An Internet of Things-based flow metering method, system and device

Abstract

The present invention belongs to the technical field of flow metering, and discloses a flow metering method, system and device based on the Internet of Things. The method includes monitoring data collection and transmission, monitoring data preprocessing, analyzing the initial volumetric flow rate, analyzing the mass flow rate, and displaying the flow monitoring data. The system includes a monitoring data collection and transmission module, a monitoring data preprocessing module, an initial volumetric flow rate analysis module, a mass flow rate analysis module, and a flow monitoring data display module. By comprehensively using ultrasonic and differential pressure flow sensors for multi-dimensional data acquisition, combining Internet of Things data acquisition nodes with convolutional neural networks for working condition identification, calculating the volumetric flow rate according to the fusion weight matrix, then converting the mass flow rate according to the mass flow rate calculation model, and transmitting it to the remote monitoring center through the Internet of Things communication module, the natural gas mass flow rate can be measured with high precision under different working conditions, solving the problem that the measurement accuracy of the traditional method is limited in the full working condition range.

Description

Technical Field

[0001] The present invention belongs to the technical field of flow measurement, and particularly relates to a flow measurement method, system and device based on the Internet of Things. Background Art

[0002] With the continuous adjustment of the energy structure, natural gas, as a clean and efficient energy source, has been increasingly widely used in various fields such as industrial production, chemical preparation and residential life. During the transportation process of natural gas from the production end to the use end, accurately measuring its flow rate is not only crucial for the reasonable allocation and efficient utilization of energy, but also an important guarantee for the fairness and justice of natural gas trade settlement. However, traditional natural gas flow measurement technologies face many challenges in practical applications, especially the problem of limited measurement accuracy under complex working conditions, which has become the key bottleneck restricting the development of natural gas flow measurement technologies.

[0003] In the prior art, natural gas flow measurement mainly relies on a single sensor or a fixed-weight fusion method. For example, ultrasonic flow sensors and differential pressure flow sensors are commonly used measurement tools, but their measurement accuracies vary under different working conditions. Ultrasonic flow sensors perform well at low flow rates, while differential pressure flow sensors are more accurate at high flow rates. However, traditional methods usually fuse the data of different sensors with fixed weights, which cannot flexibly adjust the weights according to changes in working conditions, resulting in limited measurement accuracy across the entire working condition range. In addition, traditional methods fail to fully utilize the influence of environmental parameters (such as temperature, pressure and natural gas composition) on flow measurement, further restricting the improvement of measurement accuracy.

[0004] In recent years, the rapid development of Internet of Things technology and machine learning algorithms has provided new ideas for solving the above problems. Internet of Things technology can realize the real-time collection and transmission of multi-source data, providing a richer data basis for flow measurement; while machine learning algorithms can identify and model complex working conditions through learning and analysis of historical data. Therefore, it is possible to consider combining these two technologies to develop an adaptive flow measurement method. Summary of the Invention

[0005] In view of the above existing problems, the purpose of the present invention is to provide a flow measurement method, system and device based on the Internet of Things, which can accurately measure the mass flow rate of natural gas under different working conditions and solve the problem of limited measurement accuracy of traditional methods across the entire working condition range.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A flow measurement method based on the Internet of Things, comprising the following steps:

[0007] S1. Monitoring data collection and transmission: Obtain the monitoring data during the normal transmission of natural gas and transmit the monitoring data to the IoT data acquisition node. The monitoring data includes the initial volumetric flow velocity vector collected by the ultrasonic flow sensor, the volumetric flow velocity vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor.

[0008] S2. Pretreatment of monitoring data: After receiving the monitoring data, the IoT data acquisition node performs pretreatment on it.

[0009] S3. Analyze the initial volumetric flow: Based on the pretreated monitoring data, perform working condition identification to generate a working condition feature vector, and analyze the volumetric flow based on the working condition feature vector.

[0010] S4. Analyze the mass flow: Analyze the mass flow based on the volumetric flow and the environmental monitoring data.

[0011] S5. Display of flow monitoring data: Transmit the volumetric flow, mass flow, and monitoring data to the remote monitoring center through the IoT communication module for visual monitoring in the remote monitoring center.

[0012] Preferably, in the above S1, the steps for collecting the initial volumetric flow velocity vector by the ultrasonic flow sensor include the following:

[0013] S111. Transmit ultrasonic pulses into the natural gas pipeline through the transmitting transducer of the ultrasonic flow sensor, and the receiving transducer receives the ultrasonic signal after propagation through the natural gas medium.

[0014] S112. Obtain the inner diameter of the pipeline, and measure the time of downstream propagation and the time of upstream propagation of ultrasonic waves in the natural gas medium.

[0015] S113. Based on the time of downstream propagation, the time of upstream propagation, and the inner diameter of the pipeline, calculate the initial volumetric flow velocity vector of natural gas through the initial volumetric flow velocity vector calculation formula.

[0016] The initial volumetric flow velocity vector calculation formula is:

[0017] ;

[0018] where, is the initial volumetric flow velocity vector, C is a constant, is the time of downstream propagation, is the time of upstream propagation, and D is the inner diameter of the pipeline.

[0019] Preferably, in the above S1, the steps for collecting the volumetric flow velocity vector by the differential pressure flow sensor include the following:

[0020] S121. When natural gas flows through the throttling device in the differential pressure flow sensor, use a pressure sensor to measure the pressure difference generated before and after the throttling device. The differential pressure flow sensor is installed at a preset position on the natural gas pipeline;

[0021] S122. According to the relationship curve of natural gas differential pressure - flow velocity characteristics set in the database, convert the measured pressure difference into the volumetric flow velocity vector of natural gas.

[0022] Preferably, in step S3, generating the working condition characteristic vector includes the following steps:

[0023] S311. Obtain the natural gas working condition identification model on the Internet of Things data acquisition node;

[0024] S312. Analyze the monitoring data through the natural gas working condition identification model to generate the working condition characteristic vector;

[0025] The acquisition method of the natural gas working condition identification model is as follows:

[0026] Obtain the historical natural gas flow monitoring data sets under various working conditions and divide them into a training set and a test set;

[0027] Mark the working condition categories for the natural gas flow monitoring data sets corresponding to each working condition information in the training set;

[0028] Input the marked natural gas flow monitoring data sets into a convolutional neural network for training, and output the primary natural gas working condition identification model;

[0029] Test the primary natural gas working condition identification model through the test set, and output the natural gas working condition identification model.

[0030] Preferably, in step S3, analyzing the volumetric flow based on the working condition characteristic vector includes the following steps:

[0031] S321. According to the generated working condition characteristic vector, retrieve the fusion weight matrix in the database. The fusion weight matrix includes the weights of the ultrasonic flow sensor and the differential pressure flow sensor for the measurement results under different working conditions;

[0032] S322. Perform weighted fusion on the initial volumetric flow velocity vector and the volumetric flow velocity vector according to the natural gas volumetric flow velocity formula to obtain the final natural gas volumetric flow velocity ,

[0033] S323. Combine the cross-sectional area S of the pipeline and calculate the natural gas volumetric flow through the formula .

[0034] Preferably, the natural gas volumetric flow velocity formula is:

[0035] ;

[0036] Wherein, is the weight of the ultrasonic flow sensor under the j-th working condition for ; is the weight of the differential pressure flow sensor under the j-th working condition for ; j is the working condition type number, is the initial volume flow rate vector, is the volume flow rate vector.

[0037] Preferably, in the step S4, analyzing the mass flow rate based on the volume flow rate and the environmental monitoring data includes the following steps:

[0038] S401. Obtain the natural gas volume flow rate, and extract the temperature, pressure and natural gas component data from the environmental monitoring data;

[0039] S402. Calculate the mass flow rate of the natural gas by using the mass flow rate calculation model.

[0040] Preferably, the mass flow rate calculation model is:

[0041] ;

[0042] Wherein, is the mass flow rate, is the volume flow rate, is the molar mass of the i-th component, i is the natural gas component type number, and n is the total number of natural gas component types, , is the molar fraction of the i-th component, Z is the compression factor of the natural gas, R is the universal gas constant, T is the temperature, and P is the pressure.

[0043] An Internet of Things-based flow metering system for implementing the above method, comprising a monitoring data collection and transmission module, a monitoring data preprocessing module, an initial volume flow rate analysis module, a mass flow rate analysis module, and a flow monitoring data display module, wherein:

[0044] The monitoring data collection and transmission module is used to obtain the monitoring data during the normal transportation of natural gas and transmit the monitoring data to the Internet of Things data acquisition node. The monitoring data includes the initial volume flow rate vector collected by the ultrasonic flow sensor, the volume flow rate vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor;

[0045] The monitoring data preprocessing module is used to preprocess the monitoring data after the Internet of Things data acquisition node receives the monitoring data;

[0046] The initial volume flow rate analysis module is used to identify the working conditions based on the preprocessed monitoring data, generate the working condition feature vectors, and analyze the volume flow rate based on the working condition feature vectors;

[0047] The mass flow rate analysis module is used to analyze the mass flow rate based on the volume flow rate and the environmental monitoring data;

[0048] The flow monitoring data display module is used to transmit the volume flow rate, the mass flow rate, and the monitoring data to the remote monitoring center through the Internet of Things communication module for visual monitoring in the remote monitoring center.

[0049] A flow metering device based on the Internet of Things includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The above system is implemented by the processor executing the computer program.

[0050] The beneficial effects of the present invention are as follows:

[0051] By comprehensively using ultrasonic and differential pressure flow sensors for multi-dimensional data acquisition, combining the Internet of Things data acquisition nodes with the convolutional neural network for working condition identification, calculating the volume flow rate according to the fusion weight matrix, then converting the mass flow rate according to the mass flow rate calculation model, and transmitting it to the remote monitoring center through the Internet of Things communication module, the natural gas mass flow rate can be measured with high precision under different working conditions, solving the problem that the measurement accuracy of the traditional method is limited in the full working condition range.

[0052] By transmitting the collected multi-source data to the Internet of Things data acquisition nodes for preliminary processing, and then using machine learning algorithms to mine the working condition characteristics in the data to generate the working condition feature vectors, the complex working conditions of the natural gas at present can be described, and then the flow calculation process can be more in line with the actual working conditions, avoiding large errors generated by the general calculation method under special working conditions.

[0053] Based on the working condition feature vectors, the volume flow rate data collected by different sensors are weighted and fused to obtain the accurate volume flow rate, and then combined with the environmental monitoring data and substituted into the mass flow rate calculation model to calculate the mass flow rate, thus realizing a high-precision flow metering method with full working condition adaptability and comprehensive consideration of multiple factors, which is conducive to reasonably planning the natural gas resource allocation, optimizing the energy utilization structure, and ensuring the efficient and stable operation of the entire natural gas industrial chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow schematic diagram of the method of the present invention;

[0055] Figure 2 It is a module schematic diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0056] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings of the specification.

[0057] Embodiment 1:

[0058] As Figure 1 shown, a flow metering method based on the Internet of Things includes the following steps:

[0059] S1. Monitoring data collection and transmission: Obtain the monitoring data during the normal transmission of natural gas, and transmit the monitoring data to the Internet of Things data acquisition node. The monitoring data includes the initial volumetric flow velocity vector collected by the ultrasonic flow sensor, the volumetric flow velocity vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor;

[0060] S2. Monitoring data preprocessing: After receiving the monitoring data, the Internet of Things data acquisition node performs preprocessing on it;

[0061] S3. Analyze the initial volumetric flow: Based on the preprocessed monitoring data, perform working condition identification to generate a working condition feature vector, and analyze the volumetric flow based on the working condition feature vector;

[0062] S4. Analyze the mass flow: Analyze the mass flow based on the volumetric flow and the environmental monitoring data;

[0063] S5. Display of flow monitoring data: Transmit the volumetric flow, mass flow, and monitoring data to the remote monitoring center through the Internet of Things communication module for visual monitoring in the remote monitoring center.

[0064] The Internet of Things data acquisition node can establish connections with multiple sensors. In the scenario of natural gas flow measurement, it will be connected to ultrasonic flow sensors, differential pressure flow sensors, environmental multi-parameter sensors, etc. simultaneously. These sensors continuously generate monitoring data during the transmission of natural gas, and the Internet of Things data acquisition node aggregates the information from different sensors together. For example, the ultrasonic flow sensor will generate ultrasonic flow monitoring data, reflecting the natural gas flow information measured by the ultrasonic principle; the differential pressure flow sensor will output differential pressure flow monitoring data, reflecting the flow information obtained based on the differential pressure principle; the environmental multi-parameter sensor will provide environmental monitoring data such as temperature and pressure. The Internet of Things data acquisition node receives these data from different sources and of different types, and centrally forms a complete data set.

[0065] The Internet of Things communication module is a hardware module integrating a communication chip, peripheral circuits, and communication protocols. Its main function is to connect the Internet of Things data acquisition node to the network and realize data transmission between the device and the remote monitoring center, which can be implemented using well-known technologies.

[0066] In S1, collecting the initial volumetric flow velocity vector by an ultrasonic flow sensor includes the following steps:

[0067] S111. Transmit ultrasonic pulses into the natural gas pipeline through the transmitting transducer of the ultrasonic flow sensor, and the receiving transducer receives the ultrasonic signal after propagation through the natural gas medium;

[0068] S112. Obtain the inner diameter of the pipeline, and measure the time of downstream propagation and the time of upstream propagation of ultrasonic waves in the natural gas medium;

[0069] S113. Based on the time of downstream propagation, the time of upstream propagation, and the inner diameter of the pipeline, calculate the initial volumetric flow velocity vector of natural gas through the initial volumetric flow velocity vector calculation formula.

[0070] The initial volumetric flow velocity vector calculation formula is:

[0071] ;

[0072] Wherein, is the initial volumetric flow velocity vector, C is a constant, is the time of downstream propagation, is the time of upstream propagation, and D is the inner diameter of the pipeline.

[0073] Collecting the volumetric flow velocity vector by a differential pressure flow sensor includes the following steps:

[0074] S121. When natural gas flows through the throttling device in the differential pressure flow sensor, use a pressure sensor to measure the pressure difference generated before and after the throttling device. The differential pressure flow sensor is installed at a preset position (the installation position is selected according to needs) in the natural gas pipeline;

[0075] S122. According to the natural gas differential pressure - flow velocity characteristic relationship curve set in the database, convert the measured pressure difference into the volumetric flow velocity vector of natural gas.

[0076] Common throttling devices include orifice plates, Venturi tubes, nozzles, etc. According to Bernoulli's principle, due to the change in the flow velocity of natural gas, a pressure difference will be generated before and after the throttling device. Because when natural gas flows through the throttling device, the flow area changes and the flow velocity increases. According to the law of conservation of energy, the pressure will decrease accordingly.

[0077] In S3, generating the working condition characteristic vector includes the following steps:

[0078] S311. On the IoT data acquisition node, obtain the natural gas condition recognition model. The IoT data acquisition node serves as the data processing and transmission hub of the entire system and can store or access the natural gas condition recognition model. The natural gas condition recognition model is a pre-trained algorithm model used to identify different conditions during natural gas transportation.

[0079] S312. Analyze the monitoring data through the natural gas condition recognition model to generate a condition feature vector.

[0080] The acquisition method of the natural gas condition recognition model is as follows:

[0081] Obtain historical natural gas flow monitoring data sets under various conditions and divide them into a training set and a test set.

[0082] Mark the natural gas flow monitoring data sets corresponding to each condition information in the training set. Mark the data with low flow velocity, high pressure, and low temperature as the "low flow velocity - high pressure - low temperature" condition, and mark the data with high flow velocity, moderate pressure, and high temperature as the "high flow velocity - medium pressure - high temperature" condition, etc. Through this marking, a clear learning target is provided for the natural gas condition recognition model, enabling the model to learn the mapping relationship between the characteristics of different conditions and the corresponding category labels during the training process.

[0083] Input the marked natural gas flow monitoring data sets into a convolutional neural network for training to output a primary natural gas condition recognition model.

[0084] Test the primary natural gas condition recognition model through the test set to output the natural gas condition recognition model.

[0085] The convolutional neural network can adopt a well-known architecture or a dedicated convolutional neural network. For example, a convolutional neural network architecture specifically applicable to this embodiment includes a multi-modal input fusion module, a dynamic weight adjustment module, a depthwise separable convolution module, a multi-scale feature fusion module, and an adaptive condition classification module, where:

[0086] The structure of the multi-modal input fusion module includes:

[0087] Input layer: Take the ultrasonic flow sensor data, differential pressure flow sensor data, and environmental parameters (temperature, pressure, composition) as independent input channels respectively.

[0088] Feature extraction layer: Design independent convolutional layers for each modality to extract their features respectively. For example:

[0089] Ultrasonic data: Use a 1D convolutional layer to extract time series features.

[0090] Differential pressure data: Use a 1D convolutional layer to extract the characteristics of the pressure difference change;

[0091] Environmental parameters: Use a fully connected layer to convert parameters such as temperature, pressure, and composition into feature vectors;

[0092] Fusion layer: Through an attention mechanism module, dynamically adjust the weights of each modality data under different working conditions to achieve adaptive fusion.

[0093] The dynamic weight adjustment module includes:

[0094] Working condition feature extraction: Extract the working condition feature vector in the middle layer of the CNN;

[0095] Weight generation network: Input the working condition feature vector into a small fully connected network and output the weights of each sensor data;

[0096] Weight application: Apply the generated weights to the output of the multi-modal input fusion module to obtain the weighted feature vector.

[0097] The depthwise separable convolution module includes:

[0098] Depthwise convolution: Independently perform convolution operations on each input channel to extract local features;

[0099] Pointwise convolution: Use 1×1 convolution to perform channel fusion on the output of the depthwise convolution to generate the final feature map.

[0100] The multi-scale feature fusion module includes:

[0101] Multi-scale convolution: Use different-sized convolution kernels (such as 3×3, 5×5, 7×7) to extract features in parallel;

[0102] Feature fusion: Through skip connection and concatenation, fuse the feature maps of different scales;

[0103] Feature enhancement: Use a lightweight attention module to enhance key features and suppress redundant features.

[0104] The adaptive working condition classification module includes:

[0105] Working condition classification network: Based on the extracted working condition feature vector, output the working condition category through a fully connected network;

[0106] Weight adjustment network: Dynamically adjust the weights of the sensor data according to the working condition category to generate a fusion weight matrix;

[0107] Output layer: Combine the working condition category and the weight matrix to output the final working condition feature vector and weight matrix for subsequent flow calculation.

[0108] The analysis of the volumetric flow rate based on the operating condition characteristic vector includes the following steps:

[0109] S321. According to the generated operating condition characteristic vector, retrieve the fusion weight matrix in the database. The fusion weight matrix includes the weights of the ultrasonic flow sensor and the differential pressure flow sensor for the measurement results under different operating conditions;

[0110] S322. Perform weighted fusion on the initial volumetric flow velocity vector and the volumetric flow velocity vector according to the natural gas volumetric flow velocity formula to obtain the final natural gas volumetric flow velocity ,

[0111] S323. Combine the cross-sectional area S of the pipeline and calculate the natural gas volumetric flow rate through the formula .

[0112] The natural gas volumetric flow velocity formula is:

[0113] ;

[0114] Among them, is the weight of the ultrasonic flow sensor for under the j-th operating condition, is the weight of the differential pressure flow sensor for under the j-th operating condition, j is the number of the operating condition type, is the initial volumetric flow velocity vector, is the volumetric flow velocity vector.

[0115] The rows of the fusion weight matrix represent different operating condition categories, and the columns represent the weights of the ultrasonic flow sensor and the differential pressure flow sensor respectively; the fusion weight matrix W can be expressed as:

[0116] ;

[0117] Among them, M is the total number of operating conditions.

[0118] In S4, the analysis of the mass flow rate based on the volumetric flow rate and the environmental monitoring data includes the following steps:

[0119] S401. Obtain the natural gas volumetric flow rate and extract the temperature, pressure, and natural gas composition data from the environmental monitoring data;

[0120] S402. Calculate the natural gas mass flow rate using the mass flow rate calculation model.

[0121] The mass flow rate calculation model is:

[0122] ; ​

[0123] Among them, is the mass flow rate, is the volumetric flow rate, is the molar mass of the i-th component, i is the serial number of the natural gas component type, and n is the total number of natural gas component types. , is the molar fraction of the i-th component, Z is the dimensionless compressibility factor of natural gas, obtained through the AGA8 equation, R is the universal gas constant, with a value of 8.314 J / (mol·K), T is the temperature, and P is the pressure.

[0124] Example 2:

[0125] Based on Example 1, this example further includes:

[0126] S6. Dynamic adaptive model optimization: Based on the changes in real-time monitoring data and environmental parameters, the natural gas operating condition identification model and / or the mass flow rate calculation model are dynamically updated through an online learning algorithm. The steps include:

[0127] S611. Real-time collect natural gas flow monitoring data, environmental monitoring data, and the corresponding actual operating condition labels;

[0128] S612. Take the newly collected data as an incremental training set and input it into the natural gas operating condition identification model and / or the mass flow rate calculation model, and use the online transfer learning algorithm to iteratively optimize the model parameters;

[0129] S613. Dynamically adjust the fusion weight matrix, the compressibility factor Z, or the molar fraction of natural gas components according to the optimized model parameters to improve the real-time accuracy of flow rate calculation;

[0130] S614. When it is detected that the environmental parameters change suddenly or the operating condition feature vector exceeds the preset threshold, trigger the global calibration of the model parameters and generate an optimization log for transmission to the remote monitoring center.

[0131] By introducing the online transfer learning algorithm, the model parameters can be dynamically optimized according to real-time data, solving the problem of the accuracy degradation of traditional static models under complex operating conditions or sudden environmental changes, and significantly improving the adaptive ability. Combining the incremental training and the global calibration mechanism not only ensures the real-time responsiveness of the model but also avoids the model degradation caused by local data deviation, enhancing the robustness and reliability of flow measurement.

[0132] Example 3:

[0133] Such as Figure 2As shown in the figure, an Internet of Things-based flow metering system for implementing the method in Embodiment 1 or Embodiment 2 includes a monitoring data collection and transmission module, a monitoring data preprocessing module, an initial volumetric flow analysis module, a mass flow analysis module, and a flow monitoring data display module, where:

[0134] The monitoring data collection and transmission module is used to obtain the monitoring data during the normal transmission of natural gas and transmit the monitoring data to the Internet of Things data acquisition node. The monitoring data includes the initial volumetric flow velocity vector collected by the ultrasonic flow sensor, the volumetric flow velocity vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor;

[0135] The monitoring data preprocessing module is used to preprocess the monitoring data after it is received by the Internet of Things data acquisition node;

[0136] The initial volumetric flow analysis module is used to identify the working conditions based on the preprocessed monitoring data, generate the working condition feature vector, and analyze the volumetric flow based on the working condition feature vector;

[0137] The mass flow analysis module is used to analyze the mass flow based on the volumetric flow and the environmental monitoring data;

[0138] The flow monitoring data display module is used to transmit the volumetric flow, the mass flow, and the monitoring data to the remote monitoring center through the Internet of Things communication module for visual monitoring in the remote monitoring center.

[0139] Embodiment 4:

[0140] An Internet of Things-based flow metering device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The system in Embodiment 3 is implemented by the processor executing the computer program.

Claims

1. A flow metering method based on the Internet of Things, characterized in that: The following steps are involved: S1. Monitoring data collection and transmission: Acquire monitoring data during the normal natural gas transportation process and transmit the monitoring data to the IoT data collection node. The monitoring data includes the initial volume flow velocity vector collected by the ultrasonic flow sensor, the volume flow velocity vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor; S2. Monitoring data preprocessing: After receiving the monitoring data, the IoT data collection node preprocesses it; S3. Analyze the initial volume flow rate: identify the working condition based on the preprocessed monitoring data, generate a working condition feature vector, and analyze the volume flow rate based on the working condition feature vector; S4. Analyze mass flow: Analyze mass flow based on volume flow and environmental monitoring data; S5. Flow monitoring data display: The volume flow, mass flow and monitoring data are transmitted to the remote monitoring center through the Internet of Things communication module, and visual monitoring is performed in the remote monitoring center; In S3, analyzing the volume flow rate based on the operating condition characteristic vector includes the following steps: S321, according to the generated working condition feature vector, retrieve the fusion weight matrix in the database, the fusion weight matrix includes the weights of the ultrasonic flow sensor and the differential pressure flow sensor for the measurement results under different working conditions; S322, weighted fusion of the initial volume flow velocity vector and the volume flow velocity vector is performed according to the natural gas volume flow velocity formula to obtain the final natural gas volume flow velocity , S323, combined with the cross-sectional area S of the pipe, through the formula Calculate the natural gas volume flow ; The natural gas volume flow rate formula is: ； in, For the jth working condition, the ultrasonic flow sensor The weight of For the jth working condition, the differential pressure flow sensor is The weight of, j is the working condition type number, is the initial volume flow velocity vector, is the volume flow velocity vector.

2. A flow metering method based on the Internet of Things as claimed in claim 1, characterized in that: In S1, collecting the initial volume flow velocity vector by the ultrasonic flow sensor includes the following steps: S111, transmitting an ultrasonic pulse into the natural gas pipeline through a transmitting transducer of the ultrasonic flow sensor, and receiving the ultrasonic signal after being transmitted through the natural gas medium through a receiving transducer; S112, obtaining the inner diameter of the pipeline, and measuring the propagation time of the ultrasonic wave in the natural gas medium along the flow and against the flow; S113, calculating the initial volume flow velocity vector of the natural gas based on the downstream propagation time, the upstream propagation time, and the inner diameter of the pipeline by using the initial volume flow velocity vector calculation formula; The initial volume flow velocity vector calculation formula is: ； in, is the initial volume flow rate vector, C is a constant, is the time for downstream propagation, is the time of countercurrent propagation, and D is the inner diameter of the pipe.

3. A flow metering method based on the Internet of Things as claimed in claim 1, characterized in that: In S1, collecting the volume flow velocity vector by using a differential pressure flow sensor includes the following steps: S121. When natural gas flows through the throttling device in the differential pressure flow sensor, the pressure difference generated before and after the throttling device is measured by the pressure sensor. The differential pressure flow sensor is installed at a preset position of the natural gas pipeline. S122. According to the natural gas differential pressure-flow rate characteristic relationship curve set in the database, the measured pressure difference is converted into a volume flow rate vector of the natural gas.

4. A flow metering method based on the Internet of Things as claimed in claim 1, characterized in that: In S3, generating the operating condition feature vector includes the following steps: S311. Obtaining a natural gas operating condition identification model on an IoT data collection node; S312, analyzing the monitoring data through a natural gas operating condition identification model to generate an operating condition feature vector; The natural gas operating condition identification model is obtained as follows: Obtain historical natural gas flow monitoring data sets under various working conditions and divide them into training sets and test sets; Mark the working condition category of the natural gas flow monitoring data group corresponding to each working condition information in the training set; The labeled natural gas flow monitoring data set is input into the convolutional neural network for training, and a primary natural gas operating condition recognition model is output; The primary natural gas operating condition identification model is tested through the test set, and the natural gas operating condition identification model is output.

5. A flow metering method based on the Internet of Things as claimed in claim 1, characterized in that: In S4, analyzing the mass flow rate based on the volume flow rate and environmental monitoring data includes the following steps: S401, obtaining natural gas volume flow, and extracting temperature, pressure and natural gas composition data from environmental monitoring data; S402. Calculate the mass flow rate of natural gas using a mass flow rate calculation model.

6. A flow metering method based on the Internet of Things as claimed in claim 5, characterized in that: The mass flow calculation model is: ； in, is the mass flow rate, is the volume flow rate, is the molar mass of the i-th component, i is the number of the natural gas component type, n is the total number of natural gas component types, , is the mole fraction of the ith component, Z is the compressibility factor of natural gas, R is the universal gas constant, T is the temperature, and P is the pressure.

7. A flow metering system based on the Internet of Things, used to implement the method described in any one of claims 1 to 6, characterized in that: It includes monitoring data collection and transmission module, monitoring data preprocessing module, initial volume flow analysis module, mass flow analysis module, and flow monitoring data display module, among which: The monitoring data collection and transmission module is used to obtain the monitoring data during the normal natural gas transportation process and transmit the monitoring data to the IoT data collection node. The monitoring data includes the initial volume flow velocity vector collected by the ultrasonic flow sensor, the volume flow velocity vector collected by the differential pressure flow sensor, and the environmental monitoring data collected in real time by the environmental multi-parameter sensor; The monitoring data preprocessing module is used to preprocess the monitoring data after it is received by the IoT data collection node; An initial volume flow analysis module is used to identify the working condition based on the pre-processed monitoring data, generate a working condition feature vector, and analyze the volume flow based on the working condition feature vector; Analytical mass flow module, used to analyze mass flow based on volume flow and environmental monitoring data; The flow monitoring data display module is used to transmit the volume flow, mass flow and monitoring data to the remote monitoring center through the Internet of Things communication module, and perform visual monitoring in the remote monitoring center.

8. A flow metering device based on the Internet of Things, characterized in that: The system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the system described in claim 7 is implemented by executing the computer program by the processor.

Images