Ultrasonic flowmeter based on AI engine

Abstract

The invention discloses an ultrasonic flowmeter based on an AI engine, and particularly relates to the technical field of ultrasonic flow detection. According to the method, the fluid working condition is accurately identified through AI analysis, the measurement suitability in a complex scene is remarkably improved, the ultrasonic signal time domain, frequency domain and propagation characteristic multi-dimensional parameters are integrated, a weighted fusion algorithm and a mapping rule are adopted, the flow state type, the gas content and the impurity interference level are accurately judged, and the measurement accuracy is improved. The problem that the traditional technology is difficult to quantify the pain point of the complex working condition is solved, meanwhile, a time difference method, a frequency difference method or a comprehensive correction method is dynamically matched based on the working condition recognition result, personalized adaptation of computational logic is achieved, the measurement deviation of a single algorithm under transition flow, high gas content and strong interference scenes is effectively avoided, and flow detection better fits the actual working condition.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic flow detection technology, and more specifically, to an ultrasonic flow meter based on an AI engine. Background Technology

[0002] Ultrasonic flow meters, with their advantages of non-contact measurement, no pressure loss, and compatibility with various fluids, have been widely used in many key fields such as petrochemicals, biopharmaceuticals, municipal water supply, and medical devices, becoming an important piece of equipment in the field of flow detection.

[0003] However, in actual industrial and civilian applications, fluid conditions are often complex and variable, and traditional ultrasonic flow meters face the following technical shortcomings: In terms of flow regime adaptation, the flow regime of fluid in the pipe will dynamically switch to laminar flow, transitional flow or turbulent flow depending on factors such as flow velocity and viscosity. The flow velocity distribution characteristics of fluid under different flow regimes are significantly different. Traditional ultrasonic flow meters mostly use a single fixed flow calculation logic, which cannot be dynamically adapted according to the flow regime changes, resulting in large measurement errors under complex flow regimes such as transitional flow. Meanwhile, the actual fluid being measured often contains gas. The mixing of gas will cause the ultrasonic signal to attenuate more, increase noise, and reduce the proportion of effective signal. Traditional equipment lacks accurate identification of gas content and a targeted compensation mechanism, which further amplifies the flow measurement deviation. In terms of anti-interference capability, fluids in industrial environments often contain solid impurities. These impurities can cause ultrasonic distortion, increased clutter intensity, decreased signal-to-noise ratio, and even loss of signal peaks. Traditional ultrasonic flow meters are not capable of quantitatively assessing and correcting impurity interference, and it is difficult to distinguish different levels of interference intensity and take corresponding compensation strategies.

[0004] To address this, an ultrasonic flow meter based on an AI engine has been launched. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an ultrasonic flow meter based on an AI engine.

[0006] To achieve the above objectives, the present invention provides the following technical solution: An ultrasonic flow meter based on an AI engine includes an AI processing module, wherein the AI ​​processing module is built-in: Parameter storage unit: stores basic pipeline parameters, basic fluid parameters, and flow calculation logic library; Signal processing unit: acquires the original ultrasonic wave signal, filters, amplifies, and performs impedance matching on it, and then outputs the time domain parameters, frequency domain parameters, and ultrasonic wave propagation characteristic parameters of the ultrasonic signal; AI Analysis Unit: Analyzes the time-domain parameters, frequency-domain parameters, and ultrasonic propagation characteristic parameters of the output ultrasonic signal, combines them with the basic parameters in the parameter storage unit, completes the identification of flow type, gas content, and impurity interference level, and determines the flow calculation logic based on the identification results; Traffic output unit: Calls the selected traffic calculation logic to complete the traffic calculation and outputs the traffic measurement results.

[0007] Specifically, the pipeline basic parameters, fluid basic parameters, and flow calculation logic library include: Pipeline basic parameters include pipe diameter, wall thickness, transducer spacing, and angle; The basic fluid parameters include preset temperature, viscosity, standard velocity of sound of pure fluid, fluid density, and pure fluid attenuation coefficient. The flow calculation logic library includes time difference method, frequency difference method and comprehensive correction method; The time-domain parameters, frequency-domain parameters, and ultrasonic propagation characteristics parameters of ultrasonic signals specifically include: The time-domain parameters of an ultrasound signal include signal amplitude, waveform distortion coefficient, and effective signal duration. Ultrasonic signal frequency domain parameters include harmonic component ratio, frequency domain clutter intensity, and clutter echo number; Ultrasonic propagation characteristics include signal attenuation coefficient, sound velocity, and round-trip time difference of ultrasonic signal.

[0008] Specifically, the logic for identifying flow types; Flow patterns include laminar flow, transitional flow, and turbulent flow; The round-trip time difference, sound velocity, and harmonic component ratio of the ultrasonic signal are retrieved for x consecutive sampling periods; x>5; after calculation using the standard deviation formula, the time fluctuation value, sound velocity stability, and harmonic stability are output. For the signal amplitude within x sampling periods, the standard deviation and mean are calculated respectively to obtain the amplitude standard deviation and the average amplitude. The amplitude stability is obtained by calculating the ratio with the amplitude standard deviation as the numerator and the average amplitude as the denominator. After comprehensively processing the time fluctuation value, sound velocity stability, harmonic stability and amplitude stability by weighted fusion, the flow characteristic coefficient is output. The system retrieves pipe diameter, fluid viscosity, and standard sound velocity of the pure fluid, and calculates the average flow velocity using ultrasonic signals. After verification based on flow characteristic coefficients and Reynolds number, it outputs the flow type. Using a pre-constructed mapping rule between Reynolds number and flow regime verification coefficient, the calculated Reynolds number is converted into a flow regime verification coefficient and then multiplied by the flow regime characteristic coefficient to obtain the flow regime determination coefficient. Three sets of coefficient intervals are preset to correspond to the flow regime determination coefficients, and each set of coefficient intervals corresponds to a flow regime type; the flow regime determination coefficients are matched with the corresponding coefficient intervals to determine the flow regime type.

[0009] Specifically, the calculation logic for gas content; Retrieve the signal attenuation coefficient for x consecutive cycles, calculate the difference between it and the pure fluid attenuation coefficient, and take the average value to obtain the attenuation coefficient increment. Retrieve the duration of the effective signal within x consecutive periods, and calculate the proportion of the duration of the effective signal in the total sampling time to obtain the proportion of the effective signal. Count the number of clutter echoes over x consecutive periods and sum them up to obtain the total clutter count; After comprehensively processing the attenuation coefficient increment, effective signal ratio, and total clutter using weighted fusion, the gas-bearing characteristic coefficient is output. By utilizing a pre-constructed mapping rule between gas-bearing characteristic coefficients and gas-bearing percentage, the calculated gas-bearing characteristic coefficients are transformed into gas-bearing percentage.

[0010] Specifically, the logic for determining the level of impurity interference; The similarity between the measured waveform and the standard pure fluid waveform over x consecutive periods is retrieved, and the average value is calculated before outputting the waveform distortion coefficient. The power values ​​falling outside the set effective frequency bandwidth within x consecutive periods are summed to obtain the clutter power; the proportion of clutter power in the total signal power is calculated to obtain the clutter intensity proportion. Calculate the average signal-to-noise ratio of each group within x consecutive periods, and output the overall signal-to-noise ratio. The standard number of peak values ​​within a single period is preset. The measured time-domain waveform within a single period is analyzed. If the amplitude of a certain sampling point is greater than the amplitude of the three sampling points before and after it, and is also greater than the preset reference amplitude, it is determined to be a valid peak value. Periods in which the number of valid peak values ​​is lower than the standard number of peak values ​​are marked as lost periods. The proportion of lost periods in x is calculated as the peak loss ratio. After comprehensively processing the waveform distortion coefficient, clutter intensity ratio, overall signal-to-noise ratio, and peak loss ratio using weighted fusion, the interference characteristic coefficient is output. Five sets of coefficient ranges are set for the interference characteristic coefficients, and each set of coefficient ranges corresponds to an interference level. The interference levels are divided into 1-5 levels. The interference characteristic coefficients are matched with the corresponding coefficient ranges to determine the interference level.

[0011] Specifically, the identification results determine the selected traffic calculation logic; The flow regime type, gas content, and impurity interference level are integrated and retrieved into the flow calculation logic library. The flow calculation logic library has pre-set flow calculation logic corresponding to the range of gas content and impurity interference level under different flow regime types.

[0012] Specifically, the specific steps for flow calculation; : Retrieve the matched flow calculation logic, flow type, gas content, and impurity interference level; The system uses the matched flow calculation logic as its core, substitutes the synchronous measured ultrasonic parameters, pipeline and fluid basic parameters, executes the standard algorithm of the flow calculation logic, and calculates the basic flow value. Based on the basic flow rate value, combined with the flow regime correction coefficient, gas content correction coefficient, and interference correction coefficient converted from the flow regime type, gas content, and impurity interference level, the final flow rate value is output as the flow measurement result.

[0013] Specifically, If the comprehensive correction method is matched in the process, the flow type is extracted, and the basic flow value is calculated based on the calculation logic set for different flow types.

[0014] Specifically, The process of determining the flow regime correction coefficient, gas content correction coefficient, and disturbance correction coefficient in the steps; Set a set of flow regime correction coefficients for laminar and turbulent flow types respectively; If the flow type is transitional flow, then retrieve the three sets of coefficient intervals corresponding to the flow determination coefficient, retrieve the highest value in the coefficient interval corresponding to laminar flow and the lowest value in the coefficient interval corresponding to turbulent flow, calculate the absolute difference between the flow determination coefficient and the highest and lowest values ​​respectively, compare the two sets of absolute differences, and select the flow type with the lower absolute difference as the replacement type of transitional flow; Extract the gas content characteristic coefficient and interference characteristic coefficient corresponding to the gas content and impurity interference level, respectively, and convert them into gas content correction coefficient and interference correction coefficient using the mapping rules of gas content characteristic coefficient-gas content correction coefficient and interference characteristic coefficient-interference correction coefficient.

[0015] The technical effects and advantages of this invention are as follows: (1) By using AI analysis, the fluid working conditions can be accurately identified, significantly improving the measurement adaptability in complex scenarios. It integrates multiple parameters of ultrasonic signal time domain, frequency domain and propagation characteristics, and adopts weighted fusion algorithm and mapping rules to accurately determine the flow type, gas content and impurity interference level. This solves the pain point that traditional technology is difficult to quantify complex working conditions. At the same time, based on the working condition identification results, it dynamically matches the time difference method, frequency difference method or comprehensive correction method to realize the personalized adaptation of the calculation logic, effectively avoiding the measurement deviation of a single algorithm in transition flow, high gas content and strong interference scenarios, making the flow detection more in line with the actual working conditions. (2) This invention significantly improves measurement accuracy and ensures data reliability through a correction mechanism. After the basic flow rate is calculated, it combines the exclusive correction coefficients for flow regime, gas content and impurity interference level conversion to complete accurate compensation through formula. The flow regime correction coefficient specifically solves the error caused by the difference in laminar and turbulent flow velocity distribution, while the gas content and interference correction coefficients offset the signal distortion caused by gas mixing and impurity interference. It can still output high-precision flow data under complex working conditions to meet the accurate measurement needs of industrial production and people's livelihood applications. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of an ultrasonic flow meter based on an AI engine, according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, an ultrasonic flow meter based on an AI engine includes an AI processing module, which has a built-in parameter storage unit, a signal processing unit, an AI analysis unit, and a flow output unit. Parameter storage unit: stores basic pipeline parameters, basic fluid parameters, and flow calculation logic library; Pipeline basic parameters include pipe diameter, wall thickness, transducer spacing, and angle; The basic fluid parameters include preset temperature, viscosity, standard velocity of sound of pure fluid, fluid density, and pure fluid attenuation coefficient. The relevant parameters in the parameter storage unit can be collected by pre-deployed smart sensors; For example, the transducer spacing and installation angle can be determined by MEMS triaxial tilt sensor + laser displacement sensor. The basic value is calibrated during installation, and the displacement / angle deviation caused by pipeline vibration and thermal expansion and contraction is collected and corrected in real time. Fluid viscosity and density: A tuning fork resonant intelligent sensor is used for direct online synchronous measurement.

[0019] The flow calculation logic library includes time difference method, frequency difference method and comprehensive correction method; Signal processing unit: Connected to the ultrasonic transducer, it is used to acquire the original ultrasonic wave signal, perform preliminary conditioning such as filtering, amplification and impedance matching, and then realize digitization through high-speed analog-to-digital conversion, outputting the time domain parameters, frequency domain parameters and ultrasonic wave propagation characteristic parameters of the ultrasonic signal; The time-domain parameters of an ultrasound signal include signal amplitude, waveform distortion coefficient, and effective signal duration. Ultrasonic signal frequency domain parameters include harmonic component ratio, frequency domain clutter intensity, and clutter echo number; Ultrasonic propagation characteristics include signal attenuation coefficient, sound velocity, and round-trip time difference of ultrasonic signal; An ultrasonic transducer transmits and receives ultrasonic signals, enabling bidirectional propagation of ultrasonic waves in the fluid being measured.

[0020] AI Analysis Unit: Analyzes the time-domain parameters, frequency-domain parameters, and ultrasonic propagation characteristic parameters of the output ultrasonic signal, and combines them with the basic parameters in the parameter storage unit to identify the flow type, gas content, and impurity interference level. Based on the identification results, it determines the optimal flow calculation logic. The process of identifying flow types: Flow patterns include laminar flow, transitional flow, and turbulent flow; the essence of flow pattern is the uniformity of fluid velocity distribution, which is reflected in ultrasonic signals as the stability of propagation characteristics. Retrieve the round-trip time difference, sound velocity, and harmonic component ratio of the ultrasonic signal for x consecutive sampling periods; x > 5 and is an integer; After calculation using the standard deviation formula, the output values ​​are time fluctuation, sound velocity stability, and harmonic stability. For the signal amplitude within x sampling periods, the standard deviation and mean are calculated respectively to obtain the amplitude standard deviation and the average amplitude. The amplitude stability is obtained by calculating the ratio with the amplitude standard deviation as the numerator and the average amplitude as the denominator. After comprehensively processing the time fluctuation value, sound velocity stability, harmonic stability and amplitude stability by weighted fusion, the flow characteristic coefficient is output. Calculation process: After normalizing the time fluctuation values, sound velocity stability, harmonic stability, and amplitude stability, use... The expression represents the time fluctuation value, sound speed stability, harmonic stability, and amplitude stability, respectively. Using formula Calculate the flow regime characteristic coefficients ;in These are preset weighting coefficients, with values ​​set to 0.3 / 0.25 / 0.25 / 0.2; Weighting criteria: Time difference fluctuations directly reflect flow velocity distribution and have the highest weight; sound velocity and amplitude are second, and harmonic stability is used for auxiliary verification. These can be dynamically adjusted according to actual conditions.

[0021] The pipe diameter, fluid viscosity, and standard sound velocity of the pure fluid are retrieved, and the average flow velocity is calculated using the ultrasonic signal. Calculate the average flow velocity based on the ultrasonic signal derivation process. 2L; of which The measured average sound velocity is given by L, where L is the transducer spacing. For the angle of propagation, To extract the time difference between downstream propagation and upstream propagation.

[0022] After verification using flow characteristic coefficients and Reynolds number, the flow type is output. Reynolds number ;in For fluid density, Where is the fluid viscosity and D is the pipe diameter.

[0023] Inertial force dominates: the smaller Re is, the greater the possibility of laminar flow, and vice versa, the greater the possibility of turbulent flow. When Re is neither high nor low, the greater the possibility of transitional flow.

[0024] Using a pre-constructed mapping rule between Reynolds number and flow regime verification coefficient, the calculated Reynolds number is converted into a flow regime verification coefficient and then multiplied by the flow regime characteristic coefficient to obtain the flow regime determination coefficient. Mapping rule description: Set each set of numerical intervals corresponding to the Reynolds number, and each set of numerical intervals corresponds to a set of flow regime verification coefficients; the range of flow regime verification coefficients is limited to 0.967-1.068, which is preset by technical personnel and can be dynamically adjusted later. Match the Reynolds number with the corresponding numerical interval to determine the flow regime verification coefficient. The higher the Reynolds number, the higher the probability of matching 1.068.

[0025] Three sets of coefficient intervals are preset to correspond to the flow regime determination coefficients, and each set of coefficient intervals corresponds to a flow regime type; the flow regime determination coefficients are matched with the corresponding coefficient intervals to determine the flow regime type.

[0026] The larger the flow regime determination coefficient, the higher the probability that the corresponding flow regime type is turbulence.

[0027] The calculation process of gas content: Gas in a fluid can cause ultrasonic signal attenuation, increased noise, and a reduced proportion of effective signal.

[0028] Retrieve the signal attenuation coefficient for x consecutive cycles, calculate the difference between it and the pure fluid attenuation coefficient, and take the average value to obtain the attenuation coefficient increment. Retrieve the duration of the effective signal within x consecutive periods, and calculate the proportion of the duration of the effective signal in the total sampling time to obtain the proportion of the effective signal. Count the number of clutter echoes over x consecutive periods and sum them up to obtain the total clutter count; After comprehensively processing the attenuation coefficient increment, effective signal ratio, and total clutter using weighted fusion, the gas-bearing characteristic coefficient is output. Calculation process: After normalizing the attenuation coefficient increment, effective signal ratio, and total clutter, use... , as well as express; Using formula Calculate the gas-bearing characteristic coefficient ;in , as well as These are preset weighting coefficients, with values ​​set to 0.5 / 0.3 / 0.2; The weighting is based on the following criteria: the increase in attenuation coefficient is most sensitive to gas content and has the highest weight; the proportion of effective signal is a secondary indicator; and the total number of clutter and the attenuation coefficient complement each other and have the next highest weight.

[0029] As the gas content increases, the attenuation coefficient increment and the total number of clutter gradually increase, while the proportion of effective signal gradually decreases.

[0030] By utilizing a pre-constructed mapping rule between gas-holding characteristic coefficients and gas-holding percentage, the calculated gas-holding characteristic coefficients are transformed into gas-holding percentages. Mapping rule description: Set the coefficient intervals corresponding to the gas content characteristic coefficients, and each coefficient interval corresponds to a gas content rate; the gas content rate ranges from 1% to 100%. Match the gas content characteristic coefficients with the corresponding coefficient intervals to determine the gas content rate. The higher the gas content characteristic coefficient, the higher the probability of matching 100%.

[0031] The process of determining the level of impurity interference: Impurities can cause ultrasonic distortion, increased noise, and reduced signal-to-noise ratio.

[0032] The similarity between the measured waveform and the standard pure fluid waveform over x consecutive periods is retrieved; cosine similarity is used for calculation, and the result is subtracted from 1 to obtain the final similarity; the waveform distortion coefficient is then output after averaging. It reflects the degree of distortion of the measured ultrasonic waveform caused by factors such as impurities and interference. The value range is 0 to indicate complete consistency (no distortion) and 1 to indicate complete distortion (the standard waveform characteristics cannot be identified).

[0033] Based on the effective frequency bandwidth of the pure fluid standard power spectrum, the power values ​​falling outside the set effective frequency bandwidth within x consecutive periods are summed and used as clutter power. Calculate the proportion of clutter power in the total signal power to obtain the clutter intensity proportion; Calculate the average signal-to-noise ratio of each group within x consecutive periods, and output the overall signal-to-noise ratio. The standard number of peak values ​​within a single period is preset. The measured time-domain waveform within a single period is analyzed. If the amplitude of a certain sampling point is greater than the amplitude of the three adjacent sampling points before and after it, and is also greater than the preset reference amplitude, it is determined to be a valid peak value. Periods with fewer effective peak values ​​than the standard peak value are marked as lost periods; Calculate the percentage of lost periods in x, as the peak loss ratio; After comprehensively processing the waveform distortion coefficient, clutter intensity ratio, overall signal-to-noise ratio, and peak loss ratio using weighted fusion, the interference characteristic coefficient is output. Calculation process: After normalizing the waveform distortion coefficient, clutter intensity ratio, overall signal-to-noise ratio, and peak loss ratio, the following parameters are used: , , as well as express; Using formula The interference characteristic coefficients were calculated; where , , as well as These are preset weighting coefficients, with values ​​set to 0.3 / 0.25 / 0.25 / 0.2; Weighting criteria: Waveform distortion coefficient directly reflects signal distortion and has the highest weight; Clutter intensity ratio quantifies interference energy and has the second highest weight; Comprehensive signal-to-noise ratio reflects interference intensity inversely and complements clutter intensity; Peak loss ratio reflects the degree of damage to core features and assists in verification.

[0034] Five sets of coefficient ranges are set for the interference characteristic coefficients, and each set of coefficient ranges corresponds to an interference level. The interference levels are divided into 1-5 levels, with higher levels indicating more severe interference. The interference characteristic coefficients are matched with the corresponding coefficient ranges to determine the interference level; The flow regime type, gas content, and impurity interference level are integrated and entered into the flow calculation logic library for retrieval. The flow calculation logic library has pre-set flow calculation logic corresponding to the range of gas content and impurity interference level under different flow regime types. Additional explanation: The flow type will be represented by... , as well as This means that, in the flow calculation logic library, sub-libraries of different flow types are retrieved based on the current flow type. Each sub-library independently stores the calculation logic corresponding to the (A, B) combination, with no overlap. Here, A represents the gas content range and B represents the interference level. Example: The operating condition identification result is (laminar flow) + A (1%-10%) + B (interference level 2). Step 1: Search the fluid sub-library Identified flow type As a primary search keyword, it is retrieved and entered into the traffic calculation logic library. Sub-library (laminar flow sub-library), shielding G2 and G3 sub-libraries; Step 2: Match HJ combination exist In the sub-database, the identified A (1%-10%) + B (interference level 2) is used as the secondary search keywords to search the preset combination comparison table in the sub-database; Step 3: Determine the computational logic The combination A (1%-10%) + B (interference level 2) in the sub-library uniquely matches S (time difference method). The time difference method algorithm is directly retrieved from the traffic calculation logic library to perform subsequent traffic calculation.

[0035] Flow output unit: Calls the selected flow calculation logic to complete the flow calculation and outputs the flow measurement results; The specific steps are as follows: : Retrieve the matched flow calculation logic, flow type, gas content, and impurity interference level; The flow calculation logic includes formulas, parameter calling rules, and unit conversion standards; The system uses the matched flow calculation logic as its core, substitutes the synchronous measured ultrasonic parameters, pipeline and fluid basic parameters, executes the standard algorithm of the flow calculation logic, and calculates the basic flow value. The measured ultrasonic parameters, pipeline and fluid basic parameters include the measured average sound velocity, time difference between upstream and downstream flow, frequency difference between upstream and downstream flow, pipe diameter, transducer spacing, propagation angle, fluid density, viscosity, and standard sound velocity of pure fluid.

[0036] Time difference method: Based on the time difference of ultrasonic wave propagation in the upstream and downstream directions, first calculate the measured average flow velocity, then calculate the pipe flow area, and finally obtain the basic flow rate; Frequency difference method: The calculation is based on the frequency difference of ultrasonic waves propagating in the upstream and downstream directions. The flow velocity and frequency difference are linearly related.

[0037] If the comprehensive correction method is matched, the flow type is extracted, and the basic flow value is calculated based on the calculation logic corresponding to different flow types. Laminar flow using time difference method, turbulent flow using frequency difference method, and transitional flow using time difference method.

[0038] Based on the basic flow rate value, combined with the flow pattern correction coefficient, gas content correction coefficient, and interference correction coefficient converted from the flow pattern type, gas content, and impurity interference level, the final flow rate value is output as the flow measurement result. That is, the final flow rate value is calculated using a formula. ;in This is the base flow value.

[0039] A set of flow regime correction coefficients is set for laminar and turbulent flow types respectively; the flow regime correction coefficient for laminar flow is 1.05 to compensate for the error of low near-wall velocity in laminar flow, and the flow regime correction coefficient for turbulent flow is 0.98 to compensate for the error of high center velocity in turbulent flow; if the flow regime type is transitional flow, the three sets of coefficient intervals corresponding to the flow regime determination coefficient are retrieved, the highest value in the coefficient interval corresponding to laminar flow and the lowest value in the coefficient interval corresponding to turbulent flow are retrieved, and the absolute difference between the flow regime determination coefficient and the highest and lowest values ​​is calculated respectively. The two sets of absolute differences are compared, and the flow regime type with the lower absolute difference is selected as the replacement type of transitional flow. Extract the gas content characteristic coefficient and interference characteristic coefficient corresponding to the gas content and impurity interference level, respectively, and convert them into gas content correction coefficient and interference correction coefficient using the mapping rules of gas content characteristic coefficient-gas content correction coefficient and interference characteristic coefficient-interference correction coefficient.

[0040] Mapping rule description: Define the coefficient intervals corresponding to the gas-containing characteristic coefficients, and each coefficient interval corresponds to a set of gas-containing correction coefficients; the range of the gas-containing correction coefficients is limited to 0.85-1.0, where the lower the gas-containing characteristic coefficient, the higher the probability of matching 1.0; Define the coefficient intervals corresponding to the interference feature coefficients, and each coefficient interval corresponds to a set of interference correction coefficients; the range of the interference correction coefficients is limited to 0.73-1.0, where the lower the interference feature coefficient, the higher the probability of matching 1.0; The basic flow rate value is calculated based on an algorithm (time difference method / frequency difference method) under ideal pure fluid conditions. It does not take into account the actual impact of gas content and impurities. High gas content and high interference will cause the basic flow rate value to deviate from the true value in two key dimensions, and the deviation direction is larger in both cases.

[0041] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0042] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as 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, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0043] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0044] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0045] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0046] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0047] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0048] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0049] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An ultrasonic flow meter based on an AI engine, characterized in that, Includes an AI processing module, which is built-in: Parameter storage unit: stores basic pipeline parameters, basic fluid parameters, and flow calculation logic library; Signal processing unit: acquires the original ultrasonic wave signal, filters, amplifies, and performs impedance matching on it, and then outputs the time domain parameters, frequency domain parameters, and ultrasonic wave propagation characteristic parameters of the ultrasonic signal; AI Analysis Unit: Analyzes the time-domain parameters, frequency-domain parameters, and ultrasonic propagation characteristic parameters of the output ultrasonic signal, combines them with the basic parameters in the parameter storage unit, completes the identification of flow type, gas content, and impurity interference level, and determines the flow calculation logic based on the identification results; Traffic output unit: Calls the selected traffic calculation logic to complete the traffic calculation and outputs the traffic measurement results.

2. The ultrasonic flow meter based on an AI engine according to claim 1, characterized in that: The pipeline basic parameters, fluid basic parameters, and flow calculation logic library specifically include: Pipeline basic parameters include pipe diameter, wall thickness, transducer spacing, and angle; The basic fluid parameters include preset temperature, viscosity, standard velocity of sound of pure fluid, fluid density, and pure fluid attenuation coefficient. The flow calculation logic library includes time difference method, frequency difference method and comprehensive correction method; The time-domain parameters, frequency-domain parameters, and ultrasonic propagation characteristics parameters of ultrasonic signals specifically include: The time-domain parameters of an ultrasound signal include signal amplitude, waveform distortion coefficient, and effective signal duration. Ultrasonic signal frequency domain parameters include harmonic component ratio, frequency domain clutter intensity, and clutter echo number; Ultrasonic propagation characteristics include signal attenuation coefficient, sound velocity, and round-trip time difference of ultrasonic signal.

3. The ultrasonic flow meter based on an AI engine according to claim 2, characterized in that: Logic for identifying flow type; Flow patterns include laminar flow, transitional flow, and turbulent flow; The round-trip time difference, sound velocity, and harmonic component ratio of the ultrasonic signal are retrieved for x consecutive sampling periods; x>5; after calculation using the standard deviation formula, the time fluctuation value, sound velocity stability, and harmonic stability are output. For the signal amplitude within x sampling periods, the standard deviation and mean are calculated respectively to obtain the amplitude standard deviation and the average amplitude. The amplitude stability is obtained by calculating the ratio with the amplitude standard deviation as the numerator and the average amplitude as the denominator. After comprehensively processing the time fluctuation value, sound velocity stability, harmonic stability and amplitude stability by weighted fusion, the flow characteristic coefficient is output. The system retrieves pipe diameter, fluid viscosity, and standard sound velocity of the pure fluid, and calculates the average flow velocity using ultrasonic signals. After verification based on flow characteristic coefficients and Reynolds number, it outputs the flow type. Using a pre-constructed mapping rule between Reynolds number and flow regime verification coefficient, the calculated Reynolds number is converted into a flow regime verification coefficient and then multiplied by the flow regime characteristic coefficient to obtain the flow regime determination coefficient. Three sets of coefficient intervals are preset to correspond to the flow regime determination coefficients, and each set of coefficient intervals corresponds to a flow regime type; the flow regime determination coefficients are matched with the corresponding coefficient intervals to determine the flow regime type.

4. The ultrasonic flow meter based on an AI engine according to claim 3, characterized in that: The calculation logic for gas content; Retrieve the signal attenuation coefficient for x consecutive cycles, calculate the difference between it and the pure fluid attenuation coefficient, and take the average value to obtain the attenuation coefficient increment. Retrieve the duration of the effective signal within x consecutive periods, and calculate the proportion of the duration of the effective signal in the total sampling time to obtain the proportion of the effective signal. Count the number of clutter echoes over x consecutive periods and sum them up to obtain the total clutter count; After comprehensively processing the attenuation coefficient increment, effective signal ratio, and total clutter using weighted fusion, the gas-bearing characteristic coefficient is output. By utilizing a pre-constructed mapping rule between gas-bearing characteristic coefficients and gas-bearing percentage, the calculated gas-bearing characteristic coefficients are transformed into gas-bearing percentage.

5. The ultrasonic flow meter based on an AI engine according to claim 4, characterized in that: The logic for determining the level of impurity interference; The similarity between the measured waveform and the standard pure fluid waveform over x consecutive periods is retrieved, and the average value is calculated before outputting the waveform distortion coefficient. The power values ​​falling outside the set effective frequency bandwidth within x consecutive periods are summed to obtain the clutter power; the proportion of clutter power in the total signal power is calculated to obtain the clutter intensity proportion. Calculate the average signal-to-noise ratio of each group within x consecutive periods, and output the overall signal-to-noise ratio. The standard number of peak values ​​within a single period is preset. The measured time-domain waveform within a single period is analyzed. If the amplitude of a certain sampling point is greater than the amplitude of the three sampling points before and after it, and is also greater than the preset reference amplitude, it is determined to be a valid peak value. Periods in which the number of valid peak values ​​is less than the standard number of peak values ​​are marked as lost periods. Calculate the percentage of lost periods in x, as the peak loss ratio; After comprehensively processing the waveform distortion coefficient, clutter intensity ratio, overall signal-to-noise ratio, and peak loss ratio using weighted fusion, the interference characteristic coefficient is output. Five sets of coefficient ranges are set for the interference characteristic coefficients, and each set of coefficient ranges corresponds to an interference level. The interference levels are divided into 1-5 levels. The interference characteristic coefficients are matched with the corresponding coefficient ranges to determine the interference level.

6. The ultrasonic flow meter based on an AI engine according to claim 5, characterized in that: The identification results determine the selected traffic calculation logic; The flow regime type, gas content, and impurity interference level are integrated and retrieved into the flow calculation logic library. The flow calculation logic library has pre-set flow calculation logic corresponding to the range of gas content and impurity interference level under different flow regime types.

7. The ultrasonic flow meter based on an AI engine according to claim 6, characterized in that: The specific steps for flow calculation; : Retrieve the matched flow calculation logic, flow type, gas content, and impurity interference level; The system uses the matched flow calculation logic as its core, substitutes the synchronous measured ultrasonic parameters, pipeline and fluid basic parameters, executes the standard algorithm of the flow calculation logic, and calculates the basic flow value. Based on the basic flow rate value, combined with the flow regime correction coefficient, gas content correction coefficient, and interference correction coefficient converted from the flow regime type, gas content, and impurity interference level, the final flow rate value is output as the flow measurement result.

8. The ultrasonic flow meter based on an AI engine according to claim 7, characterized in that: If the comprehensive correction method is matched in the process, the flow type is extracted, and the basic flow value is calculated based on the calculation logic set for different flow types.

9. An ultrasonic flow meter based on an AI engine according to claim 7, characterized in that: The process of determining the flow regime correction coefficient, gas content correction coefficient, and disturbance correction coefficient in the steps; Set a set of flow regime correction coefficients for laminar and turbulent flow types respectively; If the flow type is transitional flow, then retrieve the three sets of coefficient intervals corresponding to the flow determination coefficient, retrieve the highest value in the coefficient interval corresponding to laminar flow and the lowest value in the coefficient interval corresponding to turbulent flow, calculate the absolute difference between the flow determination coefficient and the highest and lowest values ​​respectively, compare the two sets of absolute differences, and select the flow type with the lower absolute difference as the replacement type of transitional flow; Extract the gas content characteristic coefficient and interference characteristic coefficient corresponding to the gas content and impurity interference level, respectively, and convert them into gas content correction coefficient and interference correction coefficient using the mapping rules of gas content characteristic coefficient-gas content correction coefficient and interference characteristic coefficient-interference correction coefficient.

Images