Flow adjusting method of natural gas metering station

Abstract

The embodiment of the invention provides a flow regulation method for a natural gas metering station. The technical problem that reliability of flow regulation of the natural gas metering station is poor through manual operation can be solved. The method comprises the following steps: determining a first pressure comparison value and a second temperature comparison value of a first-level standard; determining a second pressure comparison value and a second temperature comparison value of a second-level standard; determining a flow point and a flow value of the flow point based on the first pressure comparison value, the second temperature comparison value, the second pressure comparison value, the second temperature comparison value and the first frequency; according to the flow value, based on a machine learning model, calculating a flow adjusting parameter and a pipeline combination result of the flow point; the flow adjusting parameters comprise a valve opening value, an adjusting valve caliber and an adjusting valve model; the pipeline combination result is used for representing the size, the number and the connection mode of the standard meter pipelines. Automation is achieved, intelligent flow adjustment is further achieved, and the method is suitable for high-pressure, large-flow and high-accuracy scenes.

Description

Technical Field

[0001] The present application relates to the technical field of natural gas transportation, and in particular to a flow regulation method of a natural gas metering station. Background Art

[0002] Oil and gas metering stations are facilities used to measure and record natural gas flow and related parameters. They play a vital role in the production, transportation, distribution and sales of natural gas. For example, they measure the volume or mass flow of natural gas through the pipeline. Commonly used flow meters include turbine flow meters, ultrasonic flow meters, orifice flow meters and rotor flow meters. In order to meet the increasing verification needs of flow meters, oil and gas metering stations are equipped with natural gas metering verification systems.

[0003] At present, the natural gas metering and verification system has a verification module and a control module. Manually enter the measurement data, such as pressure and temperature, into the verification module. The verification module transmits the data to the control module. The verifier with many years of work experience realizes intelligent adjustment of the verification flow through the control module.

[0004] However, in the verification process, key steps are all manual operations, with great risk of errors and poor reliability. Summary of the invention

[0005] The embodiment of the present application provides a flow regulation method for a natural gas metering station, which can solve the technical problem of poor reliability of flow regulation of a natural gas metering station achieved through manual operation.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a flow regulation method for a natural gas metering station, which includes: determining a first pressure comparison value and a first temperature comparison value of a first-level standard; determining a second pressure comparison value and a second temperature comparison value of a second-level standard; determining a flow point and a flow value of the flow point based on the first pressure comparison value, the first temperature comparison value, the second pressure comparison value, the second temperature comparison value and the first frequency; the flow value includes an instantaneous flow; according to the flow value, based on a machine learning model, the flow regulation parameters and pipeline combination results of the flow point are calculated; the flow regulation parameters include a valve opening value, a regulating valve caliber and a regulating valve model; the pipeline combination results are used to characterize the size, quantity and connection method of the standard meter pipeline; wherein the standard meter pipeline includes a verification ultrasonic flowmeter and a standard turbine flowmeter; the first frequency is the frequency of the standard turbine flowmeter; the verification ultrasonic flowmeter and the standard turbine flowmeter are used to collect the flow value.

[0008] Based on the above description of the flow rate regulation method of the natural gas metering station provided in the embodiment of the present application, it can be known that the flow rate regulation method of the natural gas metering station realizes automation of the control monitoring, flow rate regulation and other functions involved in the flow meter calibration process of the natural gas metering station through the collection, processing and calculation of flow rate data, thereby realizing intelligent flow rate regulation. This embodiment is suitable for high pressure, large flow and high accuracy application scenarios.

[0009] In a feasible implementation of the first aspect, the flow points include a first flow point and a second flow point; after adjusting the flow based on the flow regulation parameters and pipeline combination results of the first flow point, the flow regulation method of the natural gas metering station also includes: adjusting the current flow based on the flow regulation parameters of the second flow point; replacing the current line based on the pipeline combination result of the second flow point.

[0010] In a feasible implementation manner of the first aspect, the flow regulation method of the natural gas metering station further includes: obtaining a reliability result according to the chromatographic information of the flow point.

[0011] In a feasible implementation of the first aspect, when executing the step of calculating the flow regulation parameters and pipeline combination results of the flow point according to the flow value based on the machine learning model, the machine learning model is a SENet network.

[0012] In a feasible implementation of the first aspect, when executing the step of determining the flow point and the flow value of the flow point based on the first pressure comparison value, the first temperature comparison value, the second pressure comparison value, the second temperature comparison value and the first frequency, the flow regulation method of the natural gas metering station also includes: obtaining the flow value of the flow point based on multiple continuous flow monitoring values.

[0013] In a feasible implementation of the first aspect, when executing the step of calculating the flow control parameters and pipeline combination results of the flow point according to the flow value based on the machine learning model, the flow control method of the natural gas metering station also includes: determining the caliber of the regulating valve based on the gas source flow value.

[0014] In a feasible implementation of the first aspect, the number of the standard meter pipelines is eight; the eight standard meter pipelines include five standard meter pipelines with a caliber of 250.

[0015] In the second aspect, an embodiment of the present application provides a flow regulation system for a natural gas metering station, which flow regulation system includes: a calibration module, a control module and a machine learning module; the calibration module includes a multi-channel standard meter pipeline, each of the multi-channel standard meter pipelines includes a verification ultrasonic flowmeter and a standard turbine flowmeter; the verification ultrasonic flowmeter and the standard turbine flowmeter are used to collect flow values; the flow value is determined based on a first pressure comparison value, a first temperature comparison value, a second pressure comparison value, a second temperature comparison value and a first frequency; the control module is used to receive a first parameter sent by the standard turbine flowmeter; the first parameter includes frequency, temperature and pressure; the machine learning module is used to calculate the flow regulation parameters and pipeline combination results of the flow point based on the flow value and the machine learning model.

[0016] In this way, through the collection, processing and calculation of flow data, the control monitoring, flow regulation and other functions involved in the flow meter calibration process of the natural gas metering station are automated, thereby realizing intelligent flow regulation. This embodiment is suitable for high pressure, large flow and high accuracy application scenarios.

[0017] In a third aspect, an embodiment of the present application provides a flow regulation system for a natural gas metering station, the flow regulation system for a natural gas metering station comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided in the first aspect.

[0018] The flow regulation system of the natural gas metering station implements the method provided in the first aspect, so that through the collection, processing and calculation of flow data, the control monitoring, flow regulation and other functions involved in the flow meter calibration process of the natural gas metering station are automated, thereby realizing intelligent flow regulation. This embodiment is suitable for high pressure, large flow and high accuracy application scenarios.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement the method provided in the first aspect.

[0020] The computer program instructions in the computer-readable medium implement the method provided in the first aspect, so that through the collection, processing and calculation of flow data, the control monitoring, flow regulation and other functions involved in the flow meter calibration process of the natural gas metering station are automated, thereby realizing intelligent flow regulation. This embodiment is suitable for high-pressure, large-flow, and high-accuracy application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1A schematic diagram of the structure of a flow regulation system of a natural gas metering station provided in an embodiment of the present application;

[0022] Figure 2 A flow chart of a method for regulating flow at a natural gas metering station provided in an embodiment of the present application;

[0023] Figure 3 A schematic structural diagram of a flow regulation system for a natural gas metering station provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention. In the description of the embodiments of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0025] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. At the same time, in the embodiments of the present invention, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0026] The principles and features of the present application are described below. The examples given are only used to explain the present application and are not used to limit the scope of the present application.

[0027] The embodiment of the present application provides a flow regulation method for a natural gas metering station, which is suitable for high-pressure, large-flow, and high-accuracy application scenarios. Through the collection, processing, and calculation of flow data, the control monitoring, flow regulation, and other functions involved in the flow meter calibration process of the natural gas metering station are automated, thereby realizing intelligent flow regulation.

[0028] The embodiment of the present application provides a flow regulation system for a natural gas metering station, which can execute the flow regulation method for a natural gas metering station provided in the embodiment of the present application. Figure 1 A schematic structural diagram of a flow regulation system for a natural gas metering station provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the flow regulation system 001 of the natural gas metering station includes at least one processor 011 and a memory 012 communicatively connected to the at least one processor; wherein the memory 012 stores instructions executable by the at least one processor 011, and the instructions are executed by the at least one processor 011 so that the at least one processor 011 can execute the flow regulation method of the natural gas metering station provided in the embodiment of the present application.

[0030] like Figure 3 As shown, in some embodiments, an embodiment of the present application provides a flow regulation system for a natural gas metering station, and the flow regulation system includes a verification module, a control module and a machine learning module.

[0031] The calibration module includes a multi-channel standard meter pipeline, each of which includes a verification ultrasonic flowmeter and a standard turbine flowmeter. The verification ultrasonic flowmeter and the standard turbine flowmeter are used to collect flow values. The flow value is determined based on a first pressure comparison value, a first temperature comparison value, a second pressure comparison value, a second temperature comparison value and a first frequency.

[0032] The control module is used to receive the first parameter sent by the standard turbine flow meter. The first parameter includes frequency, temperature and pressure.

[0033] The machine learning module is used to calculate the flow regulation parameters and pipeline combination results of the flow point according to the flow value based on the machine learning model.

[0034] Figure 2 The following is a flow chart of a method for regulating the flow of a natural gas metering station provided in an embodiment of the present application. Figure 2 As shown, in some embodiments, the flow rate regulation method of the natural gas metering station includes the following steps:

[0035] S1, determining a first pressure comparison value and a first temperature comparison value of a first level standard.

[0036] The first level standard is the secondary standard. The secondary standard is the secondary standard device.

[0037] The following is an explanation of the relevant contents of the secondary standard device.

[0038] Natural gas flow metering devices can be divided into three levels according to their accuracy and purpose, including primary standard devices, secondary standard devices and working standard devices. They each have different application scenarios and accuracy requirements. In the natural gas flow metering process, these three types of devices form a calibration chain to ensure accurate transfer and calibration from the top primary standard to the final working device. The primary standard device refers to a standard device that can achieve the highest measurement accuracy and is usually used to calibrate secondary standard devices and the highest precision flow measurement tasks. This device is used to provide the most accurate measurement benchmark.

[0039] Secondary Standard Device**, whose measurement accuracy is inferior to that of the primary standard device, but it still has a higher precision. Secondary Standard Device is usually used to calibrate the working standard device, or to directly measure the natural gas flow when the highest accuracy is not required.

[0040] In the case of the first level standard, the authorized pressure range is 5.5-9MPa.

[0041] In the case of the primary standard, the expanded uncertainty is better than 0.1°C, calculated at 0.1°C, the result is 0.14°C, and the control limit is set at 0.14°C. The expanded uncertainty is the measured value of the temperature transmitter supporting the secondary standard device.

[0042] S2, determining a second pressure comparison value and a second temperature comparison value of a second level standard.

[0043] The second level standard is the working level standard. Also known as the working standard device (Working Standard Device). Working level standard devices are used for natural gas flow measurement in daily production and commerce. Although their accuracy is not as high as that of secondary and primary standard devices, they meet the needs of daily use. Working level devices are usually used in industrial pipelines, commercial transactions and other scenarios.

[0044] In one implementation, the working-level standard can calibrate both the check ultrasonic flowmeter and the standard turbine flowmeter. The working-level standard consists of two flowmeters, the standard turbine flowmeter and the check ultrasonic flowmeter. The standard turbine flowmeter measures the flow rate and compares the measured flow rate with the flowmeter to be checked. The check ultrasonic flowmeter can check the measured value of the standard turbine flowmeter.

[0045] In the case of the second level standard, the pressure authorization range is 5-7.2MPa. In one example, the calculation is performed according to the minimum pressure of 5MPa and the 0.05 level, the calculation result is 3.535kPa, and the control limit is set to 3.5kPa.

[0046] In the case of the second-level standard, the expanded uncertainty is better than 0.06°C. According to 0.06°C, the calculated result is 0.085°C, and the control limit is set at 0.08°C. The expanded uncertainty is the measured value of the temperature transmitter supporting the working-level standard device.

[0047] S3, determining a flow point and a flow value of the flow point based on the first pressure comparison value, the first temperature comparison value, the second pressure comparison value, the second temperature comparison value and the first frequency.

[0048] In some embodiments, when executing step S3, the flow regulation method of the natural gas metering station further includes: obtaining the flow value of the flow point based on multiple continuous flow monitoring values. In one example, when calibrating each flow point, three continuous calibration data that meet the requirements are selected by monitoring the rapid sampling value. Among them, the requirements that need to be met include repeatability <0.2 and indication error <1. These three continuous monitoring values ​​are valid calibration values ​​of a flow point.

[0049] The flow value includes the instantaneous flow.

[0050] In some embodiments, the number of standard meter pipelines is eight. In one example, to calibrate a flow meter with a nominal diameter (DN) of 600m, the eight standard meter pipelines include five standard meter pipelines with a diameter of 250m.

[0051] The standard meter pipeline includes a verification ultrasonic flowmeter and a standard turbine flowmeter. In one implementation, each standard meter pipeline includes a verification ultrasonic flowmeter and a standard turbine flowmeter, and the total flow measurement range is 8-12000m 3 / h.

[0052] The first frequency is the frequency of the standard turbine flowmeter and is directly connected to the flow regulation system of the natural gas metering station.

[0053] The temperature signal and the pressure signal are connected in a fully digital serial bidirectional transmission communication system (foundation fieldbus, FF). The temperature signal is confirmed based on the first temperature comparison value and the second temperature comparison value. The pressure signal is confirmed based on the first pressure comparison value and the second pressure comparison value.

[0054] Ultrasonic flowmeters and standard turbine flowmeters were checked for collecting flow values.

[0055] S4, according to the flow value, based on the machine learning model, calculates the flow adjustment parameters and pipeline combination results of the flow point.

[0056] Flow control parameters include valve opening value, control valve diameter and control valve model.

[0057] The pipeline combination results are used to characterize the size, quantity and connection method of the standard table pipelines. The pipeline combination results are used to achieve the optimal pipeline combination.

[0058] In some embodiments, flow points, flow adjustment parameters and pipeline combination results are associated and stored in the verification client account system.

[0059] According to the flow value required for calibration of the flow meter under test obtained in step S3, a certain working standard pipeline or a plurality of working standard pipelines in parallel are selected for different measuring ranges.

[0060] Exemplarily, the combination of standards is selected as shown in Table 1.

[0061] Table 1 Combination selection of standard instruments (working level standards)

[0062]

[0063]

[0064] As shown in Table 1, the calibers include DN50, DN80, DN100, DN150, DN200, DN250, DN300 and DN400.

[0065] In some embodiments, the caliber of the meter to be calibrated is selected based on the flow rate of the gas source on that day.

[0066] In some embodiments, the flow control valve can be used for both verification flow control and bypass flow control. Different flow ranges correspond to control valves of different calibers. The specific flow control valve combination selection table is shown in Table 2.

[0067] Table 2 Flow control valve combination selection table

[0068]

[0069] Exemplarily, the number of the flow regulating valves is four.

[0070] Exemplarily, the flow regulating valves (FV) 6102L, 6202L, 6302L and 6402L of the flow regulating valve group are automatically regulated by the calibration control system based on the linear regulation law (PID regulating), and the flow regulation (opening position, closing position, fault alarm, valve position feedback and valve position control) is displayed. It can be understood that when automatic control is not required, the automatic control state can be set to the manual control state, and then the control unit adjusts the opening of the two regulating valves on the computer screen, and displays their states (opening position, closing position, fault alarm, valve position feedback and valve position control), and the feedback flow value of the flow regulation is the flow of the working standard device.

[0071] Among them, PID can be a linear regulation law with proportional, integral and differential effects.

[0072] In some embodiments, according to the target flow rate and the calibration pipeline pressure, the flow regulation of the metering station can be achieved by automatically selecting the valve adjustment combination, determining the valve adjustment amount, adjustment speed, etc., without manual intervention, to achieve intelligent adjustment of the calibration flow.

[0073] The machine learning model is explained in detail below.

[0074] The machine learning model is configured based on actual on-site flow regulation data.

[0075] In some embodiments, the machine learning method used is a convolutional neural network. In one implementation, the machine learning model is a SENet network.

[0076] In some embodiments, a convolutional neural network is an overall process framework of a classifier based on deep learning. First, the input data is preprocessed by dimensionality reduction, normalization, denoising, etc., so that the subsequent deep learning network can extract more important spatial spectrum information; second, the input data is divided into a training set for training the model and a test set for evaluating the model, and the training set is fed into the network model in batches for training; then, the network model uses a loss function to calculate the loss value between the predicted label and the true label, where the smaller the loss value, the smaller the difference between the true label and the predicted label, and the larger the loss value, the greater the difference between the true label and the predicted label.

[0077] In some embodiments, based on the calculated loss value, the gradients of each weight of the network model structure are calculated by the optimizer in a back-to-forward manner, and the weights are updated in the gradient direction according to the set learning rate. The above training process is repeated continuously. When the loss value tends to be stable, the training ends and the best training model is obtained; finally, the test set is fed into the trained best model for prediction to obtain the final classification result.

[0078] In some embodiments, the convolutional neural network structure is mainly composed of a convolution layer, a pooling layer, and a fully connected layer. In the convolution layer, the input containing spatial context information is convolved with a set of linear shift-invariant convolution kernels. In the pooling layer, operations such as average pooling or maximum pooling are used to obtain general and abstract features. In the fully connected layer, these features are further converted into feature vectors for classification.

[0079] In some embodiments, after the model is built, it is necessary to use an optimizer for training. During the training process, a back propagation algorithm is generally used to measure the difference between the corresponding predicted value and the true value, and the weights and biases are updated by backpropagating the error through the objective function, and the process is repeated continuously using the stochastic gradient descent algorithm.

[0080] In some embodiments, the convolution layer is the most basic structural unit in the convolutional neural network model, which uses multiple convolution kernels to perform convolution processing on the input data and extract features. Shallow convolution layers usually only extract detailed features such as lines, edges, and corners, while deep convolution layers iterate and integrate these shallow features to obtain abstract features.

[0081] In some embodiments, since ordinary two-dimensional images contain a lot of redundant information, researchers generally periodically embed pooling layers after convolutional layers. At the same time, the training parameters and computational costs of the network model are also reduced, which can not only prevent overfitting but also improve the training speed of the model.

[0082] In some embodiments, the neurons in the current layer of the fully connected layer are fully connected to the neurons in the previous layer. After the pooling operation, the features of the previous layer are reshaped into a one-dimensional vector and transmitted to the fully connected layer to extract abstract high-level features for the final classification task. The fully connected layer is generally placed at the last layer of the network model to enhance the performance of the network.

[0083] In some embodiments, the target function updates and adjusts the training parameters of the network according to the difference between the predicted value and the true value, and plays a directive role in the entire convolutional neural network. The objective function is generally composed of a cost function and regularization. Among them, the loss function represents the error of a single sample, while the cost function represents the average of all sample errors. Depending on the task, the selected loss function is also different. The loss function can be roughly divided into two types: classification loss and regression loss. Regression loss is selected here.

[0084] In some embodiments, with the continuous advancement and development of computing platforms, many typical convolutional neural network models have been proposed such as VGGNet, AlexNet, GoogleNet, MobileNet, SENet, ResNet, DenseNet and other models. This patent selects the SENet network.

[0085] In some embodiments, the Squeeze-and-Excitation Network (SENet) improves the classification performance of the network by capturing the correlation between channels. The main idea of ​​the channel attention mechanism is to obtain the importance of different channels through learning, emphasize important spectral bands and weaken useless spectral bands, and achieve feature recalibration.

[0086] In some embodiments, squeeze and excitation. The squeeze part uses a global average pooling operation to compress the global information of the model into a channel descriptor. The excitation part obtains the weight value of each channel through a self-gating mechanism and adaptively adjusts the captured information. The excitation part is composed of two fully connected layers, which are used to obtain the interdependence between channels. Among them, the number of neurons in the first fully connected layer is small, which plays a role in dimensionality reduction, and the ReLU activation function is often used to activate the data of this layer; the number of neurons in the second fully connected layer is the same as the input feature dimension, which plays a role in dimensionality increase, and the Sigmoid activation function is often used to activate the data of this layer. Finally, the scale layer is used to realize feature recalibration, which is to multiply the importance value of each channel obtained by the original input data, thereby emphasizing important spectral channels.

[0087] Furthermore, the data sources of the training set and validation set used for modeling are data acquisition devices, including indicators such as flow regulation data and valve switch status data.

[0088] In some embodiments, the ratio of the training set to the validation set used is 8:2.

[0089] In some embodiments, when executing step S4, the flow rate regulation method of the natural gas metering station further includes:

[0090] S41, determining the caliber of the regulating valve based on the gas source flow value.

[0091] In some embodiments, the flow point includes a first flow point and a second flow point. By executing steps 1 to S4, the flow adjustment parameters and pipeline combination results of the first flow point and the second flow point are calculated respectively. After adjusting the flow based on the flow adjustment parameters and pipeline combination results of the first flow point, the flow adjustment method of the natural gas metering station further includes: adjusting the current flow based on the flow adjustment parameters of the second flow point. Based on the pipeline combination result of the second flow point, the current line is replaced.

[0092] In this way, the flow rate of the second flow point is adjusted. When changing the flow point, sometimes different flow points use different lines. At this time, the principle of adjusting the flow first and then changing the line is followed to protect the flow meter. In one example, when there are more than one optional calibration lines for the flow point to be tested, the line with the smaller maximum flow value that can be tested is preferred to ensure that the calibration value is more accurate.

[0093] In addition to the first flow point and the second flow point, the flow points may also include a third flow point, a fourth flow point, etc. In some embodiments, the flow points are tested in descending order. In this way, during the rough adjustment process, standard working-level ultrasonic flowmeters and turbine flowmeters are prevented from being damaged due to the flow in the pipeline exceeding the measuring range.

[0094] In some embodiments, the flow rate regulation method of a natural gas metering station further includes: obtaining reliability results according to chromatographic information of the flow points.

[0095] The chromatographic information can be obtained by a set chromatographic device. The chromatographic device can be an online gas chromatograph. The online gas chromatograph can measure the composition and quality of natural gas, including the content of components such as methane, ethane, propane, and nitrogen.

[0096] In one implementation, two chromatographic devices are provided. Thus, during the calibration operation, the chromatographic devices are configured according to the actual needs on site. The reliability of the calibration results is ensured by observing the chromatographic information in real time.

[0097] The flow regulation method of the natural gas metering station provided in the embodiment of the present application is studied on the basis of the calibration management and control unit to realize the full life cycle management function of the flow meter sent for inspection, and the calibration system has the automatic switching function of the secondary standard device pipeline. The process switching, pressure regulation, flow regulation, calibration operation, calibration process results and the judgment and processing of the calibration results in the calibration process all need to be completed automatically, and the pressure and flow regulation are automatically controlled.

[0098] In addition, the actual flow calibration process of the flow meter is calibrated by using intelligent control strategies combined with digital twin models. Based on the actual needs of intelligent calibration, the flow control strategy in the flow meter calibration operation is studied and analyzed, and the results obtained by the model established by machine learning are compared and analyzed with the actual operation of traditional manual operation. The machine learning model is continuously optimized to obtain the optimal solution to obtain a complete set of intelligent control strategies, and the traditional manual operation based on the calibration procedure is realized in the form of intelligent control software. After on-site testing, the test report analysis shows that the solution is accurate and feasible. It verifies that the research work on the calibration of natural gas flow meters using artificial intelligence and big data technology is feasible.

[0099] In some embodiments, on the day before the start of the calibration, the process is cut according to the calibration task of the next day, and the gas line is selected according to the gas quality composition of the incoming gas source. After the gas source is selected, the pipeline in the station is first connected, that is, the ball valve on the selected line is fully opened, and the regulating valve is fully opened. After the connection is completed, the valve on the incoming gas pipeline is closed to introduce the gas source into the station through the connection line, and then enter the downstream of the incoming gas pipeline. The data collection device is a software embedded in the computer, which can collect relevant information during the flow meter calibration process.

[0100] Among them, the gas source is the gas from the upstream gas transmission station, and the gas lines are divided into branch lines and trunk lines and are owned by this station.

[0101] In some embodiments, on the day of the calibration, the task arrangement is delegated to the flow control system of the natural gas metering station. The task arrangement is transferred to the calibration operation system (calibration client) for calibration setting, and the calibration information (including: calibration flow point, calibration number, calibration time) is entered to prepare for the calibration operation.

[0102] The embodiments of the present application also provide a flow regulation system for a natural gas metering station. The system is a visualization system. The flow regulation system includes a station control machine, which is provided with a screen for user operation. In some embodiments, the calibration operation is started, the calibration flow point is checked on the station control machine, and the flow is regulated by adjusting the opening of the regulating valve on the station control machine.

[0103] In some embodiments, the flow regulation system of the natural gas metering station also includes an engineer workstation module, and the valve opening size and valve switch records are stored in the engineer workstation module.

[0104] Based on the same application concept, a flow regulation system for a natural gas metering station is also provided in an embodiment of the present application. The method corresponding to the flow regulation system for the natural gas metering station may be the flow regulation method for the natural gas metering station in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The flow regulation system for the natural gas metering station provided in an embodiment of the present application includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0105] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application described above.

[0106] Specifically, the present embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0107] Computer readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0108] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0109] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0110] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0115] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0117] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A flow regulation method for a natural gas metering station, characterized in that: include: Determine a first pressure comparison value and a first temperature comparison value of a first level standard; Determine a second pressure comparison value and a second temperature comparison value of a second level standard; Determine a flow point and a flow value of the flow point based on a first pressure comparison value, a first temperature comparison value, a second pressure comparison value, a second temperature comparison value and a first frequency; the flow value includes an instantaneous flow; According to the flow value, based on the machine learning model, the flow adjustment parameters and pipeline combination results of the flow point are calculated; the flow adjustment parameters include valve opening value, regulating valve caliber and regulating valve model; the pipeline combination results are used to characterize the size, quantity and connection method of the standard meter pipeline; Wherein, the standard meter pipeline includes a verification ultrasonic flowmeter and a standard turbine flowmeter; the first frequency is the frequency of the standard turbine flowmeter; the verification ultrasonic flowmeter and the standard turbine flowmeter are used to collect the flow value.

2. The flow rate regulation method of a natural gas metering station according to claim 1, characterized in that: The flow points include a first flow point and a second flow point; After adjusting the flow rate based on the flow rate adjustment parameter of the first flow rate point and the pipeline combination result, the flow rate adjustment method of the natural gas metering station further includes: adjusting the current flow rate based on the flow rate adjustment parameter of the second flow rate point; Based on the pipeline combination result of the second flow point, the current line is replaced.

3. The flow rate regulation method of a natural gas metering station according to claim 1 or 2, characterized in that: The flow regulation method of the natural gas metering station also includes: A reliability result is obtained according to the chromatographic information of the flow point.

4. The flow rate regulating method of a natural gas metering station according to claim 1 or 2, characterized in that: When executing the step of calculating the flow regulation parameters and pipeline combination results of the flow point according to the flow value based on the machine learning model, the machine learning model is a SENet network.

5. The flow rate regulating method of a natural gas metering station according to claim 1 or 2, characterized in that: When executing the step of determining the flow point and the flow value of the flow point based on the first pressure comparison value, the first temperature comparison value, the second pressure comparison value, the second temperature comparison value and the first frequency, the flow regulation method of the natural gas metering station further includes: Based on a plurality of continuous flow monitoring values, the flow value of the flow point is obtained.

6. The flow rate regulating method of a natural gas metering station according to claim 1 or 2, characterized in that: When executing the step of calculating the flow control parameters and pipeline combination results of the flow point according to the flow value based on the machine learning model, the flow control method of the natural gas metering station also includes: determining the caliber of the regulating valve based on the gas source flow value.

7. The flow rate regulation method of a natural gas metering station according to claim 4, characterized in that: The number of the standard meter pipelines is eight; the eight standard meter pipelines include five standard meter pipelines with a diameter of 250.

8. A flow control system for a natural gas metering station, characterized in that: include: The calibration module comprises a multi-channel standard meter pipeline, each of which comprises a verification ultrasonic flowmeter and a standard turbine flowmeter; the verification ultrasonic flowmeter and the standard turbine flowmeter are used to collect flow values; the flow values ​​are determined based on a first pressure comparison value, a first temperature comparison value, a second pressure comparison value, a second temperature comparison value and a first frequency; A control module, used for receiving a first parameter sent by the standard turbine flowmeter; the first parameter includes frequency, temperature and pressure; A machine learning module is used to calculate the flow regulation parameters and pipeline combination results of the flow point according to the flow value based on a machine learning model.

9. A flow control system for a natural gas metering station, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8.

10. A computer readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images