Intelligent control system and method for special anti-explosion digital display turbine flowmeter for oil

Abstract

The invention relates to the technical field of flow detection, and discloses an intelligent control system and method for an anti-explosion digital display turbine flowmeter special for oils, and the method comprises the steps: calculating the rotation speed change proportion according to basic operation data, determining intermediate detection data based on the rotation speed change proportion and initial detection data, the method comprises the following steps of: analyzing a rotation speed change proportion belonging to an external factor, then determining a rotation influence value according to impeller rotation data, generating a state influence vector based on bearing state data, and finally determining accurate detection data based on the rotation influence value, the state influence vector and intermediate detection data. And then the rotation influence values and the state influence vectors belonging to the internal factors are continuously analyzed, so that secondary correction is carried out, the accumulative errors in the correction process can be reduced in a step-by-step processing mode, and the detection precision of the turbine flowmeter can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of flow detection, and more specifically, to an intelligent control system and method for an explosion-proof digital turbine flowmeter specifically for oil. Background Art

[0002] Flowmeter is a tool for flow measurement. In industrial production, the application of fluid measurement is indispensable, and the required accuracy is becoming more and more precise. In addition to its own complexity, fluid measurement is also affected by environmental factors, and the requirements for flowmeters are constantly increasing. According to its structure, the flow meter can be divided into turbine flowmeter, vortex flowmeter, electromagnetic flowmeter and differential pressure flowmeter. Turbine flowmeter is one of the main representatives of velocity flowmeter, with high accuracy, wide measurement range, strong durability, fast response speed and can be used for digital technology. With the continuous improvement of the level of production automation, higher requirements are also put forward for the detection accuracy of turbine flowmeter.

[0003] In the prior art, for example, a Chinese patent with publication number CN102393236A provides a method for self-correcting the instrument coefficient of a gas turbine flowmeter. The patent implants an electromagnetic coil in the turbine flowmeter housing, applies an equivalent detection force to simulate the impact force of the fluid on the turbine blades, and calculates a new instrument coefficient after measuring the frequency change, thereby correcting the flow measurement and improving the measurement accuracy. A Chinese patent with publication number CN113932889A provides an intelligent fuel metering correction device based on a turbine flowmeter. The patent can correct the density under temperature and pressure, and correct the volume flow under temperature and pressure to obtain the corrected fuel mass flow.

[0004] Although the prior art discloses relevant methods for improving the detection accuracy of turbine flowmeters, most of them focus on the influence of external factors, such as pressure, impact force and temperature, but lack analysis of the influence of internal factors (such as bearing wear) on the detection accuracy. Therefore, the prior art is rarely able to combine external and internal factors, resulting in difficulty in significantly improving the detection accuracy of turbine flowmeters.

[0005] In view of this, the present invention proposes an intelligent control system and method for an oil-specific explosion-proof digital turbine flowmeter to solve the above-mentioned problem. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent control system and method for an oil-specific explosion-proof digital turbine flowmeter.

[0007] To achieve the above object, the present invention provides the following technical solutions: In the first aspect, an intelligent control system for an explosion-proof digital turbine flowmeter for oil, comprising: The first calibration module is used to obtain the basic operation data and initial detection data of the turbine flowmeter under the pulsating flow condition, calculate the speed change ratio according to the basic operation data, and determine the intermediate detection data based on the speed change ratio and the initial detection data; Data processing module: used to obtain the impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determine the rotation influence value according to the impeller rotation data, and generate the state influence vector based on the bearing status data; The second correction module is used to determine the precise detection data based on the rotation influence value, the state influence vector and the intermediate detection data.

[0008] Furthermore, the basic operation data includes basic structure data and real-time operation data, the basic structure data includes impeller hub radius, blade number, impeller radius, blade inclination angle and cross-sectional radius, and the real-time operation data includes pulsation amplitude and incoming flow velocity. The method for calculating the speed change ratio according to the basic operation data includes: SVR= ; Where SVR is the speed change ratio, is the pulsation amplitude, is the incoming flow velocity, is the number of leaves, is the blade inclination angle, is the cross-sectional radius, is the instrument factor, is the impeller hub radius, is the impeller radius.

[0009] Furthermore, the method for determining the intermediate detection data based on the rotation speed change ratio and the initial detection data includes: Input the speed change ratio and initial detection data into a pre-built flow correction model to obtain intermediate detection data; The method for constructing the flow correction model includes: Acquire a sample data set, wherein the sample data set includes a historical speed change ratio, historical initial detection data, and historical intermediate detection data; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical speed change ratio and historical initial detection data in the sample training set are used as input data of the regression network, and the historical intermediate detection data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the intermediate detection data. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a flow correction model.

[0010] Further, the method for determining the rotation influence value according to the impeller rotation data includes: A corresponding weight judgment matrix is ​​constructed based on the impeller rotation data, and a consistency check is performed on the weight judgment matrix. When the consistency check passes, the influence standard weight corresponding to each element in the impeller rotation data is determined according to the weight judgment matrix, and the product of each element and the corresponding influence standard weight is summed to obtain the rotation influence value.

[0011] Further, performing consistency check on the weight judgment matrix refers to calculating the consistency ratio corresponding to the weight judgment matrix. When the consistency ratio is less than a preset ratio threshold, the consistency check passes. The method for calculating the consistency ratio includes: ; In the formula, is the consistency ratio, Represented as a weight judgment matrix, is the dimension of the weight judgment matrix, is the eigenvalue corresponding to the weight judgment matrix, is the consistency indicator, is the maximum eigenvalue corresponding to the weight judgment matrix, is the identity matrix, is the determinant function of the matrix.

[0012] Further, the method of determining the weight of the influencing criteria includes: The elements of each column in the weight judgment matrix are summed to generate an intermediate judgment matrix, and each element in the weight judgment matrix is ​​divided by the sum of the corresponding elements in the intermediate judgment matrix to obtain a normalized matrix. The average of each row in the normalized matrix is ​​used as the influence criterion weight.

[0013] Furthermore, the bearing state data includes a bearing surface image and bearing working data, and the method for generating a state influence vector based on the bearing state data includes: After the bearing surface image is Gaussian filtered and de-reflected, the processed bearing surface image is compared with the preset standard surface image to generate a comparison result. The internal influence coefficient is calculated according to the bearing working data, and the state influence vector is constructed based on the comparison result and the internal influence coefficient.

[0014] Furthermore, the method for generating the comparison result includes: The absolute value of the grayscale difference between each pixel in the bearing surface image and the corresponding pixel in the standard surface image is calculated, and a grayscale difference sequence is formed. The corresponding standard deviation is calculated based on the grayscale difference sequence, and the grayscale difference sequence and the standard deviation are used as the comparison results.

[0015] Furthermore, the bearing operating data includes the bearing surface temperature, the bearing load torque and the noise frequency value, and the internal influence coefficient is calculated according to the bearing surface temperature, the bearing load torque and the noise frequency value.

[0016] In a second aspect, an intelligent control method for an oil-specific explosion-proof digital turbine flowmeter is implemented based on the above-mentioned intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, comprising: Obtaining basic operating data and initial detection data of the turbine flowmeter under pulsating flow conditions, calculating the speed change ratio according to the basic operating data, and determining intermediate detection data based on the speed change ratio and the initial detection data; Obtaining impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determining a rotation influence value according to the impeller rotation data, and generating a state influence vector based on the bearing status data; The precise detection data is determined based on the rotation influence value, the state influence vector, and the intermediate detection data.

[0017] In a third aspect, an electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned intelligent control method for an oil-specific explosion-proof digital turbine flowmeter when executing the computer program.

[0018] In a fourth aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed, the intelligent control method of the above-mentioned oil-specific explosion-proof digital turbine flowmeter is implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention first calculates the speed change ratio according to the basic operating data, determines the intermediate detection data based on the speed change ratio and the initial detection data, then obtains the impeller rotation data and the bearing status data of the turbine flowmeter under the pulsating flow condition, determines the rotation influence value according to the impeller rotation data, generates the state influence vector based on the bearing status data, and finally determines the precise detection data based on the rotation influence value, the state influence vector and the intermediate detection data. Then, the present invention first analyzes the speed change ratio belonging to the external factors, thereby performing the first correction, and then continues to analyze the rotation influence value and the state influence vector belonging to the internal factors, thereby performing the second correction. This step-by-step processing method helps to reduce the cumulative error in the correction process, thereby significantly improving the detection accuracy of the turbine flowmeter. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural schematic diagram of an intelligent control system of an oil-specific explosion-proof digital turbine flowmeter in the present invention; Figure 2 This is a flow chart of an intelligent control method for an oil-specific explosion-proof digital turbine flowmeter in the present invention; Figure 3 It is a schematic diagram of the central axis of the impeller and the inclination angle of the blades in the present invention.

[0021] Reference numerals: 10, blade; 20, impeller center axis. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Example 1

[0024] See also Figure 1 As shown, this embodiment discloses an intelligent control system for an explosion-proof digital turbine flowmeter for oil, comprising: The first calibration module is used to obtain the basic operation data and initial detection data of the turbine flowmeter under the pulsating flow condition, calculate the speed change ratio according to the basic operation data, and determine the intermediate detection data based on the speed change ratio and the initial detection data; In this embodiment, the pulsating flow condition refers to a non-steady-state flow state. In this state, parameters such as the flow rate and pressure of the fluid will fluctuate periodically over time. Specifically, the fluid flows at an uneven speed or pressure in the pipeline, forming a flow pattern similar to a fluctuation. For example, in a pulsating flow, the velocity of the fluid may show a sinusoidal change over time. Such fluctuations will affect the measurement accuracy of the turbine flowmeter, because the rotation speed of the turbine will change with the fluctuation of the flow rate, resulting in an increase in the error of the measurement result. Pulsating flow conditions are commonly found in fluid pipelines affected by periodic equipment, such as the output end of a pump, an engine exhaust system, etc.

[0025] The basic operation data includes basic structure data and real-time operation data. The basic structure data includes at least the impeller hub radius, the number of blades, the impeller radius, the blade inclination angle and the cross-sectional radius. It is worth noting that the impeller hub radius is different from the impeller radius. The impeller hub radius refers to the distance from the impeller center axis to the edge of the impeller hub (center disk), the impeller radius refers to the farthest distance from the impeller center axis to the outer edge of the blade, and the blade inclination angle refers to the angle between the blade and the impeller center axis, such as Figure 3 As shown, Figure 3The blades 10, the impeller central axis 20 and the blade inclination angle θ are shown. The cross-sectional radius refers to the radius of the flow cross section in the turbine flow meter, indicating the radius of the area through which the fluid passes inside the turbine flow meter.

[0026] In this embodiment, the real-time operating data includes the pulsation amplitude and the incoming flow velocity. The incoming flow velocity refers to the average flow velocity of the fluid entering the turbine flowmeter, and the pulsation amplitude refers to the variation amplitude of the fluid flow velocity under pulsating flow conditions. For example, if the average flow velocity is 5m / s and the pulsation amplitude is 1m / s, the flow velocity will fluctuate between 4m / s and 6m / s. The incoming flow velocity can be obtained in real time through the ultrasonic flow sensor, and the pulsation amplitude can be obtained in real time through the pressure sensor.

[0027] Methods for calculating the speed change ratio based on basic operating data include: SVR= ; Where SVR is the speed change ratio, is the pulsation amplitude, is the incoming flow velocity, is the number of leaves, is the blade inclination angle, is the cross-sectional radius, is the instrument factor, is the impeller hub radius, is the impeller radius.

[0028] It should be noted that the instrument coefficient is an important parameter in the turbine flowmeter, which is used to indicate the number of pulses generated when a unit flow passes through. Specifically, it indicates the number of pulse signals output by the turbine flowmeter when each unit volume (such as cubic meters or gallons) of fluid passes through the flowmeter during the measurement process. The instrument coefficient is usually a constant. The working principle of the turbine flowmeter relies on the speed of the fluid passing through the turbine to drive the impeller to rotate. When the flow rate of the fluid pulsates, it will cause the impeller speed to fluctuate. Therefore, in this embodiment, the greater the speed change ratio, the greater the detection error of the turbine flowmeter.

[0029] The initial detection data refers to the flow data measured in real time by the turbine flowmeter. The initial detection data includes instantaneous flow or instantaneous flow velocity, etc. The method of determining the intermediate detection data based on the speed change ratio and the initial detection data includes: The rotation speed change ratio and the initial detection data are input into the pre-built flow correction model to obtain the intermediate detection data.

[0030] The method for constructing the flow correction model includes: Acquire a sample data set, wherein the sample data set includes a historical speed change ratio, historical initial detection data, and historical intermediate detection data; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical speed change ratio and historical initial detection data in the sample training set are used as input data of the regression network, and the historical intermediate detection data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the intermediate detection data. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a flow correction model. The initial regression network is a deep neural network model.

[0031] It should be supplemented that the intermediate detection data in this embodiment refers to the initial detection data after correction. For example, if the initial detection data includes instantaneous flow rate or instantaneous flow velocity, then the intermediate detection data includes the instantaneous flow rate or instantaneous flow velocity after correction. The above-mentioned historical intermediate detection data is collected by a volumetric flow meter that is not affected by pulsating flow conditions, such as a gear flow meter or a piston flow meter. The volumetric flow meter is not affected by pulsating flow conditions during operation, thereby achieving accurate detection. Therefore, technical personnel in this field can obtain historical intermediate detection data through experiments for subsequent model training.

[0032] This embodiment calculates the rotation speed change ratio and corrects the initial detection data in combination with the flow correction model, thereby effectively reducing the measurement error caused by the pulsating flow, thereby improving the detection accuracy of the turbine flowmeter.

[0033] Data processing module: used to obtain the impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determine the rotation influence value according to the impeller rotation data, and generate the state influence vector based on the bearing status data; Generally, the impeller rotation data includes but is not limited to the speed fluctuation amplitude, the speed fluctuation frequency and the speed stability value. The speed fluctuation amplitude refers to the maximum change value of the impeller speed within a preset time period. The speed fluctuation frequency refers to the number of times the impeller speed fluctuates within the preset time period. The speed stability value refers to the standard deviation value of the impeller speed within the preset time period. The preset time period can be 3 minutes or 5 minutes, etc., and this embodiment is not limited to this.

[0034] Methods for determining the rotation influence value based on the impeller rotation data include: A corresponding weight judgment matrix is ​​constructed based on the impeller rotation data, and a consistency check is performed on the weight judgment matrix. When the consistency check passes, the influence standard weight corresponding to each element in the impeller rotation data is determined according to the weight judgment matrix, and the product of each element and the corresponding influence standard weight is summed to obtain the rotation influence value.

[0035] It should be noted that the weight judgment matrix can be constructed by the expert scoring method in the analytic hierarchy process (AHP). In this case, a standard scale needs to be established first in the analytic hierarchy process, for example: Table 1

[0036] As shown above, 3 in Table 1 indicates that the speed fluctuation amplitude is more important than the speed fluctuation frequency, and 1 / 2 in Table 1 indicates that the speed fluctuation amplitude is slightly less important than the speed stability value. Then the weight judgment matrix WJ is as follows: WJ= ; It is not difficult to understand that the consistency check of the weight judgment matrix refers to calculating the consistency ratio corresponding to the weight judgment matrix. When the consistency ratio is less than the preset ratio threshold, it indicates that the weight judgment matrix has good consistency and the weight judgment matrix can continue to be used for weight calculation. When the consistency ratio is greater than or equal to the preset ratio threshold, it indicates that there is a large inconsistency in the weight judgment matrix and the parameters in the weight judgment matrix need to be adjusted.

[0037] Methods for calculating the consistency ratio include: ; In the formula, is the consistency ratio, Represented as a weight judgment matrix, is the dimension of the weight judgment matrix, is the eigenvalue corresponding to the weight judgment matrix, is the consistency indicator, is the maximum eigenvalue corresponding to the weight judgment matrix, is the identity matrix, is the determinant function of the matrix.

[0038] For example, if the weight judgment matrix is the 3×3 matrix shown above, then is 3, according to the standard table in the analytic hierarchy process (AHP) is 0.58, it is understandable that the eigenvalue It is an inherent property of matrices, usually implemented by software tools such as Python's NumPy library. Solve to get the eigenvalue It can be understood that the definition of the consistency ratio CR is based on the maximum eigenvalue of a real number. If the calculated maximum eigenvalue is a complex number, then the consistency ratio CR will also be a complex number. Therefore, when the maximum eigenvalue obtained by solution is a complex number, if the imaginary part of the complex number is close to zero, the imaginary part can be ignored. If the imaginary part of the complex number is large, the parameters in the weight judgment matrix should be readjusted, and each element in the weight judgment matrix should be checked to ensure the symmetry of the weight judgment matrix.

[0039] In this embodiment, the method for determining the weight of the influencing criterion includes: The elements of each column in the weight judgment matrix are summed to generate an intermediate judgment matrix, and each element in the weight judgment matrix is ​​divided by the sum of the corresponding elements in the intermediate judgment matrix to obtain a normalized matrix. The average of each row in the normalized matrix is ​​used as the influence criterion weight.

[0040] For example, WJ= ; Then IJ= ; NJ= ; Among them, IJ is the intermediate judgment matrix and NJ is the normalized matrix.

[0041] Then, the influence standard weight corresponding to the speed fluctuation amplitude is , and accordingly the influence standard weights corresponding to the speed fluctuation frequency and the speed stability value can be calculated.

[0042] In this embodiment, under different working conditions or environments, the relative importance of influencing factors may change. By calculating the influencing standard weights, the influencing standard weights of each factor can be dynamically adjusted to make the system more adaptable, while directly preset fixed weights are difficult to cope with such changes.

[0043] In this embodiment, the bearing status data includes a bearing surface image and bearing operating data. The bearing operating data includes but is not limited to the bearing surface temperature, the bearing load torque and the noise frequency value. It can be understood that the bearing surface image is mainly used to present the degree of damage to the bearing surface, while the bearing operating data characterizes the degree of influence of the dirty medium inside the bearing. For example, the dirty medium increases the friction resistance, making the bearing load torque larger. By monitoring the torque sensor on the bearing, the additional load caused by the dirty medium can be quantified.

[0044] Methods for generating a state influence vector based on bearing state data include: After the bearing surface image is Gaussian filtered and de-reflected, the processed bearing surface image is compared with the preset standard surface image to generate a comparison result. The internal influence coefficient is calculated according to the bearing working data, and the state influence vector is constructed based on the comparison result and the internal influence coefficient.

[0045] It is not difficult to understand that the bearing surface image is mainly used to present the degree of damage to the bearing surface. However, there is noise caused by oil pollution in the acquired bearing surface image. Therefore, the noise is removed through Gaussian filtering and de-reflection processing. The standard surface image refers to an ideal image of the bearing surface state without damage and oil pollution. This image is usually taken when the bearing is in a normal and healthy state and is used as a benchmark.

[0046] Methods for generating comparison results include: The absolute value of the grayscale difference between each pixel in the bearing surface image and the corresponding pixel in the standard surface image is calculated, and a grayscale difference sequence is formed. The corresponding standard deviation is calculated based on the grayscale difference sequence, and the grayscale difference sequence and the standard deviation are used as the comparison results.

[0047] It can be understood that the specifications of the bearing surface image and the standard surface image are the same, so each pixel in the bearing surface image has a pixel in the same position. The above-mentioned grayscale difference sequence is a collection of several grayscale difference absolute values. Calculating the standard deviation is a prior art and this embodiment will not go into details.

[0048] Methods for calculating internal influence coefficients based on bearing operating data include: INC= ; Where INC is the internal influence coefficient, is the bearing load torque, is the bearing surface temperature, is the noise frequency value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, It is an exponential function with e as base, where e is a natural constant.

[0049] In this embodiment, when the bearing load torque increases, this usually indicates that there is dirty medium inside the bearing, which leads to increased friction and causes the bearing to generate more friction heat during operation. This phenomenon is mostly caused by dirt accumulation. Therefore, it can be concluded that the larger the internal influence coefficient, the more serious the impact of the dirty medium on the detection accuracy of the turbine flowmeter.

[0050] It should be added that constructing the state influence vector based on the comparison result and the internal influence coefficient may be to convert the comparison result and the internal influence coefficient into a vector form and then concatenate them to obtain the state influence vector.

[0051] In this embodiment, by acquiring the impeller rotation data and the bearing status data, the operating status of the turbine flowmeter under pulsating flow conditions can be monitored from multiple angles. This multi-dimensional monitoring helps to more comprehensively understand the working conditions of the flowmeter and the factors that may cause measurement errors. For example, the rotation influence value is calculated through the impeller rotation data to identify the degree of influence of the pulsating flow during the rotation process, thereby reflecting the speed fluctuation in the turbine flowmeter detection. In addition, based on the bearing status data, a state influence vector can be constructed. Combined with the comparison results and the internal influence coefficient, the influence of internal factors on the detection accuracy of the turbine flowmeter can be quantified. This quantitative analysis helps to correct measurement errors in a timely manner and improve the overall detection accuracy of the turbine flowmeter.

[0052] The second correction module is used to determine the precise detection data based on the rotation influence value, the state influence vector and the intermediate detection data.

[0053] Methods for determining accurate detection data include: The rotation influence value, state influence vector and intermediate detection data are input into the pre-built detection correction model to obtain accurate detection data.

[0054] It can be understood that the construction method of the detection correction model is basically the same as the construction method of the flow correction model, except that the input is adjusted to the historical rotation influence value, the historical state influence vector and the historical intermediate detection data, and the output is changed to the historical precise detection data. It should be noted that the historical precise detection data is obtained by technical personnel in this field by conducting experiments using a turbine flowmeter with no obvious wear and oil stains on the bearing surface.

[0055] It should be noted that the above-mentioned initial correction is mainly carried out through the rotational speed change ratio to first deal with the detection error caused by the pulsating flow condition and reduce the direct measurement error caused by the flow velocity fluctuation. In this way, most of the significant errors can be filtered out first, thereby obtaining intermediate detection data that is closer to the actual situation. Then, further correction is performed in combination with the rotation influence value and the state influence vector. The remaining complexity errors can be refined and adjusted to make the final accurate detection data closer to the true value.

[0056] In this embodiment, the speed change ratio is first calculated according to the basic operating data, and the intermediate detection data is determined based on the speed change ratio and the initial detection data. Then, the impeller rotation data and the bearing status data of the turbine flowmeter under the pulsating flow condition are obtained, and the rotation influence value is determined according to the impeller rotation data. The state influence vector is generated based on the bearing status data. Finally, the precise detection data is determined based on the rotation influence value, the state influence vector and the intermediate detection data. Then, in this embodiment, the speed change ratio belonging to the external factors is first analyzed to perform the first correction, and then the rotation influence value and the state influence vector belonging to the internal factors are further analyzed to perform the second correction. This step-by-step processing method helps to reduce the cumulative error in the correction process, thereby significantly improving the detection accuracy of the turbine flowmeter.

[0057] Example 2

[0058] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses an intelligent control method for an oil-specific explosion-proof digital turbine flowmeter. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes: S10: acquiring basic operation data and initial detection data of the turbine flowmeter under pulsating flow conditions, calculating a rotation speed change ratio according to the basic operation data, and determining intermediate detection data based on the rotation speed change ratio and the initial detection data; The basic operation data includes basic structure data and real-time operation data. The basic structure data includes at least the impeller hub radius, the number of blades, the impeller radius, the blade inclination angle and the cross-sectional radius. It is worth noting that the impeller hub radius is different from the impeller radius. The impeller hub radius refers to the distance from the impeller center axis to the edge of the impeller hub (center disk), the impeller radius refers to the farthest distance from the impeller center axis to the outer edge of the blade, and the blade inclination angle refers to the angle between the blade and the impeller center axis, such as Figure 3 As shown, Figure 3 The blades 10, the impeller central axis 20 and the blade inclination angle θ are shown. The cross-sectional radius refers to the radius of the flow cross section in the turbine flow meter, indicating the radius of the area through which the fluid passes inside the turbine flow meter.

[0059] In this embodiment, the real-time operating data includes the pulsation amplitude and the incoming flow velocity. The incoming flow velocity refers to the average flow velocity of the fluid entering the turbine flowmeter, and the pulsation amplitude refers to the variation amplitude of the fluid flow velocity under pulsating flow conditions. For example, if the average flow velocity is 5m / s and the pulsation amplitude is 1m / s, the flow velocity will fluctuate between 4m / s and 6m / s. The incoming flow velocity can be obtained in real time through the ultrasonic flow sensor, and the pulsation amplitude can be obtained in real time through the pressure sensor.

[0060] Methods for calculating the speed change ratio based on basic operating data include: SVR= ; Where SVR is the speed change ratio, is the pulsation amplitude, is the incoming flow velocity, is the number of leaves, is the blade inclination angle, is the cross-sectional radius, is the instrument factor, is the impeller hub radius, is the impeller radius.

[0061] The initial detection data refers to the flow data measured in real time by the turbine flowmeter. The initial detection data includes instantaneous flow or instantaneous flow velocity, etc. The method of determining the intermediate detection data based on the speed change ratio and the initial detection data includes: The rotation speed change ratio and the initial detection data are input into the pre-built flow correction model to obtain the intermediate detection data.

[0062] The method for constructing the flow correction model includes: Acquire a sample data set, wherein the sample data set includes a historical speed change ratio, historical initial detection data, and historical intermediate detection data; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical speed change ratio and historical initial detection data in the sample training set are used as input data of the regression network, and the historical intermediate detection data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the intermediate detection data. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a flow correction model. The initial regression network is a deep neural network model.

[0063] S20: acquiring impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determining a rotation influence value according to the impeller rotation data, and generating a state influence vector based on the bearing status data; Methods for determining the rotation influence value based on the impeller rotation data include: A corresponding weight judgment matrix is ​​constructed based on the impeller rotation data, and a consistency check is performed on the weight judgment matrix. When the consistency check passes, the influence standard weight corresponding to each element in the impeller rotation data is determined according to the weight judgment matrix, and the product of each element and the corresponding influence standard weight is summed to obtain the rotation influence value.

[0064] Methods for calculating the consistency ratio include: ; In the formula, is the consistency ratio, Represented as a weight judgment matrix, is the dimension of the weight judgment matrix, is the eigenvalue corresponding to the weight judgment matrix, is the consistency indicator, is the maximum eigenvalue corresponding to the weight judgment matrix, is the identity matrix, is the determinant function of the matrix.

[0065] Methods for determining the weights of influencing criteria include: The elements of each column in the weight judgment matrix are summed to generate an intermediate judgment matrix, and each element in the weight judgment matrix is ​​divided by the sum of the corresponding elements in the intermediate judgment matrix to obtain a normalized matrix. The average of each row in the normalized matrix is ​​used as the influence criterion weight.

[0066] Methods for generating a state influence vector based on bearing state data include: After the bearing surface image is Gaussian filtered and de-reflected, the processed bearing surface image is compared with the preset standard surface image to generate a comparison result. The internal influence coefficient is calculated according to the bearing working data, and the state influence vector is constructed based on the comparison result and the internal influence coefficient.

[0067] Methods for generating comparison results include: The absolute value of the grayscale difference between each pixel in the bearing surface image and the corresponding pixel in the standard surface image is calculated, and a grayscale difference sequence is formed. The corresponding standard deviation is calculated based on the grayscale difference sequence, and the grayscale difference sequence and the standard deviation are used as the comparison results.

[0068] Methods for calculating internal influence coefficients based on bearing operating data include: INC= ; Where INC is the internal influence coefficient, is the bearing load torque, is the bearing surface temperature, is the noise frequency value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, It is an exponential function with e as base, where e is a natural constant.

[0069] S30: Determine precise detection data based on the rotation influence value, the state influence vector and the intermediate detection data.

[0070] Methods for determining accurate detection data include: The rotation influence value, state influence vector and intermediate detection data are input into the pre-built detection correction model to obtain accurate detection data.

[0071] It can be understood that the construction method of the detection correction model is basically the same as the construction method of the flow correction model, except that the input is adjusted to the historical rotation influence value, the historical state influence vector and the historical intermediate detection data, and the output is changed to the historical precise detection data. It should be noted that the historical precise detection data is obtained by technical personnel in this field by conducting experiments using a turbine flowmeter with no obvious wear and oil stains on the bearing surface.

[0072] Example 3

[0073] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an intelligent control method for an oil-specific explosion-proof digital turbine flowmeter provided by the above methods is implemented.

[0074] Since the electronic device introduced in this embodiment is an electronic device used to implement an oil-specific explosion-proof digital display turbine flowmeter intelligent control system in the embodiment of the present application, based on the oil-specific explosion-proof digital display turbine flowmeter intelligent control system introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is no longer introduced in detail. As long as technical personnel in this field implement the electronic device used in the oil-specific explosion-proof digital display turbine flowmeter intelligent control system in the embodiment of the present application, it belongs to the scope of protection of this application.

[0075] Example 4

[0076] The present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the intelligent control method of the oil-specific explosion-proof digital turbine flowmeter is implemented.

[0077] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0078] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0079] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0084] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

[0085] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control system for explosion-proof digital turbine flowmeters for oils. It is characterized in that include: The first calibration module is used to obtain the basic operation data and initial detection data of the turbine flowmeter under the pulsating flow condition, calculate the speed change ratio according to the basic operation data, and determine the intermediate detection data based on the speed change ratio and the initial detection data; Data processing module: used to obtain the impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determine the rotation influence value according to the impeller rotation data, and generate the state influence vector based on the bearing status data; The second correction module is used to determine the precise detection data based on the rotation influence value, the state influence vector and the intermediate detection data.

2. According to claim 1, an oil-specific explosion-proof digital turbine flowmeter intelligent control system, It is characterized in that The basic operation data includes basic structure data and real-time operation data. The basic structure data includes the impeller hub radius, the number of blades, the impeller radius, the blade inclination angle and the cross-sectional radius. The real-time operation data includes the pulsation amplitude and the incoming flow velocity. The method for calculating the speed change ratio according to the basic operation data includes: SVR= ; Where SVR is the speed change ratio, is the pulsation amplitude, is the incoming flow velocity, is the number of leaves, is the blade inclination angle, is the cross-sectional radius, is the instrument factor, is the impeller hub radius, is the impeller radius.

3. According to claim 2, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The method for determining the intermediate detection data based on the rotation speed change ratio and the initial detection data includes: Input the speed change ratio and initial detection data into a pre-built flow correction model to obtain intermediate detection data; The method for constructing the flow correction model includes: Acquire a sample data set, wherein the sample data set includes a historical speed change ratio, historical initial detection data, and historical intermediate detection data; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical speed change ratio and historical initial detection data in the sample training set are used as input data of the regression network, and the historical intermediate detection data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the intermediate detection data. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a flow correction model.

4. According to claim 1, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The method for determining the rotation influence value according to the impeller rotation data comprises: A corresponding weight judgment matrix is ​​constructed based on the impeller rotation data, and a consistency check is performed on the weight judgment matrix. When the consistency check passes, the influence standard weight corresponding to each element in the impeller rotation data is determined according to the weight judgment matrix, and the product of each element and the corresponding influence standard weight is summed to obtain the rotation influence value.

5. According to claim 4, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The consistency check of the weight judgment matrix refers to calculating the consistency ratio corresponding to the weight judgment matrix. When the consistency ratio is less than a preset ratio threshold, the consistency check passes. The method for calculating the consistency ratio includes: ； In the formula, is the consistency ratio, Represented as a weight judgment matrix, is the dimension of the weight judgment matrix, is the eigenvalue corresponding to the weight judgment matrix, is the consistency indicator, is the maximum eigenvalue corresponding to the weight judgment matrix, is the identity matrix, is the determinant function of the matrix.

6. According to claim 5, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The method for determining the weight of the impact criteria includes: The elements of each column in the weight judgment matrix are summed to generate an intermediate judgment matrix, and each element in the weight judgment matrix is ​​divided by the sum of the corresponding elements in the intermediate judgment matrix to obtain a normalized matrix. The average of each row in the normalized matrix is ​​used as the influence criterion weight.

7. According to claim 1, an intelligent control system for an explosion-proof digital turbine flowmeter for oil, It is characterized in that The bearing state data includes a bearing surface image and bearing working data. The method for generating a state influence vector based on the bearing state data includes: After the bearing surface image is Gaussian filtered and de-reflected, the processed bearing surface image is compared with the preset standard surface image to generate a comparison result. The internal influence coefficient is calculated according to the bearing working data, and the state influence vector is constructed based on the comparison result and the internal influence coefficient.

8. According to claim 7, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The method for generating the comparison result comprises: The absolute value of the grayscale difference between each pixel in the bearing surface image and the corresponding pixel in the standard surface image is calculated, and a grayscale difference sequence is formed. The corresponding standard deviation is calculated based on the grayscale difference sequence, and the grayscale difference sequence and the standard deviation are used as the comparison results.

9. According to claim 8, an intelligent control system for an oil-specific explosion-proof digital turbine flowmeter, It is characterized in that The bearing operating data includes bearing surface temperature, bearing load torque and noise frequency value, and the internal influence coefficient is calculated according to the bearing surface temperature, bearing load torque and noise frequency value.

10. An intelligent control method for an oil-specific explosion-proof digital turbine flowmeter, which is implemented based on the intelligent control system of an oil-specific explosion-proof digital turbine flowmeter according to any one of claims 1 to 9. It is characterized in that include: Obtaining basic operating data and initial detection data of the turbine flowmeter under pulsating flow conditions, calculating the speed change ratio according to the basic operating data, and determining intermediate detection data based on the speed change ratio and the initial detection data; Obtaining impeller rotation data and bearing status data of the turbine flowmeter under pulsating flow conditions, determining a rotation influence value according to the impeller rotation data, and generating a state influence vector based on the bearing status data; The precise detection data is determined based on the rotation influence value, the state influence vector, and the intermediate detection data.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the intelligent control method for an oil-specific explosion-proof digital turbine flowmeter as described in claim 10 is implemented.

12. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the intelligent control method for an oil-specific explosion-proof digital turbine flowmeter according to claim 10 is implemented.

Images