Mixed medium flow measurement method and device, computer equipment and medium

The method uses a machine learning model to identify and calculate the flow of mixed media in complex systems, enhancing precision and adaptability in chemical and petrochemical applications.

CN119085769AInactive Publication Date: 2024-12-06SHANGHAI INVESTIGATION DESIGN & RES INST CO LTD
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202411588361.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing technologies face challenges in accurately measuring the flow of mixed media in complex pipeline systems, particularly in chemical and petrochemical fields, due to medium mixing, which affects measurement precision.

Method used

A mixed medium flow measurement method utilizing a trained machine learning model to identify the type and proportion of each medium in a fluid, calculating the flow of each medium based on fluid characteristic data such as density, mass flow, volume flow, and temperature, and integrating data from multiple sensors to enhance accuracy.

Benefits of technology

The method achieves high-precision measurement of mixed medium flow, improving accuracy and adaptability to complex fluid environments, supporting applications like flow control and chemical reaction monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085769A_ABST
    Figure CN119085769A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of flow detection, and discloses a mixed medium flow measurement method and device, computer equipment and a medium, and the method comprises the steps: obtaining the collected fluid characteristic data of a to-be-measured fluid, inputting the fluid characteristic data into a trained machine learning model, and obtaining the fluid characteristic data of the to-be-measured fluid; the types of media contained in the to-be-measured fluid are recognized through the machine learning model, the proportion of the media of all the types in the to-be-measured fluid is determined, and the flow of the media of all the types in the to-be-measured fluid is calculated according to the proportion of the media of all the types and the fluid characteristic data. And high-precision measurement of the mixed medium flow is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of flow detection, and in particular to a mixed medium flow measurement method, device, computer equipment and medium. Background Art

[0002] When measuring flow in complex pipeline systems such as chemical production and petrochemical fields, it is often the case that fluids of multiple media appear in the pipeline at the same time.

[0003] At present, when dealing with fluid flow measurement of multiple media, traditional technologies usually face the impact of medium mixing on flow measurement accuracy and are unable to effectively distinguish and measure the flow of different media. Especially in the chemical and petrochemical fields, complex media mixing poses a challenge to accurate measurement.

[0004] Therefore, a new technology is urgently needed to achieve high-precision measurement of mixed medium flow. Summary of the invention

[0005] In view of this, the present invention provides a mixed medium flow measurement method, device, computer equipment and medium to solve the technical problem that the prior art cannot achieve high-precision measurement of mixed medium flow.

[0006] In a first aspect, the present invention provides a mixed medium flow measurement method, the method comprising: acquiring fluid characteristic data of the fluid to be measured; inputting the fluid characteristic data into a trained machine learning model, identifying the medium type contained in the fluid to be measured and determining the proportion of each type of medium in the fluid to be measured through the machine learning model; and calculating the flow of each type of medium in the fluid to be measured based on the proportion of each type of medium and the fluid characteristic data.

[0007] The mixed medium flow measurement method provided by the present invention obtains the collected fluid characteristic data of the fluid to be measured, inputs the fluid characteristic data into a trained machine learning model, identifies the medium type contained in the fluid to be measured and determines the proportion of each type of medium in the fluid to be measured through the machine learning model, calculates the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data, can identify the medium type contained in the fluid to be measured and determine the proportion of each type of medium in the fluid to be measured based on the machine learning model, and then calculate the flow of each type of medium, can adapt to complex fluid environments, realize high-precision measurement of mixed medium flow, and then provide data support for downstream applications such as flow control, chemical reaction monitoring, etc.

[0008] Optionally, the fluid characteristic data includes collected fluid density data, fluid mass flow data, fluid volume flow data and temperature data; the fluid characteristic data is input into a trained machine learning model, and the medium type contained in the fluid to be tested is identified through the machine learning model and the proportion of each type of medium in the fluid to be tested is determined, including: inputting the fluid density data, the fluid mass flow data, the fluid volume flow data and the temperature data into the trained machine learning model respectively; the fluid density flow data is calculated according to the fluid mass flow data and the fluid volume flow data by the machine learning model; the specific heat capacity data of the fluid to be tested is calculated according to the temperature data by the machine learning model; the medium type contained in the fluid to be tested is identified according to the fluid density data, the fluid density flow data and the specific heat capacity data by the machine learning model and the proportion of each type of medium in the fluid to be tested.

[0009] In this method, the type of medium contained in the fluid to be tested is identified by integrating multiple features such as fluid density data, fluid mass flow data, fluid volume flow data and temperature data, and the proportion of each type of medium in the fluid to be tested is determined, which helps to improve the accuracy of identification. By integrating these data using a machine learning model, the density flow and specific heat capacity of the fluid can be more accurately calculated, providing a more reliable basis for medium type identification.

[0010] Optionally, the machine learning model is used to identify the type of medium contained in the fluid to be tested and determine the proportion of each type of medium in the fluid to be tested based on the fluid density data, the fluid density flow data and the specific heat capacity data, including: extracting the data feature sequence of the fluid density data, the fluid density flow data and the specific heat capacity data through the machine learning model; calculating the difference between the data feature sequence and the standard feature sequence under each preset medium combination; and determining the type of medium contained in the fluid to be tested and the proportion of each type of medium based on the medium combination with the smallest difference.

[0011] In this manner, the accuracy of medium type identification is improved by calculating the difference from the standard feature sequence and selecting the medium combination with the smallest difference.

[0012] Optionally, the flow rate of each type of medium in the fluid to be measured is calculated according to the proportion of each type of medium and the fluid characteristic data, including: calculating the fluid mass flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid mass flow rate data; calculating the fluid volume flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid volume flow rate data, wherein the flow rate of the medium includes the fluid mass flow rate and the fluid volume flow rate.

[0013] In this way, the flow rate of each medium can be calculated separately according to the proportion of the medium and the mass flow rate and volume flow rate data of the fluid, which helps to refine the management and optimize the fluid flow data.

[0014] Optionally, the fluid characteristic data also includes pressure data; correspondingly, after identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested based on the fluid density data, the fluid density flow data and the specific heat capacity data through the machine learning model, it also includes: judging whether there are solids in the fluid to be tested based on the pressure data.

[0015] In this method, the presence of solids in the fluid is determined by pressure data, which is particularly important for processing fluids containing solid particles, as it can avoid equipment damage and improve processing efficiency.

[0016] Optionally, acquiring the collected fluid characteristic data of the fluid to be measured includes: receiving original characteristic data of the fluid to be measured collected by multiple sensors; and fusing the original characteristic data to obtain the fluid characteristic data.

[0017] In this way, by receiving and fusing data from multiple sensors, the accuracy and reliability of the data can be improved and the errors that may be caused by a single sensor can be reduced.

[0018] Optionally, after acquiring the collected fluid characteristic data of the fluid to be tested, the method further includes: performing data cleaning and normalization processing on the fluid characteristic data.

[0019] In this way, noise and outliers can be removed through data cleaning and normalization, ensuring the quality of data input into the machine learning model, thereby improving the model's prediction accuracy. Normalization helps eliminate differences between data of different dimensions, making model training more efficient, and also helps improve the model's generalization ability.

[0020] In the second aspect, the present invention provides a mixed medium flow measurement device, which includes: a characteristic data acquisition module, used to acquire the collected fluid characteristic data of the fluid to be measured; a medium identification module, used to input the fluid characteristic data into a trained machine learning model, and identify the medium type contained in the fluid to be measured through the machine learning model and determine the proportion of each type of medium in the fluid to be measured; a flow calculation module, used to calculate the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data.

[0021] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the mixed medium flow measurement method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the mixed medium flow measurement method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 is a schematic diagram of a flow chart of mixed medium flow measurement according to an embodiment of the present invention; Figure 2 is a flow chart of another mixed medium flow measurement method according to an embodiment of the present invention; Figure 3 is a structural block diagram of a mixed medium flow measurement device according to an embodiment of the present invention; Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] A mixed medium flow measurement method in an embodiment of the present invention aims to provide an efficient and accurate mixed medium flow measurement solution, which can be applied in scenarios such as chemical production and petrochemical industry. When applied to chemical production, it can improve the accuracy of flow measurement of various media in chemical production. When applied to the petrochemical industry, it can be suitable for flow measurement of mixed medium fluids in the petrochemical field, or industrial pipeline systems, and can optimize flow measurement and medium identification in complex pipeline systems.

[0027] According to an embodiment of the present invention, an embodiment of a mixed medium flow measurement method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In an embodiment of the present invention, a mixed medium flow measurement method is provided, which can be used in computers, servers, etc. Figure 1 : is a flow chart of a mixed medium flow measurement method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps: Step S101, acquiring the fluid characteristic data of the fluid to be tested.

[0029] Specifically, the fluid to be measured is a mixed medium, that is, it includes multiple media, and different media have different properties, such as density, specific heat capacity, conductivity, etc.

[0030] Fluid characteristic data includes the following information: Physical properties of fluids: such as density, viscosity, conductivity, refractive index, speed of sound, etc.

[0031] Environmental parameters: such as temperature, pressure, etc., which affect the behavior of the fluid.

[0032] Dynamic data: data streams such as mass flow, volume flow, temperature, etc. collected by the sensor. Mass flow refers to the mass of the fluid passing through the sensor cross section per unit time, usually expressed in kilograms per second (kg / s) or other mass units, which can directly measure the mass of the fluid passing through the sensor.

[0033] In one example, a thermal mass flow sensor is used to measure mass flow. The thermal mass flow sensor determines the mass flow by measuring the heat transfer characteristics of the fluid. The working principle is to heat the sensor element, and when the fluid flows through, it will take away some of the heat. Based on the change in sensor temperature, the system can calculate the mass flow rate passing through. The thermal mass flow sensor has a simple structure and low cost, and is suitable for measuring low flow rates or trace fluids.

[0034] The corresponding fluid characteristic data is collected by the sensor. For example, the density of the fluid is collected by the density sensor, and the density of the fluid directly reflects the physical properties of the fluid. The mass flow rate information of the fluid is collected by the mass flow sensor. The volume flow rate information of the fluid is collected by the volume flow sensor. The temperature of the fluid is collected by the temperature sensor, and the fluid temperature is one of the key influencing parameters. The pressure of the fluid is collected by the pressure sensor, and the pressure is closely related to the fluid characteristics.

[0035] The physical properties of the fluid can be obtained by direct acquisition or by calculation based on the acquired data.

[0036] Step S102, input the fluid characteristic data into the trained machine learning model, identify the medium type contained in the fluid to be tested through the machine learning model and determine the proportion of each type of medium in the fluid to be tested.

[0037] Specifically, according to the type and complexity of the medium in the actual application and the collected fluid characteristic data, different machine learning models such as neural network models or deep learning models can be selected to identify the fluid medium.

[0038] In one example, a machine learning model is constructed through a multi-layer neural network, which can capture the complex nonlinear characteristics of the fluid and is applicable to large amounts of data. It can accurately identify the type of medium contained in the fluid to be tested and determine the proportion of each type of medium in the fluid to be tested.

[0039] The machine learning model is trained by pre-collecting fluid characteristic data under different medium combinations and various proportions as training data. The supervised learning model relies on labeled fluid data for training, while the unsupervised learning model classifies by finding similarities in unlabeled data.

[0040] Among them, about 80% of the training data is used for training, and the remaining data is used to verify and test the accuracy of the model.

[0041] During the training process, the mean square error loss function is used to train the model parameters. The mean square error loss function is used to measure the average difference between the model's predicted value and the true value. The difference between each predicted value and the true value is added, and then the average is calculated. The model parameters are continuously optimized with the goal of minimizing the loss function.

[0042] Furthermore, cross-validation and hyperparameter tuning are used to optimize the machine learning model parameters.

[0043] The cross-validation method uses multiple validation models on different data subsets to ensure that the model has good generalization ability.

[0044] Hyperparameter tuning improves model performance by adjusting model hyperparameters (such as learning rate, regularization parameters, etc.).

[0045] After the machine learning model is trained, you only need to input the current fluid characteristic data to obtain the corresponding medium type and proportion of the medium. In addition, as more fluid data is collected and technology develops, the machine learning model can be updated regularly to improve its recognition ability and accuracy.

[0046] Step S103, calculating the flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data.

[0047] Specifically, the proportion of the medium may be a volume proportion or a mass proportion.

[0048] The fluid characteristic data includes the total mass flow rate and volume flow rate of the fluid to be measured. By multiplying the mass flow rate and volume flow rate by the corresponding proportion, the flow rate of each type of medium can be obtained.

[0049] After obtaining the flow rate of each type of medium in the fluid to be measured, the medium type and flow rate are displayed in real time through a visual interface. Users can view the flow data of various media and adjust the input parameter settings of the machine learning model in real time, such as the type of fluid characteristic data and the acquisition parameter settings of each sensor, to perform real-time dynamic compensation to ensure measurement accuracy.

[0050] The mixed medium flow measurement method provided by the present invention obtains the collected fluid characteristic data of the fluid to be measured, inputs the fluid characteristic data into a trained machine learning model, identifies the medium type contained in the fluid to be measured and determines the proportion of each type of medium in the fluid to be measured through the machine learning model, and calculates the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data. It can identify the medium type contained in the fluid to be measured and determine the proportion of each type of medium in the fluid to be measured based on the machine learning model, and then calculate the flow of each type of medium. It can adapt to complex fluid environments and achieve high-precision measurement of mixed medium flow, thereby providing data support for downstream applications such as flow control, chemical reaction monitoring, etc.

[0051] In some embodiments, step S101, obtaining the collected fluid characteristic data of the fluid to be tested, includes: Step S1011, receiving original characteristic data of the fluid to be tested collected by multiple sensors.

[0052] Step S1012, fusing the original characteristic data to obtain fluid characteristic data.

[0053] Specifically, for each type of characteristic data, multiple sensors are set to collect the original characteristic data at the same time, and then the fluid characteristic data is obtained by weighted accumulation or calculation of the average value of each original characteristic data.

[0054] For example, four temperature sensors are set to collect temperature data, and the collected temperature data are averaged, and the obtained average value is used as the fluid characteristic data of temperature.

[0055] The data from different sensors are integrated to reduce the error in the measurement of a single sensor and provide more accurate flow estimation. When the data of a certain sensor is lost or abnormal, the flow estimation accuracy can still be maintained at a high level by integrating the data of other sensors. It can also adapt to a variety of fluid media and working conditions in complex environments.

[0056] In this way, by receiving and fusing data from multiple sensors, the accuracy and reliability of the data can be improved and the errors that may be caused by a single sensor can be reduced.

[0057] In some embodiments, in step S101, after acquiring the collected fluid characteristic data of the fluid to be tested, the method further includes: Step S1013, performing data cleaning and normalization processing on the fluid characteristic data.

[0058] Specifically, in order to improve the accuracy of the machine learning model, the collected data needs to be cleaned and normalized.

[0059] Data cleaning involves removing noise, outliers, and missing data.

[0060] Normalization involves normalizing data of different dimensions to ensure that the feature data is within the same range, which helps in model training.

[0061] In this way, noise and outliers can be removed through data cleaning and normalization, ensuring the quality of data input into the machine learning model, thereby improving the model's prediction accuracy. Normalization helps eliminate differences between data of different dimensions, making model training more efficient, and also helps improve the model's generalization ability.

[0062] In an embodiment of the present invention, a mixed medium flow measurement method is provided, which can be used in computers, servers, etc. Figure 2 As shown, the method comprises the following steps: Step S201, obtain the collected fluid characteristic data of the fluid to be tested. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0063] Step S202: input the fluid characteristic data into the trained machine learning model, identify the medium type contained in the fluid to be tested and determine the proportion of each type of medium in the fluid to be tested through the machine learning model.

[0064] The fluid characteristic data includes the collected fluid density data, fluid mass flow data, fluid volume flow data and temperature data.

[0065] The above step S202 includes: Step S2021, input the fluid density data, fluid mass flow data, fluid volume flow data and temperature data into the trained machine learning model respectively.

[0066] S2022, calculating the fluid density flow data based on the fluid mass flow data and the fluid volume flow data through a machine learning model.

[0067] S2023, obtaining specific heat capacity data of the fluid to be tested by calculating the temperature data using a machine learning model.

[0068] S2024, identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested based on the fluid density data, fluid density flow data and specific heat capacity data through a machine learning model.

[0069] Specifically, after the machine learning model receives the input fluid density data, fluid mass flow data, fluid volume flow data and temperature data, it divides the fluid mass flow data by the fluid volume flow data to obtain the fluid density flow data.

[0070] The temperature difference of the temperature data at different time points is calculated, and the pre-calibrated absorbed heat is divided by the temperature difference to obtain the specific heat capacity data. The absorbed heat is obtained by pre-calibration, for example, the absorbed heat is calculated based on the temperature change of the known fluid medium within a set time period.

[0071] The machine learning model deduces the possible medium combinations in the fluid to be tested from multiple dimensions based on fluid density data, fluid density flow data and specific heat capacity data, including the types of media contained in the fluid to be tested and the proportion of each type of media.

[0072] In one example, the machine learning model first infers possible medium combinations based on fluid density data, taking advantage of the fact that different fluid media have different fluid densities. It then further infers possible medium combinations based on fluid density flow data, taking advantage of the fact that different fluid media have different density flow rates. Finally, the specific heat capacity data is combined to infer possible medium combinations by taking advantage of the fact that different fluid media have different specific heat capacities. The entire inference process is combined to obtain the medium combination with the highest probability, that is, to determine the medium types contained in the fluid to be tested and the proportion of each type of medium.

[0073] In this method, the type of medium contained in the fluid to be tested is identified by integrating multiple features such as fluid density data, fluid mass flow data, fluid volume flow data and temperature data, and the proportion of each type of medium in the fluid to be tested is determined, which helps to improve the accuracy of identification. By combining these data with a machine learning model, the density flow and specific heat capacity of the fluid can be calculated more accurately, providing a more reliable basis for medium type identification.

[0074] Further, S2024, identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested based on the fluid density data, the fluid density flow data and the specific heat capacity data through a machine learning model, including: S20241, extracting data feature sequences of fluid density data, fluid density flow data and specific heat capacity data through machine learning models.

[0075] S20242, calculating the difference between the data feature sequence and the preset standard feature sequence under each medium combination.

[0076] S20243, determining the types of media contained in the fluid to be tested and the proportion of each type of media based on the medium combination with the smallest difference.

[0077] Specifically, each medium combination includes the medium types contained in the fluid to be tested and the proportion of each type of medium.

[0078] The machine learning model uses a neural network classification model to obtain the fluid density, fluid density flow rate and specific heat capacity under each medium combination through calibration, and constructs a standard feature sequence based on these data.

[0079] During real-time detection, a data feature sequence is constructed based on the real-time acquired fluid density data, fluid density flow data and specific heat capacity data, and then the mean of the difference between the data feature sequence and the standard feature sequence under each preset medium combination is calculated, and the medium combination with the smallest mean is taken as the combination corresponding to the fluid to be tested, thereby determining the medium types contained in the fluid to be tested and the proportion of each type of medium.

[0080] In this manner, the accuracy of medium type identification is improved by calculating the difference from the standard feature sequence and selecting the medium combination with the smallest difference.

[0081] Step S203, calculating the flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data.

[0082] Specifically, the above step S203 includes: Step S2031, calculating the fluid mass flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid mass flow rate data.

[0083] Step S2032, calculating the fluid volume flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid volume flow rate data, wherein the flow rate of the medium includes the fluid mass flow rate and the fluid volume flow rate.

[0084] The proportion of each type of medium includes volume proportion and mass proportion. The fluid mass flow rate data and fluid volume flow rate data are collected by sensors. The data collected by the sensors are the fluid mass flow rate and fluid volume flow rate of the fluid to be measured, that is, the mixed medium fluid. The fluid mass flow rate and fluid volume flow rate are multiplied by the corresponding mass proportion and volume proportion respectively to obtain the fluid mass flow rate and fluid volume flow rate of each type of medium.

[0085] In this way, the flow rate of each medium can be calculated separately according to the proportion of the medium and the mass flow rate and volume flow rate data of the fluid, which helps to refine the management and optimize the fluid flow data.

[0086] In some embodiments, the fluid characteristic data also includes pressure data. After S2024 uses a machine learning model to identify the type of medium contained in the fluid to be tested based on the fluid density data, the fluid density flow data and the specific heat capacity data and determines the proportion of each type of medium in the fluid to be tested, it also includes: S2025, judging whether there are solids in the fluid to be tested based on the pressure data.

[0087] Specifically, when the pressure data is greater than a set pressure threshold for a period of time, it is determined that solids exist in the fluid to be tested.

[0088] In this method, the presence of solids in the fluid is determined by pressure data, which is particularly important for processing fluids containing solid particles, as it can avoid equipment damage and improve processing efficiency.

[0089] A mixed medium flow measurement in an embodiment of the present invention can accurately distinguish different medium types in the fluid to be measured, measure the flow of multiple media at the same time, and adapt to complex fluid environments.

[0090] Use machine learning models to identify media types and proportions in real time to improve measurement accuracy.

[0091] By fusing multiple sensor data, the machine learning model can improve the accuracy of real-time identification, thereby optimizing the flow estimation results.

[0092] Improve measurement accuracy by adjusting machine learning model settings in real time based on media type and flow changes.

[0093] In the embodiments of the present invention, a mixed medium flow measurement device is also provided, which is used to implement the above embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0094] The embodiment of the present invention provides a mixed medium flow measurement device, such as Figure 3 As shown, including: The characteristic data acquisition module 301 is used to acquire the fluid characteristic data of the fluid to be tested; The medium identification module 302 is used to input the fluid characteristic data into the trained machine learning model, identify the medium type contained in the fluid to be tested through the machine learning model and determine the proportion of each type of medium in the fluid to be tested; The flow calculation module 303 is used to calculate the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data.

[0095] The mixed medium flow measurement device provided by the present invention obtains the collected fluid characteristic data of the fluid to be measured, inputs the fluid characteristic data into a trained machine learning model, identifies the medium type contained in the fluid to be measured and determines the proportion of each type of medium in the fluid to be measured through the machine learning model, and calculates the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data. It can identify the medium type contained in the fluid to be measured and determine the proportion of each type of medium in the fluid to be measured based on the machine learning model, and then calculate the flow of each type of medium. It can adapt to complex fluid environments and achieve high-precision measurement of mixed medium flow, thereby providing data support for downstream applications such as flow control, chemical reaction monitoring, etc.

[0096] In some optional embodiments, the fluid characteristic data includes collected fluid density data, fluid mass flow data, fluid volume flow data, and temperature data; The medium identification module 302 includes: A data input module, used to input fluid density data, fluid mass flow data, fluid volume flow data and temperature data into the trained machine learning model respectively; A density flow calculation module, used to calculate the fluid density flow data according to the fluid mass flow data and the fluid volume flow data through a machine learning model; A specific heat capacity calculation module is used to calculate the specific heat capacity data of the fluid to be tested based on the temperature data through a machine learning model; The type proportion identification module is used to identify the type of medium contained in the fluid to be tested and determine the proportion of each type of medium in the fluid to be tested based on fluid density data, fluid density flow data and specific heat capacity data through a machine learning model.

[0097] In some optional implementations, the type proportion identification module includes: Feature extraction module, used to extract data feature sequences of fluid density data, fluid density flow data and specific heat capacity data through machine learning models; A difference calculation module, used to calculate the difference between the data feature sequence and the preset standard feature sequence under each medium combination; The difference confirmation module is used to determine the medium type contained in the fluid to be tested and the proportion of each type of medium based on the medium combination with the smallest difference.

[0098] In some optional implementations, the flow calculation module 303 includes: A mass flow calculation module is used to calculate the fluid mass flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid mass flow data; The volume flow calculation module is used to calculate the fluid volume flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid volume flow data, wherein the flow of the medium includes the fluid mass flow and the fluid volume flow.

[0099] In some optional implementations, the fluid characteristic data further includes pressure data; and the mixed medium flow measurement further includes: The solid identification module is used to determine whether there are solids in the fluid to be tested based on the pressure data.

[0100] In some optional implementations, the feature data acquisition module 301 includes: A raw data receiving module, used for receiving raw characteristic data of the fluid to be tested collected by multiple sensors; The data fusion module is used to fuse the original characteristic data to obtain fluid characteristic data.

[0101] In some optional implementations, the feature data acquisition module 301 further includes: The preprocessing module is used to clean and normalize the fluid characteristic data.

[0102] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0103] The mixed medium flow measurement device in the embodiment of the present invention is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0104] An embodiment of the present invention further provides a computer device having the mixed medium flow measurement device of the above embodiment.

[0105] See also Figure 4 , Figure 4is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0106] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0107] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0108] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0110] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0111] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0112] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0113] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A mixed medium flow measurement method, characterized in that: include: Acquiring the collected fluid characteristic data of the fluid to be tested; Inputting the fluid characteristic data into a trained machine learning model, identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested through the machine learning model; Calculating the flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data; Wherein, the fluid characteristic data includes collected fluid density data, fluid mass flow data, fluid volume flow data and temperature data; Inputting the fluid characteristic data into a trained machine learning model, identifying the medium type contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested by the machine learning model, including: Inputting the fluid density data, the fluid mass flow data, the fluid volume flow data and the temperature data into the trained machine learning model respectively; The fluid density flow data is calculated by the machine learning model according to the fluid mass flow data and the fluid volume flow data; Calculating the specific heat capacity data of the fluid to be measured according to the temperature data using the machine learning model; Identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested according to the fluid density data, the fluid density flow data and the specific heat capacity data through the machine learning model; Calculating the flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data includes: Calculate the fluid mass flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid mass flow rate data; Calculating the fluid volume flow rate of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid volume flow rate data, wherein the flow rate of the medium includes the fluid mass flow rate and the fluid volume flow rate; The fluid mass flow rate data and fluid volume flow rate data are collected by sensors. The data collected by the sensors are the fluid mass flow rate and fluid volume flow rate of the fluid to be measured, that is, the mixed medium fluid. The fluid mass flow rate and fluid volume flow rate are multiplied by the corresponding mass proportion and volume proportion respectively to obtain the fluid mass flow rate and fluid volume flow rate of each type of medium.

2. The mixed medium flow measurement method according to claim 1, characterized in that: Identifying the type of medium contained in the fluid to be tested and determining the proportion of each type of medium in the fluid to be tested by the machine learning model according to the fluid density data, the fluid density flow data and the specific heat capacity data, including: Extracting a data feature sequence of the fluid density data, the fluid density flow data, and the specific heat capacity data through the machine learning model; Calculating the difference between the data feature sequence and the preset standard feature sequence under each medium combination; The types of media contained in the fluid to be tested and the proportion of each type of media are determined based on the medium combination with the smallest difference.

3. The mixed medium flow measurement method according to claim 1, characterized in that: The fluid characteristic data also includes pressure data; Correspondingly, after identifying the medium type contained in the fluid to be measured according to the fluid density data, the fluid density flow data and the specific heat capacity data through the machine learning model and determining the proportion of each type of medium in the fluid to be measured, it also includes: It is determined whether there is solid in the fluid to be tested according to the pressure data.

4. The mixed medium flow measurement method according to claim 1, characterized in that: Obtain the collected fluid characteristic data of the fluid to be tested, including: Receiving original characteristic data of the fluid to be measured collected by multiple sensors; The original characteristic data is subjected to data fusion to obtain the fluid characteristic data.

5. The mixed medium flow measurement method according to claim 1, characterized in that: After acquiring the fluid characteristic data of the fluid to be tested, the method further includes: The fluid characteristic data is cleaned and normalized.

6. A mixed medium flow measurement device, characterized in that include: A characteristic data acquisition module is used to acquire the collected fluid characteristic data of the fluid to be tested; A medium identification module, used to input the fluid characteristic data into a trained machine learning model, identify the medium type contained in the fluid to be tested through the machine learning model and determine the proportion of each type of medium in the fluid to be tested; The flow calculation module is used to calculate the flow of each type of medium in the fluid to be measured according to the proportion of each type of medium and the fluid characteristic data.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the mixed medium flow measurement method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the mixed medium flow measurement method according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Systems and methods for multiphase flow metering accounting for dissolved gas

    CN105928578A

  • Method and system for testing flow of homogeneous gas-liquid mixed two-phase flow based on ERT

    CN110108331A

  • Construction method of fluid type prediction model, and fluid type prediction method and device

    CN112862139A

  • Medium mass flow determination method and device, electronic equipment and storage medium

    CN115824336A

  • Intelligent gas flow monitoring method

    CN117606578A