
4. The pipeline leakage judgment method according to claim 1, characterized in that Determining the pipeline leakage point area detection value includes: Obtain a significance parameter, determine the percentile corresponding to the pipeline leakage point area statistical function according to the significance parameter, and use the percentile as the pipeline leakage point area detection value.
5. The pipeline leakage judgment method according to claim 1, wherein Determining the error terms corresponding to each set of the pipeline leakage detection data according to the pipeline leakage detection data includes: Determine the average value of pipeline leakage detection according to the pipeline leakage detection data, and determine the error terms according to the pipeline leakage detection data and the average value of pipeline leakage detection.
6. The pipeline leakage judgment method according to claim 1, wherein Obtain at least seven sets of the pipeline leakage detection data.
7. A pipeline leakage judgment device, characterized in that, Including a pipeline leakage judgment unit, and the pipeline leakage judgment unit is used for: Obtain multiple sets of pipeline leakage detection data, and calculate the maximum value of the pipeline leakage point area according to the pipeline leakage detection data; Determine the error terms corresponding to each set of the pipeline leakage detection data according to the pipeline leakage detection data; Obtain a pipeline model, and generate pipeline leakage detection sample data according to the pipeline model and the error terms; Generate an empirical distribution model according to the pipeline leakage detection sample data, and resample the pipeline leakage detection sample data based on the empirical distribution model to generate pipeline leakage detection resampled sample data; Generate a statistical value of the pipeline leakage point area based on the resampled sample data for pipeline leakage detection, and generate a statistical function of the pipeline leakage point area according to the statistical value of the pipeline leakage point area; Determine whether the pipeline leaks according to the maximum pipeline leakage point area and the statistical function of the pipeline leakage point area; The distribution model is represented by the following formula: In the above formula, N is the number of pipeline leakage detection sample data , K i is the number of pipeline leakage detection sample data falling into the corresponding segmented distribution interval, represents the segmented distribution interval of the empirical distribution model; Determining whether the pipeline leaks according to the maximum pipeline leakage point area and the statistical function of the pipeline leakage point area includes: Determine the detected value of the pipeline leakage point area included in the statistical function of the pipeline leakage point area; If the maximum pipeline leakage point area is greater than the detected value of the pipeline leakage point area, it is determined that the pipeline leaks, otherwise it is determined that the pipeline does not leak.
8. A pipeline leakage judgment system, characterized in that, It includes a controller, and the controller is configured with an executable program, and when the executable program runs, it implements the pipeline leakage judgment method according to any one of claims 1 to 6.
9. The pipeline leakage judgment system according to claim 8, wherein It further includes a controllable valve and at least one transient wave sampling sensor; The controllable valve and the transient wave sampling sensor are arranged on the pipeline, the controllable valve is used to generate a transient wave, and the sampling data of the transient wave sampling sensor is used as pipeline leakage detection data.
Citation Information
Patent Citations
Pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF synergy
CN106018545A
Method for predicting mechanical seal leakage failure of in-service rotating equipment
CN109325629A