Natural gas flow metering pipe wall roughness change judgment method and device

Abstract

The invention discloses a natural gas flow metering pipe wall roughness change judgment method and device. The method comprises the steps that the type of an ultrasonic flowmeter, a sound channel layout structure and the flow speed of each sound channel are obtained; converting the flow velocity of each sound channel into the flow velocity of the pipeline diameter sound channel based on the type of the ultrasonic flowmeter, the sound channel layout structure of the ultrasonic flowmeter and the fully developed turbulent flow field distribution characteristics; according to the situation that the roughness of the natural gas flow metering pipe wall changes, new pipe wall roughness change characteristics and sound channel flow velocity characteristics are constructed by utilizing the flow velocity of each sound channel; according to the converted pipeline diameter flow velocity, performing normalization processing on the constructed pipe wall roughness change feature and the sound channel flow velocity feature; based on the normalized pipe wall roughness change characteristics and the sound channel flow velocity characteristics, training by using an isolated forest method to obtain a natural gas flow metering pipe wall roughness change judgment model; and judging whether the natural gas metering pipe wall has roughness change or not by using the natural gas flow metering pipe wall roughness change judgment model.

Description

Technical Field

[0001] The present application relates to the field of energy and power engineering technology, and in particular to a method and device for judging the roughness change of a natural gas flow metering pipe wall. Background Art

[0002] With the rapid development of my country's economy, the national economic level and living standards have significantly improved, and people's awareness and efforts on environmental protection have also been continuously strengthened. As a clean and efficient energy source, the demand for natural gas in various industries is constantly increasing. Therefore, the proportion of natural gas in the energy structure continues to increase, and it occupies an important position in my country's national energy structure.

[0003] Most of the gaseous natural gas measurement trade is mainly carried out through pipelines. Therefore, in the process of natural gas resource development, transportation and trade, it is particularly important to ensure the accuracy of pipeline natural gas measurement. However, due to the long-term and continuous measurement of pipeline natural gas, and the fact that it is usually impossible to perform repeated measurements, once the natural gas measurement system has deviations and accumulates over a long period of time, it may lead to serious economic losses and a large number of trade disputes. Therefore, the accuracy of natural gas measurement is directly related to the interests of both parties to the trade. How to further improve the accuracy of natural gas measurement has become a key issue that must be solved for pipeline natural gas.

[0004] In the field of pipeline natural gas metering, ultrasonic flowmeter, as an advanced technology, has the advantages of non-contact measurement, high repeatability, wide measurement range, simple operation, bidirectional measurement and convenient installation. In recent years, this technology has been widely used. With the rapid development of electronic technology, ultrasonic flowmeters have also made significant progress. Government agencies in many countries, including the United States, the United Kingdom, Germany, the Netherlands, etc., have confirmed ultrasonic flowmeters as legal measuring instruments for natural gas trade transfer. At the same time, ultrasonic flowmeters have been successfully used in pipeline flow measurement and natural gas trade transfer in my country. According to the planning requirements of my country's natural gas pipeline network, as of 2020, my country has more than 3,000 gas ultrasonic flowmeters used in natural gas trade measurement work, and ultrasonic flowmeters have become one of the important flow metering instruments in the field of natural gas metering trade.

[0005] Ultrasonic flowmeters are velocity flowmeters, and their measurement principle is based on the fact that the measured flow field is in a fully developed, uniform and stable flow state. However, in complex natural gas metering sites, the measurement accuracy of ultrasonic flowmeters will be seriously affected by the flow field in the pipeline. For example, when the roughness of the inner wall of the upstream straight pipe section of the flowmeter changes, the flowmeter running on site may deviate from the metering performance, thereby affecting the metering accuracy of the ultrasonic flowmeter. Therefore, it is particularly important to study whether the roughness of the natural gas flow metering pipe wall has changed. Summary of the invention

[0006] The purpose of the embodiments of the present application is to provide a method and device for determining the roughness change of a natural gas flow metering pipe wall, so as to solve the problem in the prior art that it is difficult to accurately determine whether a metering performance deviation exists.

[0007] According to a first aspect of an embodiment of the present application, a method for determining a change in roughness of a natural gas flow metering pipe wall is provided, comprising: Obtain the ultrasonic flow meter type, channel layout structure and flow rate of each channel; Based on the ultrasonic flowmeter type and its channel layout structure, combined with the turbulent flow field distribution characteristics, the flow velocity of each channel is converted into the channel flow velocity of the pipe diameter; According to the change of pipe wall roughness for natural gas flow measurement, new pipe wall roughness change characteristics and channel velocity characteristics are constructed by using the flow velocity of each channel of the ultrasonic flowmeter. According to the converted channel velocity of the pipe diameter, the constructed pipe wall roughness variation characteristics and channel velocity characteristics are normalized; Based on the normalized pipe wall roughness variation characteristics and acoustic channel velocity characteristics, the isolation forest method is used to train a natural gas flow meter pipe wall roughness variation judgment model. The natural gas flow metering pipe wall roughness change judgment model is used to judge whether the natural gas metering pipe wall has a roughness change, and a judgment result is obtained.

[0008] According to a second aspect of an embodiment of the present application, a device for determining a change in roughness of a natural gas flow metering pipe wall is provided, comprising: An acquisition module is used to obtain the ultrasonic flow meter type, channel layout structure and flow rate of each channel; The conversion module is used to convert the flow velocity of each channel into the flow velocity of the channel of the pipe diameter based on the type of ultrasonic flow meter and its channel layout structure and the distribution characteristics of the turbulent flow field; A construction module is used to construct new pipe wall roughness change characteristics and acoustic channel flow velocity characteristics according to the situation of natural gas flow meter pipe wall roughness change, using the flow velocity of each acoustic channel of the ultrasonic flow meter; A normalization module is used to normalize the constructed pipe wall roughness variation characteristics and the acoustic channel flow velocity characteristics according to the converted pipe diameter acoustic channel flow velocity; A modeling module is used to train a natural gas flow metering pipe wall roughness change judgment model based on the normalized pipe wall roughness change characteristics and the acoustic channel flow velocity characteristics using the isolation forest method; The judgment module is used to judge whether the roughness change of the natural gas flow metering pipe wall occurs by using the natural gas flow metering pipe wall roughness change judgment model to obtain a judgment result.

[0009] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0010] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0011] The technical solution provided by the embodiments of the present application may have the following beneficial effects: It can be seen from the above embodiments that the present application is based on the ultrasonic flowmeter type and its channel layout structure and the fully developed turbulent flow field distribution characteristics, converts the flow velocity of each channel into the pipeline diameter flow velocity, and constructs new pipe wall roughness change characteristics and channel flow velocity characteristics, and then normalizes the constructed pipe wall roughness change characteristics and channel flow velocity characteristics, and based on the normalized pipe wall roughness change characteristics and channel flow velocity characteristics, uses the isolation forest method to train a natural gas flow meter pipe wall roughness change judgment model, and finally, inputs the ultrasonic flowmeter state parameters and channel flow velocity, and can judge whether the natural gas metering pipe wall has a roughness change. When the natural gas flow metering pipe wall has a roughness change, the present invention analyzes and mines new pipe wall roughness change characteristics and channel flow velocity characteristics, and uses machine learning methods to judge whether the roughness of the natural gas flow metering pipe wall has changed, which has important practical significance for ensuring the accuracy of natural gas metering and ensuring the common interests of both trading parties.

[0012] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0014] Figure 1 The present invention is a flow chart of a method for judging the change of the roughness of the wall of a natural gas flow metering pipe according to an exemplary embodiment.

[0015] Figure 2 It is a block diagram of a device for judging the change of roughness of a natural gas flow metering pipe wall according to an exemplary embodiment. DETAILED DESCRIPTION

[0016] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0017] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0018] Figure 1 FIG. 1 is a flow chart showing a natural gas flow metering pipe wall roughness change determination according to an exemplary embodiment. Figure 1 As shown, the method may include the following steps: S1: Obtain the ultrasonic flowmeter type, channel layout structure and flow rate of each channel; Specifically, the type of ultrasonic flowmeter is an insertion type ultrasonic flowmeter, and the channel layout is a multi-channel opposed-beam layout and a multi-channel reflective layout, including a four-channel opposed-beam layout, a four-channel reflective layout, a six-channel reflective layout and a six-channel opposed-beam layout, etc. The flow velocity of each channel is the average flow velocity data on each channel of the ultrasonic flowmeter.

[0019] S2: Based on the ultrasonic flowmeter type and its channel layout structure, combined with the turbulent flow field distribution characteristics, the flow velocity of each channel is converted into the channel flow velocity of the pipe diameter; Specifically, based on the ultrasonic flowmeter type and ultrasonic flowmeter sound channel layout structure, combined with the turbulent flow field distribution characteristics, the circular pipe turbulent flow velocity distribution index formula is used to calculate the distance from the pipe diameter. chordal channel velocity : in, It is half of the central angle of the pipe corresponding to the chord channel. It represents the distance between a point on the chord channel and the center of the chord channel. is the maximum flow velocity at the pipe axis, is the radius of the tube, is the experience index, is the flow velocity at a certain point in the pipeline, and the formula for the turbulent flow velocity distribution index of the circular pipe is: when = 0, the calculated chord channel velocity is the pipe diameter channel velocity, that is, According to the above two formulas, the flow velocity of each channel can be converted to the flow velocity at the pipe diameter. Opposed sound channels and Reflective channels, of which , ,…, Respectively The flow rate of the opposite channel, , ,…, Respectively The reflected sound channel velocity, and are all even numbers, and the converted flow velocities of each channel are expressed as , ,…, and , ,…, ;

[0020] Converting the flow velocity of each channel into the channel flow velocity of the pipe diameter is conducive to comparing the flow velocities of each channel and to constructing new pipe wall roughness change characteristics and channel flow velocity characteristics in the next step.

[0021] S3: According to the change of the roughness of the pipe wall for natural gas flow measurement, a new pipe wall roughness change feature and acoustic channel flow velocity feature are constructed; Specifically, according to the flow velocity of each channel, a new pipe wall roughness variation feature is constructed : Among them, the ultrasonic flow meter contains multiple sound channels at different positions. Each type of ultrasonic flow meter contains a radial sound channel and a sound channel at a certain distance from the pipe diameter. represents the number of radial channels, Respectively represent the flow velocity of each radial channel, represents the average value of the flow velocity in each radial channel, represents the number of non-radial channels, Respectively represent the flow velocity of each non-radial channel, represents the average value of the flow velocity in each non-radial channel, The roughness variation characteristics of the pipe wall constructed according to the flow velocities of all the acoustic channels of this model; The new pipe wall roughness variation characteristics can well describe the variation degree of pipe wall roughness for natural gas flow measurement; Specifically, according to the flow velocity of each channel, the channel flow velocity feature is constructed ; More specifically, The selection and construction of is as follows: for or The ultrasonic flowmeter directly selects all converted acoustic channel flow velocity characteristics, which can be specifically expressed as , , , ;for The ultrasonic flowmeter can be specifically expressed as , , , ;for The ultrasonic flowmeter directly selects all converted acoustic channel flow velocity characteristics, which can be specifically expressed as , , , , , .

[0022] According to the above-mentioned characteristic structures and selection methods of the flow velocities of each channel of various ultrasonic flowmeter types and channel layouts, those skilled in the art can select ,or ,or The flow velocity of each channel of the ultrasonic flowmeter is constructed and selected in a similar manner, and is not limited to the above examples.

[0023] Constructed acoustic channel velocity characteristics , which can better capture the patterns and relationships in the data. By converting, extracting and combining the original vocal tract flow velocity data, new features are generated to more accurately express the original flow velocity of each vocal tract, thereby improving the performance of the model.

[0024] S4: According to the converted pipeline diameter velocity, the constructed new pipe wall roughness variation characteristics and acoustic channel velocity characteristics are normalized; Specifically, the average of all converted duct flow velocities is calculated , divide the selected and constructed vocal tract velocity characteristics by , and the dimensionless acoustic channel velocity is obtained. The specific calculation is as follows: The dimensionless acoustic channel velocity characteristic can be expressed as: in, is the velocity characteristic of the vocal tract; After obtaining the dimensionless acoustic channel velocity, the roughness variation characteristics of the constructed pipe wall are Perform normalization processing, the normalization processing formula is as follows: in, represents the dimensionless acoustic channel velocity characteristics, To construct the wall roughness variation characteristics, and represent the maximum and minimum values ​​of the dimensionless acoustic channel velocity characteristics, respectively. is the normalized vocal tract velocity characteristic, and Respectively represent the maximum and minimum values ​​of the pipe wall roughness variation characteristics, is the variation characteristics of pipe wall roughness after normalization; After normalization, data with different feature ranges can be unified into the same range to avoid certain features from having too much influence on the loss function. This can speed up the model training process, increase the convergence speed, and avoid the impact of value differences between different features on subsequent model training.

[0025] S5: Based on the normalized acoustic channel velocity characteristics and pipe wall roughness change characteristics, the isolation forest method is used to train a natural gas flow meter pipe wall roughness change judgment model; Specifically, according to different types of ultrasonic flowmeters, the natural gas flow metering pipe wall roughness change judgment model includes three sub-judgment models, namely sub-judgment model 1, sub-judgment model 2 and sub-judgment model 3; For sub-judgment model 1, take Opposed sound channels and The normalized channel velocity characteristics of the ultrasonic flowmeter with a reflective channel And the variation characteristics of pipe wall roughness after normalization Training is obtained; For sub-judgment model 2, take Opposed sound channels and Normalized channel velocity characteristics corresponding to a reflection channel ultrasonic flowmeter And the variation characteristics of pipe wall roughness after normalization , Opposed sound channels and The normalized channel velocity characteristics of the ultrasonic flowmeter with a reflective channel And the variation characteristics of pipe wall roughness after normalization Training is obtained; For sub-judgment model 3, take The normalized channel velocity characteristics of the ultrasonic flowmeter with a beam channel And the variation characteristics of pipe wall roughness after normalization Training is obtained; After each sub-judgment model is obtained through training, the trained sub-judgment model can be used to judge whether the roughness change occurs on the wall of the natural gas metering pipe.

[0026] S6: using the natural gas flow metering pipe wall roughness change judgment model to judge whether the natural gas metering pipe wall has a roughness change; Specifically, the ultrasonic flow meter type, channel layout structure and all channel flow rates are input into the natural gas flow meter pipe wall roughness change judgment model to judge whether the natural gas pipeline has a roughness change; for An ultrasonic flowmeter with a beam-type sound channel can obtain a judgment result by inputting its corresponding sound channel flow velocity into the sub-judgment model 1; for Opposed sound channels and An ultrasonic flow meter with a reflective sound channel can input its corresponding sound channel flow velocity into sub-judgment model 2 to obtain the judgment result; for Opposed sound channels and An ultrasonic flow meter with a reflective sound channel can input its corresponding sound channel flow velocity into sub-judgment model 2 to obtain the judgment result; for An ultrasonic flow meter with a corresponding sound channel can input its corresponding sound channel flow rate into the sub-judgment model 3 to obtain the judgment result.

[0027] In this implementation, 70 pieces of real flow test data from a natural gas metering station in China and 61 pieces of pipe wall roughness change data obtained by CFD simulation were selected. Among them, 70 pieces of real flow test data were used to train the natural gas flow metering pipe wall roughness change judgment model, and 61 pieces of roughness change data obtained by CFD simulation were used for testing, and the working condition with a roughness greater than or equal to 0.4 was considered to be a case of roughness change.

[0028] The detection effect of the model is evaluated using statistical indicators such as accuracy, precision, and recall. The calculation method of the three indicators is as follows:

[0029] in, Indicates the number of samples with roughness changes that are correctly identified as samples with roughness changes. It indicates the number of normal samples correctly identified as normal samples. It indicates the number of normal samples that are mistakenly identified as samples with roughness changes. Indicates the number of samples with roughness changes that are misclassified as normal samples.

[0030] Table 1 Test results of natural gas flow metering pipe wall roughness change judgment model True positive (TP) True negative (TN) False positive (FP) False negative (FN) 23 31 7 0 Among them, the precision rate is 0.885, the accuracy rate is 0.767, and the recall rate is 1, which shows the effectiveness of the model.

[0031] Corresponding to the aforementioned embodiment of the method for judging the change in the roughness of the wall of a natural gas flow metering pipe, the present application also provides an embodiment of a device for judging the change in the roughness of the wall of a natural gas flow metering pipe.

[0032] Figure 2 The following is a block diagram of a device for determining the roughness change of a natural gas flow meter pipe wall according to an exemplary embodiment. Figure 2 , the device comprises:

[0033] Acquisition module 1, used to obtain the ultrasonic flow meter type, channel layout structure and flow rate of each channel; Conversion module 2, used to convert the flow velocity of each channel into the flow velocity of the channel of the pipe diameter based on the type of ultrasonic flowmeter and its channel layout structure and the distribution characteristics of the turbulent flow field; Building module 3, for building new pipe wall roughness change characteristics and acoustic channel flow velocity characteristics according to the change of pipe wall roughness of natural gas flow meter and using the flow velocity of each acoustic channel of the ultrasonic flow meter; Normalization module 4, used for normalizing the constructed pipe wall roughness variation characteristics and the acoustic channel flow velocity characteristics according to the converted pipe diameter acoustic channel flow velocity; Modeling module 5, used to train and obtain a natural gas flow metering pipe wall roughness change judgment model based on the normalized pipe wall roughness change characteristics and the acoustic channel flow velocity characteristics using the isolation forest method; The judgment module 6 is used to judge whether the roughness change of the natural gas flow metering pipe wall occurs by using the natural gas flow metering pipe wall roughness change judgment model to obtain a judgment result.

[0034] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0035] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0036] Correspondingly, the present application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for judging the change in the roughness of the natural gas flow metering pipe wall as described above.

[0037] Correspondingly, the present application also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the above-mentioned method for determining the roughness change of the natural gas flow metering pipe wall is implemented.

[0038] Those skilled in the art will readily appreciate other embodiments of the present application after considering the description and practicing the contents disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The description and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0039] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for judging the change of roughness of a natural gas flow metering pipe wall, characterized in that: include: Obtain the ultrasonic flow meter type, channel layout structure and flow rate of each channel; Based on the ultrasonic flowmeter type and its channel layout structure, combined with the turbulent flow field distribution characteristics, the flow velocity of each channel is converted into the channel flow velocity of the pipe diameter; According to the change of pipe wall roughness for natural gas flow measurement, new pipe wall roughness change characteristics and channel velocity characteristics are constructed by using the flow velocity of each channel of the ultrasonic flowmeter. According to the converted channel velocity of the pipe diameter, the constructed pipe wall roughness variation characteristics and channel velocity characteristics are normalized; Based on the normalized pipe wall roughness variation characteristics and acoustic channel velocity characteristics, the isolation forest method is used to train a natural gas flow meter pipe wall roughness variation judgment model. The natural gas flow metering pipe wall roughness change judgment model is used to judge whether the natural gas metering pipe wall has a roughness change, and a judgment result is obtained.

2. The method according to claim 1, characterized in that Based on the ultrasonic flowmeter type and its channel layout structure, combined with the turbulent flow field distribution characteristics, the flow velocity of each channel is converted into the channel flow velocity of the pipe diameter, including: Based on the ultrasonic flowmeter type and ultrasonic flowmeter sound channel layout structure, combined with the turbulent flow field distribution characteristics, the circular pipe turbulent flow velocity distribution index formula is used to calculate the distance from the pipe diameter. chordal channel velocity ; in, It is half of the central angle of the pipe corresponding to the chord channel. It represents the distance between a point on the chord channel and the center of the chord channel. is the maximum flow velocity at the pipe axis, is the radius of the tube, is the experience index, is the flow velocity at a certain point in the pipeline, and the formula for the turbulent flow velocity distribution index of the circular pipe is: when =0, the calculated chord channel velocity is the pipe diameter channel velocity, that is: Ultrasonic flow meter includes Opposed sound channels and Reflective channels, of which , ,…, Respectively The flow rate of the opposite channel, , ,…, Respectively The reflected sound channel velocity, and are all even numbers, and the converted flow velocities of each channel are expressed as , ,…, and , ,…, ; According to the above two formulas, the flow velocity of each sound channel is converted to the flow velocity at the pipe diameter.

3. The method according to claim 1, characterized in that According to the changes in the roughness of the pipe wall for natural gas flow measurement, new pipe wall roughness change characteristics and acoustic channel flow velocity characteristics are constructed, including: According to the flow velocity of each channel, a new pipe wall roughness variation characteristic is constructed ; Among them, the ultrasonic flow meter contains multiple sound channels at different positions. Each type of ultrasonic flow meter contains a radial sound channel and a sound channel at a certain distance from the pipe diameter. represents the number of radial channels, Respectively represent the flow velocity of each radial channel, represents the average flow velocity of each radial channel, represents the number of non-radial channels, Respectively represent the flow velocity of each non-radial channel, represents the average value of the flow velocity in each non-radial channel, The roughness variation characteristics of the pipe wall constructed according to the flow velocities of all the acoustic channels of this model; According to the flow velocity of each channel, construct the channel flow velocity characteristics .

4. The method according to claim 3, characterized in that Acoustic channel velocity characteristics The selection and construction of is as follows: for or The ultrasonic flowmeter directly selects all converted acoustic channel flow velocity characteristics, which can be specifically expressed as , , , ;for The ultrasonic flowmeter can be specifically expressed as , , , ;for The ultrasonic flowmeter directly selects all converted acoustic channel flow velocity characteristics, which can be specifically expressed as , , , , , .

5. The method according to claim 1, characterized in that: According to the converted pipe diameter velocity, the constructed new pipe wall roughness variation characteristics and acoustic channel velocity characteristics are normalized, including: Calculate the average of all converted duct flow velocities , divide the selected and constructed vocal tract velocity features by the average value , and the dimensionless acoustic channel velocity is obtained. The specific calculation is as follows: Dimensionless acoustic channel velocity characteristics It is expressed as: in, is the velocity characteristic of the vocal tract; The dimensionless acoustic channel velocity and pipe wall roughness variation characteristics Perform normalization processing, the normalization processing formula is as follows: in, represents the dimensionless acoustic channel flow velocity characteristics, To construct the roughness variation characteristics of the pipe wall, and represent the maximum and minimum values ​​of the dimensionless acoustic channel velocity characteristics, respectively. is the normalized vocal tract velocity characteristic, and Respectively represent the maximum and minimum values ​​of the pipe wall roughness variation characteristics, It is the variation characteristics of pipe wall roughness after normalization.

6. The method according to claim 1, characterized in that The natural gas flow metering pipe wall roughness change judgment model includes three sub-judgment models, which are respectively called sub-judgment model 1, sub-judgment model 2 and sub-judgment model 3; For sub-judgment model 1, take Opposed sound channels and The normalized channel velocity characteristics of the ultrasonic flowmeter with a reflective channel And the variation characteristics of pipe wall roughness after normalization Training is obtained; For sub-judgment model 2, take Opposed sound channels and Normalized channel velocity characteristics corresponding to a reflection channel ultrasonic flowmeter And the variation characteristics of pipe wall roughness after normalization , Opposed sound channels and The normalized channel velocity characteristics of the ultrasonic flowmeter with a reflective channel And the variation characteristics of pipe wall roughness after normalization Training is obtained; For sub-judgment model 3, take The normalized channel velocity characteristics of the ultrasonic flowmeter with a beam channel And the variation characteristics of pipe wall roughness after normalization Trained to get.

7. The method according to claim 6, characterized in that The natural gas flow metering pipe wall roughness change judgment model is used to judge whether the natural gas metering pipe wall has a roughness change, including: Inputting the ultrasonic flowmeter type, channel layout structure and all channel flow rates into the natural gas flow meter pipe wall roughness change judgment model can determine whether the natural gas pipeline has a roughness change; for An ultrasonic flowmeter with a beam-type sound channel can obtain a judgment result by inputting its corresponding sound channel flow velocity into the sub-judgment model 1; for Opposed sound channels and An ultrasonic flow meter with a reflective sound channel can input its corresponding sound channel flow velocity into sub-judgment model 2 to obtain the judgment result; for Opposed sound channels and An ultrasonic flow meter with a reflective sound channel can input its corresponding sound channel flow velocity into sub-judgment model 2 to obtain the judgment result; for An ultrasonic flow meter with a corresponding sound channel can input its corresponding sound channel flow rate into the sub-judgment model 3 to obtain the judgment result.

8. A device for judging the roughness change of a natural gas flow metering pipe wall, characterized in that: include: An acquisition module is used to obtain the ultrasonic flow meter type, channel layout structure and flow rate of each channel; The conversion module is used to convert the flow velocity of each channel into the flow velocity of the channel of the pipe diameter based on the type of ultrasonic flow meter and its channel layout structure and the distribution characteristics of the turbulent flow field; A construction module is used to construct new pipe wall roughness change characteristics and acoustic channel flow velocity characteristics according to the situation of natural gas flow meter pipe wall roughness change, using the flow velocity of each acoustic channel of the ultrasonic flow meter; A normalization module is used to normalize the constructed pipe wall roughness variation characteristics and the acoustic channel flow velocity characteristics according to the converted pipe diameter acoustic channel flow velocity; A modeling module is used to train a natural gas flow metering pipe wall roughness change judgment model based on the normalized pipe wall roughness change characteristics and the acoustic channel flow velocity characteristics using the isolation forest method; The judgment module is used to judge whether the roughness change of the natural gas flow metering pipe wall occurs by using the natural gas flow metering pipe wall roughness change judgment model to obtain a judgment result.

9. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images