Flowmeter on-line calibration system and calibration method

Abstract

The invention provides a flowmeter online calibration system and method, and the method comprises the steps: firstly collecting a real-time operation data set of a target flowmeter in a pipeline operation environment, and covering dynamic monitoring data and environment state data; preprocessing the data set to obtain an operation data sequence capable of describing the change trend of the operation state of the flowmeter at multiple continuous time nodes, inputting the operation data sequence into a pre-trained calibration parameter generation model, and generating a calibration parameter set comprising a flow correction coefficient, an environment compensation factor and an error adjustment threshold value; and adjusting and measuring output data in real time based on the calibration parameter set, generating a calibrated flow measurement result, comparing the calibrated flow measurement result with a standard flow reference value for verification, and if the deviation is greater than an error adjustment threshold value, regenerating the calibration parameter set and performing iterative adjustment until the deviation is within a threshold value range, thereby realizing high-precision and self-adaptive online calibration of the flowmeter.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production, and in particular to an online calibration system and a calibration method for a flow meter. Background Art

[0002] In many fields such as industrial production, energy transmission, and environmental monitoring, accurate measurement of fluid flow is crucial for precise control of the production process, rational use of resources, and stable operation of the system. As a key device for measuring fluid flow, the measurement accuracy of the flow meter directly affects the performance and benefits of the entire system.

[0003] At present, in the field of flow meter calibration, the traditional calibration method mostly adopts offline calibration. This method requires the flow meter to be disassembled from the actual operating pipeline system, transported to a special calibration laboratory, and calibrated using standard flow equipment. Offline calibration is not only cumbersome, time-consuming and labor-intensive, but also causes the operation of the pipeline system to be interrupted, affecting the continuity of production and increasing the operating costs of the enterprise.

[0004] Even if some existing technologies attempt to perform online calibration, they often only focus on the flow data output by the flow meter itself, ignoring the impact of the pipeline operating environment on the flow meter measurement results. In addition, the existing calibration technology lacks adaptability to the dynamic changes in the flow meter's operating status. During long-term operation, the performance of the flow meter will change over time, and the fixed calibration method cannot track these changes in real time, resulting in a gradual decrease in calibration accuracy, making it difficult to meet the increasingly high flow measurement accuracy requirements.

[0005] Moreover, in the existing calibration process, the verification and adjustment methods for the calibration results are relatively simple and rough. Often, the measured value is simply compared with the standard value, and there is a lack of effective feedback adjustment mechanism to ensure the accuracy of the calibration results. Once a deviation occurs, it is difficult to quickly and accurately adjust the calibration parameters to achieve the ideal calibration effect. Summary of the invention

[0006] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a flow meter online calibration method, the method comprising: Collecting a real-time operating data set of a target flow meter in a pipeline operating environment, wherein the real-time operating data set includes dynamic monitoring data generated by the target flow meter during fluid transportation and environmental status data corresponding to the pipeline operating environment; Performing data preprocessing on the real-time operation data set to obtain a preprocessed operation data sequence, wherein the preprocessed operation data sequence is used to describe the operation state change trend of the target flow meter at multiple consecutive time nodes; Inputting the preprocessed operation data sequence into a pre-trained calibration parameter generation model to generate a calibration parameter set matching the current operation state of the target flow meter, the calibration parameter set including a flow correction coefficient, an environmental compensation factor, and an error adjustment threshold; Based on the calibration parameter set, real-time adjustment is performed on the measurement output data of the target flow meter to generate a calibrated flow measurement result, and the calibrated flow measurement result is compared and verified with a preset standard flow reference value; When the deviation between the calibrated flow measurement result and the standard flow reference value is greater than the error adjustment threshold, an updated calibration parameter set is regenerated and the real-time adjustment is iteratively performed until the deviation is within the error adjustment threshold.

[0007] On the other hand, an embodiment of the present invention also provides a flow meter online calibration system, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0008] Based on the above aspects, the embodiment of the present application collects a real-time operation data set including dynamic monitoring data and environmental status data, and then pre-processes the real-time operation data set to obtain an operation data sequence, which can clearly describe the operation status change trend of the target flow meter at multiple continuous time nodes, thereby integrating the time series characteristics into the calibration process, and further, uses a pre-trained calibration parameter generation model to generate a calibration parameter set, wherein the comprehensive use of flow correction coefficients, environmental compensation factors, and error adjustment thresholds achieves multi-dimensional and precise correction of flow meter measurement errors. The flow correction coefficient is adjusted for the deviation of the flow measurement itself, the environmental compensation factor effectively compensates for the interference of different environmental conditions on the measurement results, and the error adjustment threshold provides a quantitative control standard for the calibration accuracy. This multi-parameter collaborative calibration method is a major breakthrough in the traditional single parameter calibration, significantly improving the flexibility and adaptability of calibration, and can better cope with various complex and changeable actual working conditions.

[0009] Then, based on the calibration parameter set, the measured output data is adjusted in real time and compared with the standard flow reference value for verification, realizing dynamic feedback and real-time optimization of the calibration process, ensuring that the flow meter always maintains a high measurement accuracy during operation, avoiding the accumulation of measurement deviations caused by long-term operation or environmental changes, and greatly improving the timeliness and accuracy of flow measurement.

[0010] Finally, when the deviation between the calibrated flow measurement result and the standard flow reference value is greater than the error adjustment threshold, iterative calibration is performed until the deviation is within the threshold range, further ensuring the accuracy of the calibration result, allowing the flow meter to automatically adapt to changing operating conditions and continuously provide high-precision flow measurement results. Through this adaptive calibration method, the frequency and workload of manual calibration are effectively reduced, and the stability and automation level of the entire flow measurement system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic diagram of the execution flow of the flow meter online calibration method provided by an embodiment of the present invention.

[0012] Figure 2 It is a schematic diagram of the hardware architecture of the flow meter online calibration system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 1 is a flow chart of an online calibration method for a flow meter provided by an embodiment of the present invention. The online calibration method for a flow meter is introduced in detail below.

[0014] Step S110, collecting a real-time operation data set of the target flow meter in the pipeline operation environment, wherein the real-time operation data set includes dynamic monitoring data generated by the target flow meter during fluid transportation and environmental status data corresponding to the pipeline operation environment.

[0015] In this embodiment, in a scenario of liquid flow measurement, consider a liquid delivery pipeline system in a chemical enterprise. The target flowmeter is installed on the pipeline to measure the flow of a certain chemical solution. This pipeline system is in a specific environment, and the surrounding environmental state data has a direct impact on the measurement accuracy of the flowmeter. The dynamic monitoring data generated by the target flowmeter during the fluid delivery process includes multiple aspects. For example, when the chemical solution flows in the pipeline, the sensor inside the flowmeter will continuously monitor the flow rate of the solution. It can be understood that there is a precise speed monitor inside the pipeline, which records the flow rate of the solution at every moment. At the same time, in terms of pressure, since the liquid will exert pressure on the pipe wall when flowing in the pipeline, the flowmeter will also monitor the changes in this pressure, which helps to monitor whether the flow state of the liquid in the pipeline is stable and other information. In terms of temperature, the chemical solution itself has a certain temperature, and heat exchange may occur with the pipe wall during the flow process, resulting in temperature changes. The flowmeter will also monitor the temperature of the solution.

[0016] In addition to these dynamic monitoring data directly related to the liquid flow, the environmental status data corresponding to the pipeline operation environment can also be loaded into the real-time operation data set. For example, the temperature of the surrounding environment has a significant impact on the entire pipeline system. If the ambient temperature is low, it may cause the pipe wall to dissipate heat faster, thereby affecting the temperature distribution of the solution in the pipe, and thus affecting the measurement accuracy of the flowmeter. The humidity of the surrounding environment should not be ignored. A high humidity environment may cause condensation on the outer wall of the pipe, which may have a slight effect on some physical properties of the pipe and indirectly affect the measurement of the flowmeter. In addition, there may be some vibration sources in the space where the pipeline is located. For example, if there are large mechanical equipment running nearby, the vibration generated is transmitted to the pipeline. This vibration may interfere with the normal operation of the internal components of the flowmeter and affect the accuracy of the measurement, so these vibration-related data will also be collected in the real-time operation data set. Therefore, by comprehensively collecting these data, a rich original data foundation is provided for subsequent flow calibration.

[0017] Step S120, performing data preprocessing on the real-time operation data set to obtain a preprocessed operation data sequence, wherein the preprocessed operation data sequence is used to describe the operation status change trend of the target flow meter at multiple continuous time nodes.

[0018] Let's continue with the example of liquid flow measurement in the above-mentioned chemical enterprise. For the temperature monitoring sub-data, extract the outer wall temperature measurement value and the fluid internal temperature measurement value of the pipeline where the target flowmeter is located, and calculate the difference between the outer wall temperature measurement value and the fluid internal temperature measurement value to obtain a temperature gradient change sequence. Assuming that when a chemical solution flows in a pipeline, the temperature sensor on the outer wall of the pipeline measures the outer wall temperature of 25 degrees Celsius at a certain moment, and at the same time the temperature sensor inside the fluid measures the temperature of the solution to be 30 degrees Celsius, then the difference between the two is -5 degrees Celsius. As time goes by, this difference at different moments constitutes a temperature gradient change sequence. This temperature gradient change sequence can reflect the dynamic situation of heat exchange between the liquid and the pipeline wall at different time nodes, which helps to discover temperature factors that may affect flow measurement.

[0019] For the pressure monitoring sub-data, the pressure fluctuation peak in the fluid flow direction in the pipeline operating environment is identified, and a pressure stability evaluation index is generated based on the frequency of occurrence of the pressure fluctuation peak. During the liquid transportation process, pressure fluctuations may occur due to the bends in the pipeline, the opening and closing of the valve, or the flow characteristics of the liquid itself. For example, when the liquid flows through a half-open valve, a local pressure change will be formed near the valve. If the pressure fluctuation peak occurs frequently within a certain period of time, it means that the flow state of the liquid is not stable. Assuming that the pressure fluctuation peak occurs 5 times within 10 minutes, this frequency of occurrence is converted into a pressure stability evaluation index through a specific algorithm. This index can quantify the pressure stability during the liquid flow process, thereby providing a basis for subsequent flow calibration.

[0020] For the flow rate monitoring sub-data, the rotor speed measurement value and the blade vibration amplitude measurement value of the target flow meter are obtained, and the rotor speed measurement value and the blade vibration amplitude measurement value are time-series aligned to generate a flow rate-related feature vector. For the rotor inside the flowmeter, its rotation speed is closely related to the flow rate of the liquid. When the rotor speed is faster, it usually means that the liquid flow rate is higher. At the same time, the vibration amplitude of the blade can also reflect some characteristics of the liquid flow. Assuming that at a certain moment, the rotor speed measurement value is 1000 revolutions per minute and the blade vibration amplitude is 0.5 mm, these data at the same time node are time-series aligned to generate a flow rate-related feature vector. As time goes by, the flow rate-related feature vectors at different times can comprehensively describe the changing trend of the flow rate-related data.

[0021] Finally, the temperature gradient change sequence, the pressure stability evaluation index and the flow rate associated characteristic vector are spliced ​​according to the time nodes to generate the pre-processed operation data sequence, wherein the data unit corresponding to each time node in the pre-processed operation data sequence contains the temperature gradient value, the pressure stability level and the flow rate associated value. In this way, a comprehensive data unit is generated at each time node. For example, the data unit at a certain moment may be a temperature gradient value of -3 degrees Celsius, a pressure stability level of medium (derived from the previous pressure stability evaluation index), and a flow rate associated value of [1200 rpm, 0.4 mm]. This data unit fully reflects the operating status related information of the target flowmeter in liquid flow measurement at that moment, and the entire pre-processed operation data sequence shows the operating status change trend at multiple consecutive time nodes.

[0022] Step S130, inputting the preprocessed operation data sequence into a pre-trained calibration parameter generation model to generate a calibration parameter set matching the current operation state of the target flow meter, wherein the calibration parameter set includes a flow correction coefficient, an environmental compensation factor, and an error adjustment threshold.

[0023] Still based on the liquid flow measurement scenario of chemical enterprises. The calibration parameter generation model includes a multi-level parameter generation unit. First, the first-level parameter generation unit is called to perform nonlinear mapping processing on the temperature gradient value in the preprocessed operating data sequence to generate a primary temperature compensation factor, and the primary temperature compensation factor is weighted and fused with the internal temperature measurement value of the fluid to obtain the final temperature compensation coefficient. Assuming that a temperature gradient value in the preprocessed operating data sequence is -2 degrees Celsius, after nonlinear mapping processing in the first-level parameter generation unit, the primary temperature compensation factor is 0.8. If the internal temperature measurement value of the fluid is 32 degrees Celsius at this time, through a specific weighted fusion algorithm (for example, weighted calculation according to a certain ratio), the final temperature compensation coefficient is 0.9 (here is just a hypothetical calculation result), which will be used to compensate for the temperature factor in flow measurement.

[0024] Next, the second-level parameter generation unit is called to discretize and classify the pressure stability level in the preprocessed operation data sequence, determine the pressure condition category to which the current pipeline operation environment belongs, and match the corresponding pressure compensation weight from the preset pressure-flow relationship table based on the pressure condition category. For example, if the pressure stability level is discretized and classified to determine that the current pipeline operation environment belongs to a condition category with large pressure fluctuations, the corresponding pressure compensation weight is found to be 1.2 from the preset pressure-flow relationship table. This weight is obtained based on a large number of previous experiments and data statistics, and is used to compensate for flow measurement under this pressure condition to improve the accuracy of the measurement.

[0025] Then, the third-level parameter generation unit is called to perform sliding window mean filtering on the velocity correlation value in the preprocessed operation data sequence to eliminate the instantaneous velocity fluctuation noise, and the velocity smoothing coefficient is calculated based on the filtered velocity correlation value. Assuming that there are some instantaneous fluctuations in the rotor speed measurement value in the velocity correlation value, a relatively smooth speed value is obtained after sliding window mean filtering. According to this filtered velocity correlation value, the velocity smoothing coefficient is calculated to be 0.95, which can suppress short-term fluctuations in the velocity data and make the flow measurement more stable and accurate.

[0026] Finally, the final temperature compensation coefficient, the pressure compensation weight and the flow rate smoothing coefficient are normalized to generate the flow correction coefficient in the calibration parameter set, and the product of the pressure compensation weight and the flow rate smoothing coefficient is determined as the environmental compensation factor. After normalization, it is assumed that the flow correction coefficient is 1.1, the pressure compensation weight is 1.2 and the product of the flow rate smoothing coefficient is 0.95 to obtain an environmental compensation factor of 1.14. At the same time, according to the requirements of the system and the statistical analysis of the data, the error adjustment threshold is determined to be 0.05. This error adjustment threshold will be used to determine whether the flow measurement results after calibration meet the requirements.

[0027] Step S140: adjusting the measurement output data of the target flow meter in real time based on the calibration parameter set, generating a calibrated flow measurement result, and comparing and verifying the calibrated flow measurement result with a preset standard flow reference value.

[0028] In the scenario of liquid flow measurement in a chemical enterprise, first obtain the original flow measurement value output by the target flow meter in an uncalibrated state, and extract the acquisition timestamp corresponding to the original flow measurement value. Assume that the original flow measurement value output by the target flow meter at a certain moment in an uncalibrated state is 100 cubic meters per hour, and the corresponding acquisition timestamp is 10:0:00 on October 1, 2023.

[0029] The corresponding temperature gradient value, pressure stability level and flow rate associated value are matched from the preprocessed operation data sequence according to the acquisition timestamp. According to the timestamp mentioned above, the corresponding temperature gradient value is -1 degrees Celsius, the pressure stability level is relatively stable, and the flow rate associated value is [1100 revolutions per minute, 0.3 mm] in the preprocessed operation data sequence.

[0030] The temperature gradient value is input into the compensation function corresponding to the final temperature compensation coefficient to obtain the temperature correction amount, and the pressure stability level is input into the adjustment function corresponding to the pressure compensation weight to obtain the pressure correction amount. Assuming that the compensation function corresponding to the final temperature compensation coefficient is a linear function, the temperature correction amount calculated based on the temperature gradient value of -1 degree Celsius is 5 cubic meters per hour. The adjustment function corresponding to the pressure compensation weight is calculated based on the pressure stability level being relatively stable to obtain a pressure correction amount of 3 cubic meters per hour.

[0031] Substitute the original flow measurement value, the temperature correction value, and the pressure correction value into the preset flow superposition formula to obtain a preliminary calibration flow value, and multiply the preliminary calibration flow value by the flow velocity smoothing coefficient to generate the calibrated flow measurement result. According to the flow superposition formula (e.g., original flow measurement value + temperature correction value + pressure correction value), the preliminary calibration flow value is 100+5+3=108 cubic meters per hour, and then multiply the preliminary calibration flow value by the flow velocity smoothing coefficient of 0.95 to obtain a calibrated flow measurement result of 102.6 cubic meters per hour.

[0032] The calibrated flow measurement result is then compared and verified with the preset standard flow reference value. A historical standard flow data set matching the current pipeline operating environment is obtained from the remote calibration database, and the historical standard flow data set contains the benchmark flow value calibrated in the laboratory under the same environmental conditions. Assume that the benchmark flow value obtained from the database is 103 cubic meters per hour. The absolute deviation value between the calibrated flow measurement result and the benchmark flow value is calculated as |102.6-103|=0.4 cubic meters per hour, and the moving average of all absolute deviation values ​​within a preset time window (e.g., 1 hour) is calculated.

[0033] Step S150, when the deviation between the calibrated flow measurement result and the standard flow reference value is greater than the error adjustment threshold, regenerate an updated calibration parameter set and iterate the real-time adjustment until the deviation is within the error adjustment threshold.

[0034] In the above-mentioned scenario of liquid flow measurement in chemical enterprises, if the previously calculated deviation of 0.4 cubic meters per hour is greater than the error adjustment threshold of 0.05 cubic meters per hour, then the operation of regenerating the updated calibration parameter set will be triggered. This may be because some factors were not fully considered or the environment has changed in the previous calibration process. When the updated calibration parameter set is regenerated, the pre-processed operation data sequence will be analyzed and processed again in the manner of step S130, and the calculation method or weight of each parameter may be adjusted. For example, it may be found that the previous nonlinear mapping processing of the temperature gradient value is not accurate enough, so the mapping function in the first-level parameter generation unit is adjusted, and the temperature compensation factor and other parameters are recalculated. Then, according to step S140, the measurement output data of the target flow meter is adjusted in real time again to obtain a new calibrated flow measurement result. Continue to compare and verify with the preset standard flow reference value. If the deviation is still greater than the error adjustment threshold, the process will continue to iterate until the deviation is within the error adjustment threshold range. For example, after multiple iterations, the calibrated flow measurement result is 102.9 cubic meters per hour, which deviates from the baseline flow value of 103 cubic meters per hour by 0.1 cubic meters per hour, which is less than the error adjustment threshold of 0.05 cubic meters per hour. At this time, it is considered that the flow measurement has achieved the required accuracy.

[0035] Based on the above steps, the embodiment of the present application collects a real-time operation data set including dynamic monitoring data and environmental status data, and then pre-processes the real-time operation data set to obtain an operation data sequence, which can clearly describe the change trend of the operation status of the target flow meter at multiple continuous time nodes, thereby integrating the time series characteristics into the calibration process, and then, using the pre-trained calibration parameter generation model to generate a calibration parameter set, wherein the comprehensive use of the flow correction coefficient, environmental compensation factor and error adjustment threshold realizes the multi-dimensional accurate correction of the flow meter measurement error. The flow correction coefficient is adjusted according to the deviation of the flow measurement itself, the environmental compensation factor effectively compensates for the interference of different environmental conditions on the measurement results, and the error adjustment threshold provides a quantitative control standard for the calibration accuracy. This multi-parameter collaborative calibration method is a major breakthrough in the traditional single parameter calibration, which significantly improves the flexibility and adaptability of the calibration, and can better cope with various complex and changeable actual working conditions.

[0036] Then, based on the calibration parameter set, the measured output data is adjusted in real time and compared with the standard flow reference value for verification, realizing dynamic feedback and real-time optimization of the calibration process, ensuring that the flow meter always maintains a high measurement accuracy during operation, avoiding the accumulation of measurement deviations caused by long-term operation or environmental changes, and greatly improving the timeliness and accuracy of flow measurement.

[0037] Finally, when the deviation between the calibrated flow measurement result and the standard flow reference value is greater than the error adjustment threshold, iterative calibration is performed until the deviation is within the threshold range, further ensuring the accuracy of the calibration result, allowing the flow meter to automatically adapt to changing operating conditions and continuously provide high-precision flow measurement results. Through this adaptive calibration method, the frequency and workload of manual calibration are effectively reduced, and the stability and automation level of the entire flow measurement system are improved.

[0038] In a possible implementation manner, the real-time operation data set includes a plurality of operation sub-data of the flow meter within a preset time period, the operation sub-data including temperature monitoring sub-data, pressure monitoring sub-data and flow rate monitoring sub-data, and step S120 includes: Step S121, extracting the outer wall temperature measurement value and the fluid internal temperature measurement value of the pipeline where the target flow meter is located for the temperature monitoring sub-data, and performing difference calculation on the outer wall temperature measurement value and the fluid internal temperature measurement value to obtain a temperature gradient change sequence.

[0039] Step S122: identifying the pressure fluctuation peak value in the fluid flow direction in the pipeline operation environment with respect to the pressure monitoring sub-data, and generating a pressure stability evaluation index based on the occurrence frequency of the pressure fluctuation peak value.

[0040] Step S123, for the flow velocity monitoring sub-data, obtain the rotor speed measurement value and the blade vibration amplitude measurement value of the target flow meter, and perform time alignment on the rotor speed measurement value and the blade vibration amplitude measurement value to generate a flow velocity associated feature vector.

[0041] Step S124, concatenating the temperature gradient change sequence, the pressure stability evaluation index and the flow rate associated characteristic vector according to time nodes to generate the preprocessed operation data sequence, wherein the data unit corresponding to each time node in the preprocessed operation data sequence contains the temperature gradient value, the pressure stability level and the flow rate associated value.

[0042] In this embodiment, in the pipeline system, the target flow meter is used to measure the flow of the chemical solution, and the real-time operation data set contains multiple operation sub-data, among which the processing of the temperature monitoring sub-data is particularly important. The pipeline where the target flow meter is located has a temperature sensor installed on its outer wall for measuring the outer wall temperature, and there is a sensor inside the pipeline specifically for measuring the internal temperature of the fluid. In a specific time period, such as the preset time period of one hour from 9:00 to 10:00 on October 1, 2023, the temperature data is continuously collected. At 9:00:00, the temperature of the outer wall of the pipeline is measured to be 23 degrees Celsius, while the temperature inside the fluid is 28 degrees Celsius, and the difference between the two is calculated to be -5 degrees Celsius. As time goes by, at 9:10:00, the outer wall temperature becomes 24 degrees Celsius, the internal temperature of the fluid is 29 degrees Celsius, and the difference is -5 degrees Celsius; at 9:20:00, the outer wall temperature is 25 degrees Celsius, the internal temperature is 30 degrees Celsius, the difference is -5 degrees Celsius, and so on. In this way, the difference calculated at different time points during the entire preset time period constitutes a temperature gradient change sequence. This temperature gradient change sequence can reflect the dynamic situation of heat exchange between the liquid and the pipe wall during this period of time. For example, if the temperature gradient remains stable, it means that the heat exchange is in a relatively stable state. If the temperature gradient fluctuates greatly, it may mean that the surrounding environment of the pipe or the flow state of the liquid has changed, which is of great significance for the subsequent analysis of the operating status of the flow meter and the calibration of flow measurement.

[0043] In terms of pressure monitoring sub-data, during the flow of chemical solutions in the pipeline, the pressure in the direction of liquid flow will fluctuate due to factors such as the layout structure of the pipeline, the valve status, and the physical properties of the liquid itself. Multiple pressure sensors are set along the pipeline to monitor pressure changes. During the above preset time period, the sensor continuously collects pressure data to identify the pressure fluctuation peak. For example, at 9:05:00, the pressure suddenly rises from the normal 1.5 MPa to 2.0 MPa, which is a pressure fluctuation peak. As time goes by, multiple such pressure fluctuation peaks continue to be monitored. The frequency of occurrence of these pressure fluctuation peaks is counted. Assume that a total of 8 pressure fluctuation peaks occurred in this hour. Based on this frequency of occurrence, a pressure stability evaluation index is generated through a specific algorithm. If the frequency of pressure fluctuation peaks is high, such as exceeding a certain threshold (this threshold is determined based on a large number of experiments and historical data), it means that the liquid flow state is not stable, and the pressure stability evaluation index will reflect this unstable state; if the frequency of pressure fluctuation peaks is low and within a reasonable range, it means that the pressure is relatively stable, and the pressure stability evaluation index will also reflect this stability accordingly. This pressure stability evaluation index plays a key role in analyzing the flow characteristics of liquids in pipelines and evaluating the factors affecting the measurement accuracy of flow meters.

[0044] For the flow rate monitoring sub-data, the rotor speed inside the target flow meter is closely related to the flow rate of the liquid, and the blade vibration amplitude can also reflect the characteristics of the liquid flow. During the preset time period, the rotor speed measurement value and the blade vibration amplitude measurement value of the target flow meter are continuously obtained. For example, at 9:00:00, the rotor speed measurement value is 900 rpm and the blade vibration amplitude is 0.3 mm. The two data are aligned in time series to form part of the flow rate correlation feature vector at a moment. At 9:10:00, the rotor speed measurement value is 950 rpm and the blade vibration amplitude is 0.4 mm, and the same time series alignment is performed. As time goes by, these data at different time points in the entire preset time period are combined to generate a flow rate correlation feature vector. This flow rate correlation feature vector completely records the flow rate-related information at different time nodes, including the correlation between the rotor speed and the blade vibration amplitude. It can reflect the actual situation of the liquid flow rate from multiple angles and provide rich flow rate-related information for subsequent flow calibration.

[0045] Finally, the temperature gradient change sequence, pressure stability evaluation index and flow rate associated characteristic vector obtained above are spliced ​​according to the time node to generate the preprocessed operation data sequence. At each time node, a data unit containing the temperature gradient value, pressure stability level and flow rate associated value is formed. For example, at the time node of 9:00:00, the temperature gradient value is -5 degrees Celsius, and the pressure stability evaluation index is calculated and classified to determine that the pressure stability level is medium (the medium here is determined according to the previously set pressure stability evaluation index classification standard), and the flow rate associated value is [900 rpm, 0.3 mm], thus forming a complete data unit. As time goes by, these data units at different time nodes constitute the preprocessed operation data sequence. This preprocessed operation data sequence comprehensively describes the operating state change trend of the target flowmeter at multiple continuous time nodes. It covers information on temperature, pressure and flow rate, and provides a comprehensive and accurate data basis for subsequent input into the calibration parameter generation model, thereby helping to more accurately calibrate the measurement results of the target flowmeter and improve the measurement accuracy in the liquid flow measurement scenario of chemical enterprises.

[0046] In a possible implementation manner, the calibration parameter generation model includes a multi-level parameter generation unit, and step S130 includes: Step S131, calling the first-level parameter generation unit, performing nonlinear mapping processing on the temperature gradient value in the preprocessed operation data sequence, generating a primary temperature compensation factor, and weightedly fusing the primary temperature compensation factor with the fluid internal temperature measurement value to obtain a final temperature compensation coefficient.

[0047] Step S132, calling the second-level parameter generation unit, discretizing and classifying the pressure stability level in the preprocessed operation data sequence, determining the pressure condition category to which the current pipeline operation environment belongs, and matching the corresponding pressure compensation weight from a preset pressure-flow relationship table based on the pressure condition category.

[0048] Step S133, calling the third-level parameter generation unit, performing sliding window mean filtering on the velocity correlation values ​​in the preprocessed operation data sequence to eliminate instantaneous velocity fluctuation noise, and calculating the velocity smoothing coefficient based on the filtered velocity correlation values.

[0049] Step S134, normalizing the final temperature compensation coefficient, the pressure compensation weight and the flow rate smoothing coefficient to generate a flow correction coefficient in the calibration parameter set, and determining the product of the pressure compensation weight and the flow rate smoothing coefficient as the environmental compensation factor.

[0050] In this embodiment, when the pre-processed operation data sequence is input into the pre-trained calibration parameter generation model, the multi-level parameter generation unit in the calibration parameter generation model starts to perform the corresponding task. First, the first-level parameter generation unit is called to perform nonlinear mapping processing on the temperature gradient value in the pre-processed operation data sequence. For example, in the process of chemical solution flowing through the pipeline, the previously obtained temperature gradient value sequence contains values ​​at different time nodes, such as the temperature gradient value of -5 degrees Celsius at 9:00:00 on October 1, 2023. The first-level parameter generation unit processes the temperature gradient value of -5 degrees Celsius according to its internal nonlinear mapping function (this function is based on a large amount of experimental data and theoretical analysis) to obtain a primary temperature compensation factor. Assume that this primary temperature compensation factor is 0.8. Then, this primary temperature compensation factor is weighted and fused with the internal temperature measurement value of the fluid. At 9:00:00, the internal temperature measurement value of the fluid is 28 degrees Celsius. According to a specific weighted fusion algorithm (this algorithm is determined based on the pipeline system and liquid characteristics), the final temperature compensation coefficient is calculated. Assume that the weighted calculation process is: final temperature compensation coefficient = 0.8 × 0.1 + 28 × 0.9 = 25.28 (here 0.1 and 0.9 are weighted coefficients determined according to system characteristics). This final temperature compensation coefficient reflects the comprehensive influence of temperature factors on flow measurement and will play an important role in the subsequent flow calibration process.

[0051] Then the second-level parameter generation unit is called to discretize and classify the pressure stability level in the preprocessed operation data sequence. In the previous pressure monitoring process, the pressure stability evaluation index was obtained based on the frequency of occurrence of the pressure fluctuation peak, and the pressure stability level was determined. For example, during the entire measurement period, if the frequency of pressure fluctuation peaks is high, the pressure stability level is determined as an unstable category after analysis and comparison with the set classification standards. Then, based on this pressure stability level, the pressure condition category to which the current pipeline operating environment belongs is determined, and then the corresponding pressure compensation weight is matched from the preset pressure-flow relationship table. Assuming that the currently determined pressure condition category is an unstable category, the corresponding pressure compensation weight of 1.2 is found in the pressure-flow relationship table. This pressure compensation weight is a compensation coefficient set for accurate flow measurement under such unstable pressure conditions based on a large amount of experimental and historical data. It reflects the need for correction of flow measurement under such pressure conditions.

[0052] Then, the third-level parameter generation unit is called to perform sliding window mean filtering on the velocity association values ​​in the preprocessed running data sequence. The velocity association values ​​obtained previously include the rotor speed measurement values ​​and blade vibration amplitude measurement values ​​of the target flow meter, such as the rotor speed and blade vibration amplitude data at different time nodes. Due to some instantaneous interference factors that may exist in the liquid flow process, the rotor speed and blade vibration amplitude will have some small fluctuations, which may affect the accuracy of flow measurement. For example, at 9:00:00, the rotor speed measurement value is 900 rpm, the blade vibration amplitude is 0.3 mm, at 9:01:00, the rotor speed is 910 rpm, the blade vibration amplitude is 0.32 mm, and so on. These instantaneous velocity fluctuation noises are eliminated by sliding window mean filtering (the size of the sliding window is determined according to the dynamic characteristics of the system and the requirements for flow velocity stability, such as a window size of 5 minutes). Assuming that a relatively smooth velocity association value is obtained after filtering, the velocity smoothing coefficient is calculated based on the filtered velocity association value. Assume that according to a specific calculation method (this method is determined based on the physical properties of the liquid in the pipeline and the working principle of the flow meter), the flow velocity smoothing coefficient is calculated to be 0.95. This flow velocity smoothing coefficient can effectively suppress short-term fluctuations in the flow velocity data and make the flow measurement more stable and accurate.

[0053] The final temperature compensation coefficient, pressure compensation weight, and flow rate smoothing coefficient obtained above are normalized to generate the flow correction coefficient in the calibration parameter set. Assume that the normalization formula is: flow correction coefficient = (final temperature compensation coefficient + pressure compensation weight + flow rate smoothing coefficient) / (final temperature compensation coefficient × pressure compensation weight × flow rate smoothing coefficient), substitute the previously obtained value into the calculation to obtain the flow correction coefficient. At the same time, the product of the pressure compensation weight and the flow rate smoothing coefficient is determined as the environmental compensation factor, such as 1.2 × 0.95 = 1.14. This environmental compensation factor takes into account the combined effect of pressure and flow rate factors on the environment, and will be used in the subsequent flow calibration process to correct the flow measurement deviation caused by environmental factors.

[0054] In a possible implementation, step S140 includes: Step S141, obtaining the original flow measurement value output by the target flow meter in an uncalibrated state, and extracting the acquisition timestamp corresponding to the original flow measurement value.

[0055] Step S142, matching the corresponding temperature gradient value, pressure stability level and flow rate correlation value from the preprocessed operation data sequence according to the acquisition timestamp.

[0056] Step S143, inputting the temperature gradient value into the compensation function corresponding to the final temperature compensation coefficient to obtain a temperature correction amount, and inputting the pressure stability level into the adjustment function corresponding to the pressure compensation weight to obtain a pressure correction amount.

[0057] Step S144, substituting the original flow measurement value, the temperature correction value and the pressure correction value into a preset flow superposition formula to obtain a preliminary calibrated flow value, and multiplying the preliminary calibrated flow value by the flow velocity smoothing coefficient to generate the calibrated flow measurement result.

[0058] In this embodiment, when the measurement output data of the target flow meter is adjusted in real time based on the calibration parameter set to generate the calibrated flow measurement result, the original flow measurement value output by the target flow meter in an uncalibrated state is first obtained, and the acquisition timestamp corresponding to the original flow measurement value is extracted. For example, at 9:0:00 am on October 1, 2023, the original flow measurement value output by the target flow meter in an uncalibrated state is 100 cubic meters per hour, and the acquisition timestamp is 9:0:00.

[0059] According to this acquisition timestamp, the corresponding temperature gradient value, pressure stability level and flow rate correlation value are matched from the preprocessed operation data sequence. At the time node of 9:00:00, the previously calculated temperature gradient value is -5 degrees Celsius, the pressure stability level is unstable, and the flow rate correlation value is [900 rpm, 0.3 mm].

[0060] Input the temperature gradient value into the compensation function corresponding to the final temperature compensation coefficient to obtain the temperature correction. Assuming that the compensation function corresponding to the final temperature compensation coefficient is a function built based on a physical model, substitute -5 degrees Celsius into this function and calculate the temperature correction to be 5 cubic meters per hour. At the same time, input the pressure stability level into the adjustment function corresponding to the pressure compensation weight to obtain the pressure correction. Assuming that the adjustment function corresponding to the pressure compensation weight is calculated based on the pressure stability level as an unstable category, the pressure correction is 3 cubic meters per hour.

[0061] Substitute the original flow measurement value, temperature correction value, and pressure correction value into the preset flow superposition formula to obtain the preliminary calibration flow value. Assume that the flow superposition formula is: preliminary calibration flow value = original flow measurement value + temperature correction value + pressure correction value, that is, preliminary calibration flow value = 100 + 5 + 3 = 108 cubic meters per hour. Then multiply the preliminary calibration flow value by the flow velocity smoothing coefficient to generate the calibrated flow measurement result. That is, the calibrated flow measurement result = 108 × 0.95 = 102.6 cubic meters per hour. This calibrated flow measurement result comprehensively considers the impact of factors such as temperature, pressure and flow velocity on the original flow measurement value, and corrects the original flow measurement value through the calibration parameter set, thereby obtaining a more accurate flow measurement result, which meets the requirements for flow measurement accuracy in the liquid flow measurement scenario of chemical enterprises.

[0062] In a possible implementation, step S140 may further include: Step S145, obtaining a historical standard flow data set matching the current pipeline operating environment from the remote calibration database, wherein the historical standard flow data set includes reference flow values ​​calibrated by a laboratory under the same environmental conditions.

[0063] In this embodiment, this remote calibration database stores a large amount of historical flow data under different pipeline operating environments in chemical companies. In the current chemical solution pipeline flow measurement scenario, the historical standard flow data set in the database contains the benchmark flow values ​​calibrated in the laboratory under the same environmental conditions. These benchmark flow values ​​are accurate flow values ​​measured for specific pipelines, liquid types and environmental conditions using high-precision measuring equipment under strictly controlled laboratory conditions. For example, for the current pipeline, the composition, temperature, pressure range of the internal chemical solution, and the material, diameter and other environmental factors of the pipeline all match certain historical data stored in the database, so that the corresponding benchmark flow value can be obtained from it.

[0064] Step S146, calculating the absolute deviation between the calibrated flow measurement result and the reference flow value, and calculating the moving average of all absolute deviation values ​​within a preset time window.

[0065] For example, if the calibrated flow measurement result is 102.6 cubic meters per hour, and the baseline flow value obtained from the database is 103 cubic meters per hour, then the absolute deviation value is |102.6-103|=0.4 cubic meters per hour. At the same time, it is necessary to calculate the moving average of all absolute deviation values ​​within the preset time window. Assuming that the preset time window is 1 hour, within this 1 hour, multiple calibrated flow measurement results are obtained at certain time intervals (such as every 10 minutes), and their absolute deviation values ​​from the corresponding baseline flow values ​​are calculated respectively, and then the moving average of these absolute deviation values ​​is calculated according to the moving average algorithm. This moving average can more comprehensively reflect the deviation between the calibrated flow measurement results and the baseline flow value over a period of time, avoiding the accidental influence of the deviation at a single moment.

[0066] Step S147: When the moving average value is greater than the error adjustment threshold, a calibration parameter update instruction is triggered, where the calibration parameter update instruction is used to instruct to regenerate the updated calibration parameter set.

[0067] Step S148, dynamically weighting the flow correction coefficient and the environmental compensation factor in the updated calibration parameter set to generate a new error adjustment threshold, and feeding the new error adjustment threshold back to the calibration parameter generation model for parameter self-optimization.

[0068] For example, if the error adjustment threshold is set to 0.05 cubic meters per hour, and the calculated moving average is 0.1 cubic meters per hour, which is greater than the error adjustment threshold, the calibration parameter update instruction will be triggered. This instruction is used to instruct the regeneration of the updated calibration parameter set to further adjust the flow measurement results. The flow correction coefficient and the environmental compensation factor in the updated calibration parameter set are dynamically weighted to generate a new error adjustment threshold. Assuming that the updated flow correction coefficient is 1.15 and the environmental compensation factor is 1.14, the new error adjustment threshold is calculated to be 0.06 cubic meters per hour according to a specific dynamic weighting algorithm (this algorithm is determined based on the system's historical data and optimization strategy). This new error adjustment threshold is then fed back to the calibration parameter generation model for parameter self-optimization, so that the calibration parameter generation model can adjust the internal parameter generation mechanism according to the new error adjustment threshold to improve the accuracy of flow measurement.

[0069] In a possible implementation manner, the pre-trained calibration parameter generation model is trained by the following steps: Step S210, obtaining a historical pipeline operation data set, wherein the historical pipeline operation data set includes uncalibrated operation data collected by multiple flow meters under different working conditions and corresponding laboratory calibration data.

[0070] Step S220, performing noise filtering and outlier removal on the uncalibrated operating data to generate a training operating data sequence, and converting the laboratory calibration data into a standard flow reference sequence.

[0071] For example, the historical pipeline operation data set covers the uncalibrated operation data collected by multiple flowmeters in chemical enterprises under different working conditions and their corresponding laboratory calibration data. Different working conditions include different chemical solution compositions, different pipeline pressure ranges, different temperature environments, and different flow rate ranges. For example, some flowmeters measure the flow rate of a certain high-concentration chemical solution under high temperature and high pressure, while others measure the flow rate of a low-concentration solution under low temperature and low pressure. For the uncalibrated operation data under these different working conditions, noise filtering and outlier removal are required to generate the training operation data sequence. In the uncalibrated operation data, there may be noise data and outliers caused by sensor failure, electromagnetic interference or other external factors. For example, due to the electromagnetic interference generated when a large motor nearby starts, the flowmeter collects a flow rate value that is obviously deviated from the normal range at a certain moment. This value is an outlier. Outliers are found by identifying mutation data points at continuous time nodes in the uncalibrated operation data. The characteristic of the mutation data point is that the difference between it and the previous data point is greater than the preset mutation threshold. Assuming that the preset mutation threshold is 100 rpm (for rotor speed measurement), if the difference between the rotor speed measurement at a certain moment and the previous moment exceeds 100 rpm, this data point is marked as a suspected outlier. Then, the context correlation analysis is performed on this mutation data point, the variance value of the preset number of data points before and after the mutation data point (such as 5 data points before and after each) is calculated, and the degree of deviation of the variance value from the historical variance mean is compared. If the degree of deviation is greater than the set threshold (this threshold is obtained based on historical data statistics), the mutation data point is determined to be an outlier. For outliers, linear interpolation of the previous and next data points is used for replacement. For example, for abnormal rotor speed values, a reasonable replacement value is obtained by linear interpolation calculation based on the normal rotor speed values ​​before and after. The replaced uncalibrated operating data is subjected to wavelet transform denoising. The data is decomposed into different frequency bands through wavelet transform, and the noise components of different frequency bands are extracted and filtered out from the original signal, thereby generating a training operating data sequence. At the same time, the laboratory calibration data is converted into a standard flow reference sequence, which is the target value for model training.

[0072] Step S230, constructing an initial parameter generation model, wherein the initial parameter generation model comprises a temperature compensation branch, a pressure compensation branch and a flow rate smoothing branch connected in series.

[0073] Step S240, input the training operation data sequence into the initial parameter generation model, generate a predicted temperature compensation coefficient through the temperature compensation branch, generate a predicted pressure compensation weight through the pressure compensation branch, and generate a predicted flow rate smoothing coefficient through the flow rate smoothing branch.

[0074] Step S250, calculating the mean square error between the predicted temperature compensation coefficient and the true value of the temperature compensation in the standard flow reference sequence to obtain a temperature loss value, and calculating the cross entropy loss value between the predicted pressure compensation weight and the true value of the pressure compensation to obtain a pressure loss value.

[0075] Step S260, weighted summing of the temperature loss value, the pressure loss value, and the cosine similarity of the predicted flow velocity smoothing coefficient and the true flow velocity smoothing value is performed to obtain a total training loss value, and back-propagation optimization is performed on the initial parameter generation model based on the total training loss value until convergence.

[0076] In this embodiment, in the temperature compensation branch, for example, the temperature gradient value in the training operation data sequence is processed by a multi-layer perceptron network. The temperature gradient value is input into the first hidden layer of the multi-layer perceptron network for nonlinear feature transformation to obtain the first hidden layer feature vector. This first hidden layer contains multiple neurons, and each neuron performs a nonlinear transformation on the input temperature gradient value according to a specific activation function (such as a ReLU function). Then the first hidden layer feature vector is input into the second hidden layer of the multi-layer perceptron network for feature dimension reduction processing to obtain the second hidden layer feature vector. The number of neurons in this second hidden layer is less than that in the first hidden layer, and the first hidden layer feature vector is processed by a specific weight matrix and activation function to obtain a more compact feature representation. Finally, the second hidden layer feature vector is spliced ​​with the external environment temperature measurement value to generate a temperature fusion feature, and the temperature fusion feature is input into the output layer of the multi-layer perceptron network to generate a predicted temperature compensation coefficient.

[0077] In the pressure compensation branch, the pressure stability level in the training running data sequence is converted into a one-hot encoding vector. For example, if the pressure stability level is divided into three categories: stable, medium, and unstable, when the pressure stability level is medium, the corresponding one-hot encoding vector is [0, 1, 0]. Then this one-hot encoding vector is input into the one-dimensional convolution layer of the convolutional neural network for local feature extraction. The convolution kernel in the convolution layer slides on the one-hot encoding vector according to the set step size, performs convolution operation, and extracts key local features. The convolution output features are processed by maximum pooling, for example, taking the maximum value in a small local area, so as to extract the key pressure pattern features, and input this key pressure pattern feature into the fully connected layer for probability distribution mapping. The fully connected layer maps the input key pressure pattern features into a probability distribution vector through multiple neurons and weight matrices. Finally, the output of the fully connected layer is processed by the softmax activation function to generate the category probability distribution corresponding to the predicted pressure compensation weight, and the category corresponding to the highest probability in the category probability distribution is used as the predicted pressure compensation weight.

[0078] The velocity smoothing branch includes a temporal attention mechanism module. The velocity association value in the training running data sequence is input into the query vector generator of the temporal attention mechanism module to generate a query vector for the current time node. This query vector reflects the importance weight information of the current velocity association value in the entire time series. Then the attention weight between the query vector and the key vector of the historical time node is calculated. This attention weight indicates the degree of correlation between the current velocity association value and the historical velocity association value. Based on this attention weight, the value vector of the historical time node is weighted and summed to obtain a context-aware velocity feature representation. This context-aware velocity feature representation integrates the information of the current and historical velocity association values. Finally, the context-aware velocity feature representation is input into the sigmoid activation function to generate a predicted velocity smoothing coefficient between 0 and 1. This predicted velocity smoothing coefficient is used to suppress short-term fluctuations in velocity data.

[0079] Calculate the mean square error between the predicted temperature compensation coefficient and the true value of temperature compensation in the standard flow reference sequence to obtain the temperature loss value. For example, if the predicted temperature compensation coefficient is 0.9 and the true value of temperature compensation is 0.95, the temperature loss value is calculated according to the calculation formula of the mean square error. At the same time, calculate the cross entropy loss value of the predicted pressure compensation weight and the true value of pressure compensation to obtain the pressure loss value. Perform weighted summation on the cosine similarity of the predicted flow rate smoothing coefficient and the true value of the flow rate smoothing to obtain the total training loss value. This total training loss value combines the prediction errors of temperature, pressure and flow rate. Based on the total training loss value, the initial parameter generation model is back-propagated and optimized. By adjusting the weight parameters in the model, the total training loss value is gradually reduced until convergence. Convergence means that the error between the model's prediction results and the standard flow reference sequence has reached an acceptable minimum value. At this time, the model training is completed and the calibration parameter set can be accurately generated for flow calibration in the liquid flow measurement scenario of chemical enterprises.

[0080] In a possible implementation, step S220 includes: Step S221, identifying mutation data points at consecutive time nodes in the uncalibrated operating data, wherein the mutation data point is characterized in that the difference between the mutation data point and the previous data point is greater than a preset mutation threshold.

[0081] In the process of measuring the flow rate of chemical solutions, the uncalibrated operation data contains multiple measurement values, such as flow rate, pressure, temperature and other time-varying data. Taking temperature measurement data as an example, assuming that when measuring the flow rate of a chemical solution in a pipeline, temperature data is continuously collected over a period of time, and the temperature value is collected every 10 seconds from 9:00 to 10:00 on October 1, 2023. Under normal circumstances, the temperature change should be relatively smooth, but due to factors such as possible short-term sensor failure or external interference, mutation data points will appear. Assuming that the preset mutation threshold is 2 degrees Celsius (this threshold is determined based on a large amount of historical data and the normal range of chemical solution temperature changes), if the temperature value measured at 9:10:00 is 30 degrees Celsius, and the temperature value measured at 9:10:10 is 33 degrees Celsius, the difference is 3 degrees Celsius, which is greater than the preset mutation threshold, then the temperature data point at 9:10:10 is identified as a mutation data point.

[0082] Step S222, performing context correlation analysis on the mutation data point, calculating the variance value of a preset number of data points before and after the mutation data point, and comparing the degree of deviation of the variance value from the historical variance mean.

[0083] Assume that the preset number is 5 data points before and after, that is, calculate the variance value of 5 data points before and after the mutation data point of 9:10:10 (that is, 9 data points from 9:10:00 to 9:10:50 excluding the mutation point). The variance value of these 9 data points is obtained by a specific variance calculation method. At the same time, the historical variance mean under similar normal operation conditions is calculated based on historical data. Assume that the historical variance mean is 0.5, and the variance value currently calculated is 1.5. Set a threshold for the degree of deviation, such as 0.8 (this threshold is determined based on the requirements for data stability and historical data statistics). Since 1.5-0.5=1, 1 is greater than 0.8, so this degree of deviation is greater than the set threshold, and this mutation data point is marked as an outlier. For this outlier, linear interpolation of the data points before and after is used. That is, linear interpolation calculation is performed based on the temperature values ​​of 9:10:00 and 9:10:20 (the first normal data point after the mutation point). Assuming that the temperature value at 9:10:00 is 30 degrees Celsius, and the temperature value at 9:10:20 is 31 degrees Celsius, the reasonable temperature value at the outlier position at 9:10:10 is 30.5 degrees Celsius through linear interpolation calculation, and this value is used to replace the original outlier.

[0084] Step S223: when the deviation degree is greater than a set threshold, the mutation data point is marked as an outlier, and the outlier is replaced by linear interpolation of the previous and next data points.

[0085] Step S224, performing wavelet transform denoising processing on the replaced uncalibrated operating data, extracting noise components of different frequency bands and filtering them out from the original signal, and generating the training operating data sequence.

[0086] In chemical flow measurement, the noise in uncalibrated operating data may come from many aspects, such as electronic noise of the sensor, slight interference from the surrounding environment of the pipeline, etc. Wavelet transform is a mathematical method that can decompose signals into different frequency bands. For the replaced measurement data such as temperature, pressure, flow rate, etc., they are decomposed into different frequency bands through wavelet transform. For example, for temperature data, it may be decomposed into a low-frequency part (reflecting the slow change trend of temperature) and a high-frequency part (which may contain noise and some rapid temperature fluctuations). Then the noise components of different frequency bands are extracted and filtered out from the original signal. Assuming that obvious high-frequency noise is found in a certain frequency band, the noise components in this frequency band are removed by setting a suitable threshold or filtering algorithm, so as to obtain purer temperature data. The same treatment is performed for pressure and flow rate data. After such processing, all uncalibrated operating data are purified and a training operating data sequence is generated. This sequence can more accurately reflect the actual operating status in the process of chemical solution flow measurement and provide a high-quality data basis for subsequent model training.

[0087] In a possible implementation, the temperature compensation branch includes a multi-layer perceptron network, and step S240 includes: Step S241: input the temperature gradient value in the training operation data sequence into the first hidden layer of the multi-layer perceptron network for nonlinear feature transformation to obtain a first hidden layer feature vector.

[0088] Step S242: input the first hidden layer feature vector to the second hidden layer of the multilayer perceptron network for feature dimensionality reduction processing to obtain a second hidden layer feature vector.

[0089] Step S243, concatenating the second hidden layer feature vector with the external environment temperature measurement value to generate a temperature fusion feature, and inputting the temperature fusion feature into the output layer of the multi-layer perceptron network to generate the predicted temperature compensation coefficient.

[0090] In the temperature compensation branch, it includes a multi-layer perceptron network, through which the predicted temperature compensation coefficient is generated. The temperature gradient value in the training operation data sequence is input into the first hidden layer of the multi-layer perceptron network for nonlinear feature transformation to obtain the first hidden layer feature vector. In the chemical solution flow measurement scenario, the temperature gradient value in the training operation data sequence reflects the change of the temperature difference between the chemical solution in the pipeline and the pipeline wall over time. The first hidden layer of the multi-layer perceptron network contains multiple neurons, each of which has its own weight and bias. When the temperature gradient value is input into the first hidden layer, each neuron is calculated according to a specific activation function. For example, assuming that the activation function is the ReLU function (RectifiedLinearUnit), for the input temperature gradient value, the neuron will calculate ReLU (temperature gradient value * weight + bias). Through the calculation of multiple neurons, the input temperature gradient value is nonlinearly transformed to obtain the first hidden layer feature vector. This first hidden layer feature vector is no longer a simple temperature gradient value, but contains more feature representations of the complex relationship between the temperature gradient and other factors after nonlinear transformation.

[0091] The first hidden layer feature vector is input into the second hidden layer of the multilayer perceptron network for feature dimension reduction to obtain the second hidden layer feature vector. The second hidden layer has fewer neurons than the first hidden layer. Each element in the first hidden layer feature vector is multiplied by the weight of the second hidden layer neuron, and then added with the bias, and the second hidden layer feature vector is calculated by the activation function (such as the ReLU function). In this process, due to the reduction in the number of neurons in the second hidden layer, feature dimension reduction is achieved, the information in the first hidden layer feature vector is compressed and refined, and more representative and key features are extracted. For example, if the first hidden layer feature vector has 10 elements, after calculation in the second hidden layer (assuming the number of neurons is 5), the second hidden layer feature vector obtained has only 5 elements, and these 5 elements can more effectively represent the relationship characteristics between the temperature gradient value and the flow measurement.

[0092] The second hidden layer feature vector is spliced ​​with the external ambient temperature measurement value to generate a temperature fusion feature, and the temperature fusion feature is input into the output layer of the multi-layer perceptron network to generate a predicted temperature compensation coefficient. In the chemical solution flow measurement scenario, the external ambient temperature measurement value is also an important influencing factor. Assume that an ambient temperature sensor is installed around the pipeline, and the measured external ambient temperature is 25 degrees Celsius. This external ambient temperature measurement value is spliced ​​with the second hidden layer feature vector. For example, if the second hidden layer feature vector is [0.1, 0.2, 0.3, 0.4, 0.5], then the spliced ​​temperature fusion feature may be [25, 0.1, 0.2, 0.3, 0.4, 0.5] (here a simple splicing method is assumed, which may actually be different according to the specific network structure and data processing requirements). This temperature fusion feature is input into the output layer of the multi-layer perceptron network. The neurons in the output layer are calculated according to the previously learned weights and biases, as well as specific activation functions (such as linear functions or other suitable functions), and finally generate a predicted temperature compensation coefficient. This predicted temperature compensation coefficient reflects the degree of temperature compensation required to accurately measure the flow rate of the chemical solution under the current temperature gradient and external ambient temperature. It will play an important role in the subsequent calibration parameter generation process and is used to perform temperature-related compensation on the flow measurement results to improve the measurement accuracy.

[0093] In a possible implementation, the pressure compensation branch includes a combined structure of a convolutional neural network and a fully connected layer, and step S240 further includes: Step S244, converting the pressure stability level in the training operation data sequence into a one-hot encoding vector, and inputting the one-hot encoding vector into the one-dimensional convolution layer of the convolutional neural network for local feature extraction.

[0094] Step S245, performing maximum pooling processing on the convolution output features, extracting key pressure pattern features, and inputting the key pressure pattern features into the fully connected layer for probability distribution mapping.

[0095] Step S246, processing the output of the fully connected layer through a softmax activation function to generate a category probability distribution corresponding to the predicted pressure compensation weight, and taking the category corresponding to the highest probability in the category probability distribution as the predicted pressure compensation weight.

[0096] Wherein, the flow rate smoothing branch includes a temporal attention mechanism module, and step S240 further includes: Step S247, inputting the flow rate association value in the training running data sequence into the query vector generator of the temporal attention mechanism module to generate a query vector for the current time node.

[0097] Step S248, calculate the attention weight between the query vector and the key vector of the historical time node, and perform weighted summation on the value vector of the historical time node based on the attention weight to obtain a context-aware flow rate feature representation.

[0098] Step S249, inputting the context-aware flow rate feature representation into a sigmoid activation function to generate the predicted flow rate smoothing coefficient between 0 and 1, wherein the predicted flow rate smoothing coefficient is used to suppress short-term fluctuations in flow rate data.

[0099] In this embodiment, in the pressure compensation branch, it includes a combination structure of a convolutional neural network and a fully connected layer, which is used to generate a predicted pressure compensation weight. First, the pressure stability level in the training operation data sequence is converted into a one-hot encoding vector, and the one-hot encoding vector is input into the one-dimensional convolution layer of the convolutional neural network for local feature extraction. In the pipeline flow measurement process of chemical solutions, the pressure stability level is a quantitative description of the stability of the pressure of the liquid flow in the pipeline. For example, according to the previous analysis of the frequency of occurrence of the pressure fluctuation peak and the pressure change, the pressure stability level is divided into three levels: stable, medium stable, and unstable. When the pressure stability level is medium stable, it is converted into a one-hot encoding vector. If stable, medium stable, and unstable are set to correspond to three positions in the one-hot encoding vector, then the one-hot encoding vector corresponding to medium stability is [0, 1, 0]. This one-hot encoding vector is input into the one-dimensional convolution layer of the convolutional neural network. The one-dimensional convolution layer contains multiple convolution kernels, each of which has a specific size and weight value. The convolution kernel slides on the one-hot encoding vector according to the set step size for convolution operation. For example, when the convolution kernel size is 3 and the step size is 1, when sliding on the one-hot encoded vector [0, 1, 0], the convolution kernel multiplies the elements in the vector and then sums them to obtain the convolution output feature. This convolution output feature can extract the local features in the one-hot encoded vector. These local features reflect the characteristic information of the pressure stability level at different local positions, which is helpful for the subsequent identification of pressure pattern features.

[0100] The convolution output features are processed by maximum pooling to extract the key pressure pattern features, and the key pressure pattern features are input to the fully connected layer for probability distribution mapping. The convolution output features obtained above may contain multiple values. The maximum pooling process is to select the maximum value as the representative value in a small local area. For example, the convolution output features are divided into several small areas, and the maximum value is selected in each area. These maximum values ​​are combined to form the key pressure pattern features. This key pressure pattern feature extracts the most significant information in the convolution output features and can better represent the key pattern in the pressure stability level. This key pressure pattern feature is then input to the fully connected layer. The fully connected layer is composed of multiple neurons, and each neuron has a connection weight with each element of the input key pressure pattern feature. Through these connection weights, the fully connected layer maps the key pressure pattern features to obtain a probability distribution vector. This probability distribution vector represents the probability size corresponding to different pressure compensation weight categories.

[0101] The output of the fully connected layer is processed by the softmax activation function to generate the category probability distribution corresponding to the predicted pressure compensation weight, and the category corresponding to the highest probability in the category probability distribution is used as the predicted pressure compensation weight. The softmax activation function converts the numerical value output by the fully connected layer into a probability value so that the sum of these probability values ​​is 1. For example, after being processed by the softmax activation function, the obtained category probability distribution is [0.2, 0.5, 0.3], which corresponds to different pressure compensation weight categories. Among them, the highest probability is 0.5, and the corresponding category is assumed to be a medium pressure compensation weight category, then this medium pressure compensation weight category is determined as the predicted pressure compensation weight. This predicted pressure compensation weight reflects the weight value required for pressure compensation of the flow measurement result under the current pressure stability level, based on the relationship between pressure and flow learned from historical data and the model. It will play an important role in the subsequent flow calibration process and is used to correct the flow measurement deviation caused by pressure factors.

[0102] In the flow rate smoothing branch, a temporal attention mechanism module is included to generate a predicted flow rate smoothing coefficient. The flow rate association value in the training running data sequence is input into the query vector generator of the temporal attention mechanism module to generate a query vector for the current time node. In the chemical solution flow measurement scenario, the flow rate association value includes information such as the rotor speed measurement value and the blade vibration amplitude measurement value of the target flow meter. These flow rate association values ​​have different values ​​at different time nodes, reflecting the dynamic changes in the liquid flow rate. When the flow rate association value is input into the query vector generator of the temporal attention mechanism module, the query vector generator processes the flow rate association value according to internal parameters and algorithms. For example, the query vector generator may include multiple linear transformation layers and activation function layers. After the flow rate association value is calculated by these layers, the query vector for the current time node is generated. This query vector contains the importance weight information of the current flow rate association value in the entire time series, which reflects the relationship between the current flow rate association value and the flow rate association values ​​of other time nodes.

[0103] The attention weights between the query vector and the key vectors of the historical time nodes are calculated, and the value vectors of the historical time nodes are weighted summed based on the attention weights to obtain the context-aware flow velocity feature representation. In the temporal attention mechanism, each historical time node has a corresponding key vector and value vector. The key vector is a feature representation of the flow velocity association value of the historical time node, and the value vector is other information related to the flow velocity association value (such as environmental factors related to the flow velocity, etc.). The similarity between the query vector and the key vector of each historical time node is calculated (for example, through methods such as dot product operations), and then these similarities are converted into attention weights through the softmax function. These attention weights represent the degree of correlation between the current flow velocity association value and the flow velocity association value of each historical time node. Based on these attention weights, the value vectors of the historical time nodes are weighted summed. For example, assuming there are three historical time nodes, the corresponding attention weights are 0.3, 0.5, and 0.2, and the corresponding value vectors of the historical time nodes are [1, 2, 3], [4, 5, 6], and [7, 8, 9], respectively. Then the context-aware flow rate feature representation obtained by weighted summation is 0.3*[1, 2, 3]+0.5*[4, 5, 6]+0.2*[7, 8, 9]=[3.4, 4.7, 5.6]. This context-aware flow rate feature representation integrates information such as the current and historical flow rate correlation values ​​and related environmental factors, and can more comprehensively reflect the actual flow rate situation.

[0104] The context-aware flow rate feature representation is input into the sigmoid activation function to generate a predicted flow rate smoothing coefficient between 0 and 1, where the predicted flow rate smoothing coefficient is used to suppress short-term fluctuations in flow rate data. The sigmoid activation function converts the input context-aware flow rate feature representation into a value between 0 and 1. For example, after inputting [3.4, 4.7, 5.6] into the sigmoid activation function, a value is obtained, assuming it is 0.8. This predicted flow rate smoothing coefficient of 0.8 represents the degree of smoothing of the flow rate data. When there are short-term fluctuations in the flow rate data, by multiplying the flow rate data by this predicted flow rate smoothing coefficient, the short-term fluctuations can be effectively suppressed, making the flow rate data smoother and more stable, thereby improving the accuracy of flow measurement. In the chemical solution flow measurement scenario, since the flow of liquid in the pipeline may be affected by various factors (such as slight opening and closing changes of the valve, slight vibration of the pump, etc.), the short-term fluctuations in the flow rate will be generated. This predicted flow rate smoothing coefficient can compensate for these fluctuations, making the final flow measurement result more reliable.

[0105] Figure 2 The hardware structure of the flow meter online calibration system 100 provided in the embodiment of the present invention for implementing the above-mentioned flow meter online calibration method is shown as follows: Figure 2 As shown, the flow meter online calibration system 100 may include a processor 110 , a machine-readable storage medium 120 , a bus 130 , and a communication unit 140 .

[0106] The machine-readable storage medium 120 may store data and / or instructions. In some embodiments, the machine-readable storage medium 120 may store data acquired from an external terminal. In some embodiments, the machine-readable storage medium 120 may store data and / or instructions that the flow meter online calibration system 100 uses to execute or use to complete the exemplary method described in the present invention.

[0107] During the specific implementation process, one or more processors 110 execute computer executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the flow meter online calibration method of the above method embodiment. The processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to control the sending and receiving actions of the communication unit 140.

[0108] The specific implementation process of the processor 110 can refer to the various method embodiments executed by the above-mentioned flow meter online calibration system 100. The implementation principles and technical effects are similar, and this embodiment will not be repeated here.

[0109] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer executable instructions are preset. When a processor executes the computer executable instructions, the above flow meter online calibration method is implemented.

[0110] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, various features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A flow meter online calibration method, characterized in that: The method comprises: Collecting a real-time operating data set of a target flow meter in a pipeline operating environment, wherein the real-time operating data set includes dynamic monitoring data generated by the target flow meter during fluid transportation and environmental status data corresponding to the pipeline operating environment; Performing data preprocessing on the real-time operation data set to obtain a preprocessed operation data sequence, wherein the preprocessed operation data sequence is used to describe the operation state change trend of the target flow meter at multiple consecutive time nodes; Inputting the preprocessed operation data sequence into a pre-trained calibration parameter generation model to generate a calibration parameter set matching the current operation state of the target flow meter, the calibration parameter set including a flow correction coefficient, an environmental compensation factor, and an error adjustment threshold; Based on the calibration parameter set, real-time adjustment is performed on the measurement output data of the target flow meter to generate a calibrated flow measurement result, and the calibrated flow measurement result is compared and verified with a preset standard flow reference value; When the deviation between the calibrated flow measurement result and the standard flow reference value is greater than the error adjustment threshold, an updated calibration parameter set is regenerated and the real-time adjustment is iteratively performed until the deviation is within the error adjustment threshold.

2. The flow meter online calibration method according to claim 1, characterized in that: The real-time operation data set includes a plurality of operation sub-data of the flow meter within a preset time period, the operation sub-data includes temperature monitoring sub-data, pressure monitoring sub-data and flow rate monitoring sub-data, and the data preprocessing of the real-time operation data set to obtain a preprocessed operation data sequence includes: For the temperature monitoring sub-data, extract the outer wall temperature measurement value and the fluid internal temperature measurement value of the pipeline where the target flow meter is located, and perform difference calculation on the outer wall temperature measurement value and the fluid internal temperature measurement value to obtain a temperature gradient change sequence; For the pressure monitoring sub-data, identifying the pressure fluctuation peak value in the fluid flow direction in the pipeline operation environment, and generating a pressure stability evaluation index based on the occurrence frequency of the pressure fluctuation peak value; For the flow velocity monitoring sub-data, obtaining the rotor speed measurement value and the blade vibration amplitude measurement value of the target flow meter, and performing time-series alignment on the rotor speed measurement value and the blade vibration amplitude measurement value to generate a flow velocity associated feature vector; The temperature gradient change sequence, the pressure stability evaluation index and the flow rate associated characteristic vector are spliced ​​according to time nodes to generate the preprocessed operation data sequence, wherein the data unit corresponding to each time node in the preprocessed operation data sequence includes the temperature gradient value, the pressure stability level and the flow rate associated value.

3. The flow meter online calibration method according to claim 2, characterized in that: The calibration parameter generation model includes a multi-level parameter generation unit, and the pre-processed operation data sequence is input into the pre-trained calibration parameter generation model to generate a calibration parameter set matching the current operation state of the target flow meter, including: Calling the first-level parameter generation unit to perform nonlinear mapping processing on the temperature gradient value in the preprocessed operation data sequence to generate a primary temperature compensation factor, and weightedly fusing the primary temperature compensation factor with the fluid internal temperature measurement value to obtain a final temperature compensation coefficient; Calling the second-level parameter generation unit to discretize and classify the pressure stability level in the preprocessed operation data sequence, determine the pressure condition category to which the current pipeline operation environment belongs, and match the corresponding pressure compensation weight from a preset pressure-flow relationship table based on the pressure condition category; Calling the third-level parameter generation unit to perform sliding window mean filtering on the velocity correlation values ​​in the preprocessed operation data sequence to eliminate instantaneous velocity fluctuation noise, and calculating the velocity smoothing coefficient based on the filtered velocity correlation values; The final temperature compensation coefficient, the pressure compensation weight and the flow rate smoothing coefficient are normalized to generate a flow correction coefficient in the calibration parameter set, and the product of the pressure compensation weight and the flow rate smoothing coefficient is determined as the environmental compensation factor.

4. The flow meter online calibration method according to claim 3, characterized in that: The step of adjusting the measurement output data of the target flow meter in real time based on the calibration parameter set to generate a calibrated flow measurement result includes: Obtaining an original flow measurement value output by the target flow meter in an uncalibrated state, and extracting a collection timestamp corresponding to the original flow measurement value; matching corresponding temperature gradient values, pressure stability levels, and flow rate association values ​​from the preprocessed operation data sequence according to the acquisition timestamp; Inputting the temperature gradient value into the compensation function corresponding to the final temperature compensation coefficient to obtain a temperature correction amount, and inputting the pressure stability level into the adjustment function corresponding to the pressure compensation weight to obtain a pressure correction amount; The original flow measurement value, the temperature correction value and the pressure correction value are substituted into a preset flow superposition formula to obtain a preliminary calibrated flow value, and the preliminary calibrated flow value is multiplied by the flow velocity smoothing coefficient to generate the calibrated flow measurement result.

5. The flow meter online calibration method according to claim 4, characterized in that: The comparing and verifying the calibrated flow measurement result with a preset standard flow reference value includes: Acquire a historical standard flow data set matching the current pipeline operation environment from a remote calibration database, wherein the historical standard flow data set includes a reference flow value calibrated by a laboratory under the same environmental conditions; Calculating the absolute deviation between the calibrated flow measurement result and the reference flow value, and calculating the moving average of all absolute deviation values ​​within a preset time window; When the moving average value is greater than the error adjustment threshold, a calibration parameter update instruction is triggered, wherein the calibration parameter update instruction is used to instruct to regenerate the updated calibration parameter set; The flow correction coefficient and the environmental compensation factor in the updated calibration parameter set are dynamically weighted to generate a new error adjustment threshold, and the new error adjustment threshold is fed back to the calibration parameter generation model for parameter self-optimization.

6. The flow meter online calibration method according to claim 5, characterized in that: The pre-trained calibration parameter generation model is trained by the following steps: Acquire a historical pipeline operation data set, wherein the historical pipeline operation data set includes uncalibrated operation data collected by multiple flow meters under different working conditions and corresponding laboratory calibration data; Performing noise filtering and outlier removal on the uncalibrated operating data to generate a training operating data sequence, and converting the laboratory calibration data into a standard flow reference sequence; Constructing an initial parameter generation model, wherein the initial parameter generation model comprises a temperature compensation branch, a pressure compensation branch and a flow rate smoothing branch connected in series; Input the training operation data sequence into the initial parameter generation model, generate a predicted temperature compensation coefficient through the temperature compensation branch, generate a predicted pressure compensation weight through the pressure compensation branch, and generate a predicted flow rate smoothing coefficient through the flow rate smoothing branch; Calculate the mean square error between the predicted temperature compensation coefficient and the true value of the temperature compensation in the standard flow reference sequence to obtain a temperature loss value, and calculate the cross entropy loss value between the predicted pressure compensation weight and the true value of the pressure compensation to obtain a pressure loss value; The temperature loss value, the pressure loss value, and the cosine similarity of the predicted flow velocity smoothing coefficient and the true flow velocity smoothing value are weightedly summed to obtain a total training loss value, and the initial parameter generation model is back-propagated and optimized based on the total training loss value until convergence.

7. The flow meter online calibration method according to claim 6, characterized in that: The step of filtering the uncalibrated operating data for noise and removing outliers to generate an operating data sequence for training includes: Identifying mutation data points at consecutive time nodes in the uncalibrated running data, wherein the mutation data point is characterized by a difference between the mutation data point and a previous data point being greater than a preset mutation threshold; Performing context correlation analysis on the mutation data point, calculating the variance value of a preset number of data points before and after the mutation data point, and comparing the degree of deviation of the variance value from the historical variance mean; When the degree of deviation is greater than a set threshold, the mutation data point is marked as an outlier, and the outlier is replaced by linear interpolation of the previous and next data points; The replaced uncalibrated operating data is subjected to wavelet transform denoising processing, noise components of different frequency bands are extracted and filtered out from the original signal, and the training operating data sequence is generated.

8. The flow meter online calibration method according to claim 7, characterized in that: The temperature compensation branch includes a multi-layer perceptron network, and generating a predicted temperature compensation coefficient through the temperature compensation branch includes: Inputting the temperature gradient value in the training operation data sequence into the first hidden layer of the multi-layer perceptron network for nonlinear feature transformation to obtain a first hidden layer feature vector; Inputting the first hidden layer feature vector into the second hidden layer of the multilayer perceptron network for feature dimension reduction processing to obtain a second hidden layer feature vector; The second hidden layer feature vector is concatenated with the external environment temperature measurement value to generate a temperature fusion feature, and the temperature fusion feature is input into the output layer of the multi-layer perceptron network to generate the predicted temperature compensation coefficient.

9. The flow meter online calibration method according to claim 8, characterized in that: The pressure compensation branch includes a combined structure of a convolutional neural network and a fully connected layer, and generating a predicted pressure compensation weight through the pressure compensation branch includes: Converting the pressure stability level in the training operation data sequence into a one-hot encoding vector, and inputting the one-hot encoding vector into a one-dimensional convolutional layer of the convolutional neural network for local feature extraction; Performing maximum pooling processing on the convolution output features, extracting key pressure pattern features, and inputting the key pressure pattern features into the fully connected layer for probability distribution mapping; The output of the fully connected layer is processed by a softmax activation function to generate a category probability distribution corresponding to the predicted pressure compensation weight, and the category corresponding to the highest probability in the category probability distribution is used as the predicted pressure compensation weight; The flow rate smoothing branch includes a temporal attention mechanism module, and the generation of a predicted flow rate smoothing coefficient through the flow rate smoothing branch includes: Inputting the flow rate correlation value in the training operation data sequence into the query vector generator of the temporal attention mechanism module to generate a query vector of the current time node; Calculating the attention weight between the query vector and the key vector of the historical time node, and performing weighted summation on the value vector of the historical time node based on the attention weight to obtain a context-aware flow rate feature representation; The context-aware flow rate feature representation is input into a sigmoid activation function to generate the predicted flow rate smoothing coefficient between 0 and 1, wherein the predicted flow rate smoothing coefficient is used to suppress short-term fluctuations in flow rate data.

10. A flow meter online calibration system, characterized in that: The flow meter online calibration system includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the flow meter online calibration method described in any one of claims 1 to 9.

Images