Leakage identification method and device for multi-heat source annular pipe network

Abstract

The present invention discloses a method and device for identifying leakage in a multi-heat source annular pipe network. The method for identifying leakage in a multi-heat source annular pipe network comprises: calculating the energy characteristic component of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which characterizes the oscillation law of the pressure numerical signal, as a sample to be classified; identifying the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipe network, and determining the location of the leakage point based on the obtained leakage condition category. The multi-heat source annular pipe network leakage identification technology of the present invention is based on a pre-established pipe network leakage data set for identification. When a leakage occurs in a multi-heat source annular pipe network, only the pressure monitoring data of each thermal power station is used to locate the leakage point in a relatively short time.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic pipe network leakage identification, and in particular to a method and device for identifying leakage of a multi-heat source annular pipe network. Background Art

[0002] As the urbanization process continues to accelerate, the scale of urban heating continues to rise, and the structure of the heating network has become more complex. At the same time, with the concept of "one network for the city", more and more small independent branch networks are integrated into a large complex multi-heat source ring network, which is uniformly dispatched and managed by the command center, which puts higher requirements on the operation and maintenance level of heating. For the operation of the heating network, pipeline leakage is a very serious problem. At the least, it affects the downstream heating effect and causes heating to stop, and at the worst, it causes equipment damage, flooding of station buildings and other safety accidents. Therefore, when a leak occurs in the pipeline network, in order to carry out emergency rescue in a timely manner, rapid identification and detection of the leak location is a very important link.

[0003] Among the commonly used methods for identifying pipeline leaks, fiber optic detection requires excavation of the land to lay the optical fiber on the outer wall of the pipeline, which has a high construction cost; infrared thermal imaging is generally based on relatively mature drones and image processing technologies, and it is difficult to achieve rapid positioning for urban-level pipelines that lack base stations or are large in scale; the negative pressure wave method is mainly used for long-distance pipelines or small branch pipelines, and cannot accurately identify the location of leaks in complex ring networks with multiple heat sources. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings and defects of the prior art and to provide a method and device for identifying leakage in a multi-heat source annular pipe network by direct monitoring by non-physical means, so as to realize pipe network leakage diagnosis by utilizing big data algorithms; it is suitable for scenarios where leakage diagnosis is performed when the pipeline leakage location cannot be found on-site by optical fiber detection, infrared thermal imaging, etc., and is particularly suitable for leakage diagnosis of complex multi-heat source annular networks.

[0005] A first aspect of the present invention provides a method for identifying leakage in a multi-heat source annular pipe network, comprising the steps of:

[0006] Calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which represents the oscillation law of the pressure numerical signal, as the sample to be classified;

[0007] The leakage condition closest to the condition of the sample to be classified is identified from the data set samples as the category of the current leakage condition of the pipeline network, and the leakage point location is determined based on the obtained leakage condition category.

[0008] Among them, the empirical mode decomposition method is used to calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source ring pipeline network, which characterizes the oscillation law of the pressure numerical signal.

[0009] The empirical mode decomposition method is used to calculate the energy characteristic component of the oscillation law of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, including:

[0010] S21. Obtaining the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source loop network;

[0011] S22. Generate an upper envelope and a lower envelope of the pressure numerical signal using a cubic spline function curve, and calculate and obtain a mean curve of the upper envelope and the lower envelope;

[0012] S23. Calculate the difference curve between the pressure numerical signal and the mean curve;

[0013] S24. Determine whether the difference curve meets the preset conditions of the intrinsic mode function component. If so, execute step S25. Otherwise, take the difference curve as a new pressure numerical signal and return to step S22 for recalculation.

[0014] S25. Using the difference curve as the intrinsic mode function component of the pressure numerical signal, and calculating the residual between the pressure numerical signal and the intrinsic mode function component;

[0015] S26. Determine whether the residual has reached the convergence condition. If so, proceed to step S27. Otherwise, take the residual as a new pressure numerical signal and return to step S22 for recalculation.

[0016] S27. Calculate the energy characteristic component carried by each eigenmode function component and normalize it as the energy characteristic component of the eigenmode function component of the thermal power station pressure numerical signal.

[0017] The preset conditions include: the number of local extreme points and zero-crossing points is equal, and the average value of the upper envelope of the local maximum value and the lower envelope of the local minimum value is 0.

[0018] The step of calculating the energy characteristic component carried by each eigenmode function component and normalizing the energy characteristic component includes:

[0019] The energy characteristic component carried by each eigenmode function component is calculated using the following formula:

[0020] ,

[0021] The following formula is used for normalization to obtain the normalized energy characteristic component: :

[0022] ,

[0023] In the formula, Indicates The energy characteristic component carried by the intrinsic mode function component, n represents the number of numerical points of the pressure numerical signal in the intrinsic mode function component, Indicates The first eigenmode function component The amplitude of the pressure value signal value point, Indicates the number of energy characteristic components.

[0024] The K-nearest neighbor algorithm is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network.

[0025] The step of using the K nearest neighbor algorithm to identify the leakage condition closest to the condition of the sample to be classified from the data set samples includes:

[0026] Calculate the Euclidean distance between the sample to be classified and the sample in the data set;

[0027] Determine the working condition category to which the K data set samples with the closest Euclidean distance to the sample to be classified belong;

[0028] The operating condition category that appears most frequently in the K data set samples is taken as the category of the current leakage condition of the pipeline network.

[0029] Wherein, the Euclidean distance is expressed as follows:

[0030] ;

[0031] In the formula, D represents the sample to be classified With the dataset sample The Euclidean distance of Represents the sample dimension.

[0032] A second aspect of the present invention provides a multi-heat source annular pipe network leakage identification device, comprising:

[0033] A feature extraction module is used to calculate the energy characteristics of the oscillation law of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, as a sample to be classified;

[0034] The leakage identification module is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network, and determine the leakage point location based on the obtained leakage condition category.

[0035] According to a third aspect of the present invention, there is provided a device for identifying leakage in a multi-heat source annular pipe network, comprising a memory and a processor, wherein the memory is used to store a method program supporting execution of the processor, and the processor is configured to execute the program stored in the memory to implement the multi-heat source annular pipe network leakage identification method.

[0036] The multi-heat source annular pipe network leakage identification method of the present invention, when a leakage actually occurs at an unknown position of the multi-heat source annular pipe network, extracts the energy characteristics of the oscillation law of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the leakage condition as the sample to be classified, and then through classification and identification, identifies the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipe network and the leakage point location, so as to judge the area or pipe section where the leakage may exist.

[0037] Among them, the data set sample is constructed by obtaining the pressure numerical signal when leakage occurs at different positions of the multi-heat source ring pipeline network through actual monitoring means or simulation means, and then extracting the energy characteristics of the oscillation law of the pressure numerical signal from the intrinsic mode function component of the pressure numerical signal, including a variety of different leakage conditions, and each leakage condition corresponds to an energy characteristic component.

[0038] The multi-heat source annular pipe network leakage identification method of the present invention is based on a previously established pipe network leakage data set for identification. When a leakage occurs in the multi-heat source annular pipe network, the leakage point can be located in a relatively short time by using only the pressure monitoring data of each thermal power station.

[0039] Compared with the current optical fiber or thermal imaging methods, it has lower application costs, and compared with the negative pressure wave method, it can be more effectively applied to multi-heat source ring pipe networks, providing strong support for emergency rescue work in heating pipe networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a leakage schematic diagram of the multi-heat source annular pipe network of the present invention.

[0041] Figure 2 It is a flow chart of the multi-heat source annular pipe network leakage identification method of the present invention.

[0042] Figure 3 It is a flow chart of calculating the energy characteristic component of the pressure numerical signal of the present invention.

[0043] Figure 4 The present invention is a flow chart of using the K-nearest neighbor algorithm to identify leakage conditions.

[0044] Figure 5 It is a schematic diagram of a multi-heat source annular pipe network leakage identification device of the present invention.

[0045] Figure 6 This is a schematic diagram of another multi-heat source annular pipe network leakage identification device invented DETAILED DESCRIPTION

[0046] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The structure of the multi-heat source annular pipe network in the present invention is as follows Figure 1 As shown, there are two heat sources and multiple heat stations. The two heat sources are connected to the multiple heat stations through a pipeline network. During the operation of the pipeline network, leakage conditions may occur, corresponding to the following Figure 1 The location of the leak is shown.

[0048] The multi-heat source annular pipe network leakage identification method of the present invention, when leakage actually occurs, extracts the energy characteristic component of the intrinsic mode function component of the pressure numerical signal of the current force station as the sample to be classified, and then based on the comparison of the energy characteristic component, identifies the working condition in the sample to be classified that is closest to the current leakage scenario from the pre-established data set as the current leakage position of the multi-heat source annular pipe network, thereby realizing the rapid positioning of the leakage point of the multi-heat source annular pipe network.

[0049] See also Figure 2 As shown, in a first aspect of the present invention, a method for identifying leakage in a multi-heat source annular pipe network is provided, comprising the following steps:

[0050] S1. Calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which represents the oscillation law of the pressure numerical signal, as the sample to be classified;

[0051] S2. Identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network, and determine the leakage point location based on the obtained leakage condition category.

[0052] The leakage condition refers to the distribution of the pressure numerical signal of the thermal power station when leakage occurs at different positions of the multi-heat source ring pipe network. Different leakage conditions are a leakage condition category, and a leakage at one position of the multi-heat source ring pipe network will correspond to a leakage condition category.

[0053] In the present invention, the data set sample is constructed by obtaining the pressure numerical signal when leakage occurs at different positions of the multi-heat source annular pipeline network through actual monitoring means or simulation means, and then extracting the energy characteristic component of the intrinsic mode function component of the pressure numerical signal that characterizes the oscillation law of the pressure numerical signal, including data sets of multiple different leakage conditions, and each leakage condition corresponds to an energy characteristic component.

[0054] The intrinsic mode function component reflects the relationship between the frequency and amplitude of the pressure numerical signal during the oscillation process and the time variation.

[0055] Among them, when constructing the data set, the empirical mode decomposition method is used to process the pressure numerical signal, decompose the pressure numerical signal into several intrinsic mode function components, and then calculate the energy characteristic components of the intrinsic mode function components that characterize the oscillation law of the pressure numerical signal. Finally, a data set sample based on the intrinsic mode function components under leakage at different positions of the multi-heat source ring pipeline network is formed for subsequent classification and identification.

[0056] Empirical mode decomposition is often used to process various data signals. After decomposition, several intrinsic mode function components that make up the signal can be obtained. The energy characteristic components of the eigenmode function components can be used to characterize the oscillation law of the signal. In the present invention, when the pressure numerical signal of the leakage condition is extracted by using the empirical mode decomposition method, the energy characteristic components of its eigenmode function components are obtained, and a leakage condition category data set is established as a data set sample. Figure 3 As shown, the specific process is as follows:

[0057] S21: Obtaining the pressure numerical signal of the multi-heat source loop network thermal power station under leakage conditions ;

[0058] S22: Generate pressure numerical signal using cubic spline function curve The upper and lower envelopes of the curve are calculated to obtain the mean curve of the upper and lower envelopes. ;

[0059] S23: Calculate and obtain the difference curve between the current pressure value signal and the envelope mean value ;

[0060] ;

[0061] S24: Determine the difference curve Whether the preset conditions of the eigenmode function components are met, if so, continue to S5, if not, the difference curve As a new pressure value signal, it is input into step S22 for recalculation;

[0062] S25: The current difference curve As the intrinsic mode function component of the pressure numerical signal , calculate the pressure value signal and the eigenmode function components The residual ;

[0063] S26: Determine the residual Whether the convergence condition has been met, if it is met, continue with step 27, if not, the residual As a new pressure value signal, it is input into step S22 and recalculated;

[0064] S27: Calculate the energy characteristic component carried by each eigenmode function component, and perform normalization processing to finally obtain the required energy characteristic component, which represents the fluctuation characteristics of the eigenmode function component of the thermal power station pressure numerical signal.

[0065] The preset conditions of the intrinsic mode function components are as follows: the number of local extreme points and zero-crossing points is equal, and the average values ​​of the upper envelope of the local maximum value and the lower envelope of the local minimum value are 0.

[0066] The step of calculating the energy characteristic component carried by each eigenmode function component and normalizing the energy characteristic component includes:

[0067] The energy characteristic component carried by each eigenmode function component is calculated using the following formula:

[0068] ,

[0069] The following formula is used for normalization to obtain the normalized energy characteristic component: :

[0070] ,

[0071] In the formula, Indicates The energy characteristic component carried by the intrinsic mode function component, n represents the number of numerical points of the pressure numerical signal in the intrinsic mode function component, Indicates The first eigenmode function component The amplitude of the pressure value signal value point, Represents the number of energy characteristic components; the denominator in the normalization process is calculated The square root of the sum of the squares is The second norm of .

[0072] In the present invention, the K nearest neighbor algorithm is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category and leakage point location of the current leakage condition of the pipeline network.

[0073] That is, after obtaining the energy characteristic components of the intrinsic mode function components of the historical leakage conditions and the current leakage conditions of the multi-heat source ring pipe network, the K nearest neighbor algorithm can be used to identify which historical leakage condition category the current leakage condition belongs to, and further determine the leakage point location.

[0074] Wherein, the K nearest neighbor algorithm is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples, see Figure 4 As shown, including:

[0075] S31. Calculate the Euclidean distance between the sample to be classified and the sample in the data set;

[0076] S32. confirming the working condition categories to which the K data set samples with the closest Euclidean distance to the sample to be classified belong;

[0077] S33. The operating condition category that appears most frequently in the K data set samples is used as the category of the current leakage condition of the pipeline network.

[0078] Wherein, the Euclidean distance is expressed as follows:

[0079] ;

[0080] In the formula, D represents the sample to be classified With the dataset sample The Euclidean distance of Represents the sample dimension.

[0081] See also Figure 5 As shown, the second aspect of the present invention provides a multi-heat source annular pipe network leakage identification device, including: a feature extraction module, used to calculate the energy characteristics of the oscillation law of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, as the sample to be classified; a leakage identification module, used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipe network, and determine the leakage point location based on the obtained leakage condition category.

[0082] See also Figure 6 As shown, a third aspect of the present invention provides a multi-heat source annular pipe network leakage identification device, including a memory and a processor, the memory is used to store a method program supporting the execution of the processor, and the processor is configured to execute the program stored in the memory to implement the multi-heat source annular pipe network leakage identification method.

[0083] Furthermore, the multi-heat source annular pipe network leakage identification device comprises:

[0084] The communication interface is used for communication between the memory and the processor. The memory is used to store computer programs that can be run on the processor. The memory may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory. If the memory, processor and communication interface are implemented independently, the communication interface, memory and processor can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0085] Optionally, in a specific implementation, if the memory, processor and communication interface are integrated on a chip, the memory, processor and communication interface can communicate with each other through an internal interface.

[0086] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0087] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, it is used to implement the multi-heat source annular pipe network leakage identification method.

[0088] In a fifth aspect of the embodiments of the present application, a computer program product is also provided, including a computer program or instructions, which, when executed, implements the above-mentioned method for identifying leakage in a multi-heat source annular pipe network.

[0089] The basic principles and main features of the present invention and the advantages of the present invention are shown and described above. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention.

[0090] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the claims are included in the present invention.

[0091] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for identifying leakage in a multi-heat source annular pipe network, characterized in that: Based on the previously established pipeline network leakage data set, when a leak occurs in a multi-heat source ring pipeline network, only the pressure monitoring data of each thermal power station is used to locate the leak point, including the following steps: Calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which represents the oscillation law of the pressure numerical signal, as the sample to be classified; Identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network, determine the leakage point location based on the obtained leakage condition category, and judge the area or pipe section where the leakage exists; The data set samples are constructed by obtaining pressure numerical signals when leakage occurs at different locations of a multi-heat source annular pipeline network through actual monitoring or simulation means, and then extracting the energy characteristics of the oscillation law of the pressure numerical signal from the intrinsic mode function components of the pressure numerical signal, including a variety of different leakage conditions, and each leakage condition corresponds to an energy characteristic component.

2. The method for identifying leakage in a multi-heat source annular pipe network according to claim 1, characterized in that: The empirical mode decomposition method is used to calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source ring pipeline network, which characterizes the oscillation law of the pressure numerical signal.

3. The method for identifying leakage in a multi-heat source annular pipe network according to claim 2, characterized in that: The empirical mode decomposition method is used to calculate the energy characteristic component of the eigenmode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which characterizes the oscillation law of the pressure numerical signal, including: S21. Obtaining the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source loop network; S22. Generate an upper envelope and a lower envelope of the pressure numerical signal using a cubic spline function curve, and calculate and obtain a mean curve of the upper envelope and the lower envelope; S23. Calculate the difference curve between the pressure numerical signal and the mean curve; S24. Determine whether the difference curve meets the preset conditions of the intrinsic mode function component. If so, execute step S25. Otherwise, take the difference curve as a new pressure numerical signal and return to step S22 for recalculation. S25. Using the difference curve as the intrinsic mode function component of the pressure numerical signal, and calculating the residual between the pressure numerical signal and the intrinsic mode function component; S26. Determine whether the residual meets the convergence condition. If so, proceed to step S27. Otherwise, take the residual as a new pressure numerical signal and return to step S22 for recalculation. S27. Calculate the energy characteristic component carried by each eigenmode function component and normalize it as the energy characteristic component of the eigenmode function component of the thermal power station pressure numerical signal.

4. The method for identifying leakage in a multi-heat source annular pipe network according to claim 3, characterized in that: The preset conditions include: the number of local extreme value points and zero-crossing points is equal, and the average value of the upper envelope of the local maximum value and the lower envelope of the local minimum value is 0.

5. The method for identifying leakage in a multi-heat source annular pipe network according to claim 3, characterized in that: The step of calculating the energy characteristic component carried by each eigenmode function component and normalizing the energy characteristic component comprises: The energy characteristic component carried by each eigenmode function component is calculated using the following formula: ， The following formula is used for normalization to obtain the normalized energy characteristic component: : ， In the formula, Indicates The energy characteristic component carried by the intrinsic mode function component, n represents the number of numerical points of the pressure numerical signal in the intrinsic mode function component, Indicates The first eigenmode function component The amplitude of the pressure value signal value point, Indicates the number of energy characteristic components.

6. The method for identifying leakage in a multi-heat source annular pipe network according to claim 1, characterized in that: The K nearest neighbor algorithm is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network.

7. The method for identifying leakage in a multi-heat source annular pipe network according to claim 6, characterized in that: The method of using the K nearest neighbor algorithm to identify the leakage condition closest to the condition of the sample to be classified from the data set samples includes: Calculate the Euclidean distance between the sample to be classified and the sample in the data set; Determine the working condition category to which the K data set samples with the closest Euclidean distance to the sample to be classified belong; The operating condition category that appears most frequently in the K data set samples is taken as the category of the current leakage condition of the pipeline network.

8. The method for identifying leakage in a multi-heat source annular pipe network according to claim 7, characterized in that: The Euclidean distance is expressed as follows: ; In the formula, D represents the sample to be classified With the dataset sample The Euclidean distance of Represents the sample dimension.

9. A multi-heat source annular pipe network leakage identification device, characterized in that: Based on the previously established pipeline network leakage data set, when a leak occurs in a multi-heat source ring pipeline network, only the pressure monitoring data of each thermal power station is used to locate the leak point, including: A feature extraction module is used to calculate the energy characteristic component of the intrinsic mode function component of the pressure numerical signal of the thermal power station under the current leakage condition of the multi-heat source annular pipe network, which characterizes the oscillation law of the pressure numerical signal, as a sample to be classified; A leakage identification module is used to identify the leakage condition closest to the condition of the sample to be classified from the data set samples as the category of the current leakage condition of the pipeline network, determine the location of the leakage point based on the obtained leakage condition category, and judge the area or pipe section where the leakage exists; The data set samples are constructed by obtaining pressure numerical signals when leakage occurs at different locations of a multi-heat source annular pipeline network through actual monitoring or simulation means, and then extracting the energy characteristics of the oscillation law of the pressure numerical signal from the intrinsic mode function components of the pressure numerical signal, including a variety of different leakage conditions, and each leakage condition corresponds to an energy characteristic component.

10. A multi-heat source annular pipe network leakage identification device, characterized in that: It includes a memory and a processor, wherein the memory is used to store a method program that supports the execution of the processor, and the processor is configured to execute the program stored in the memory to implement the multi-heat source annular pipe network leakage identification method as described in any one of claims 1-8.

Images