High-temperature and high-pressure flow detection method and system based on bi-directional probe correlation

Abstract

The invention relates to the technical field of fluid detection, in particular to a high-temperature and high-pressure flow detection method and system based on bi-directional probe correlation, and the method comprises the steps: constructing a sensor detection unit in a to-be-detected fluid channel, obtaining a plurality of sensor data sets by using the sensor detection unit, and judging the direction of a target fluid according to the plurality of sensor data sets. The method comprises the steps of measuring real-time environment temperature and real-time environment pressure, obtaining a training data set, executing high-dimensional feature expansion on the training data set to obtain a training feature data set, training a neural network model by utilizing the training feature data set to obtain a sound velocity compensation model, and calculating the real-time environment temperature and the real-time environment pressure based on the real-time environment temperature, the real-time environment pressure and the sound velocity compensation model. And performing flow velocity compensation analysis on the to-be-detected fluid channel to obtain a target fluid flow velocity. According to the invention, the accuracy and the reliability of detecting the flowing direction and the flowing speed in a high-temperature and high-pressure environment can be improved.

Description

Technical Field

[0001] This invention relates to the field of fluid detection technology, and in particular to a high-temperature and high-pressure flow detection method and system based on bidirectional probes. Background Technology

[0002] Accurate measurement of fluid flow rate is of vital importance for industrial production, energy management, and safety assurance. For example, in fields such as petrochemicals, energy and power, and aerospace, the direction and velocity of fluid flow are key parameters for optimizing process flow, improving resource utilization efficiency, and ensuring the safe operation of systems. Therefore, developing a detection method that can accurately measure the direction and velocity of fluid flow has significant practical application value for improving industrial production efficiency, ensuring system safety, and reducing energy consumption.

[0003] Traditional techniques typically employ unidirectional probes or single-sensor-based measurement methods to detect fluid flow. While these methods can achieve basic flow measurement, they are significantly affected by environmental parameters (such as temperature and pressure). In high-temperature and high-pressure environments, environmental factors can easily affect the accuracy of flow rate measurement. Summary of the Invention

[0004] This invention provides a high-temperature and high-pressure flow detection method and system based on bidirectional probes, the main purpose of which is to improve the accuracy and reliability of detecting flow direction and flow velocity under high-temperature and high-pressure environments.

[0005] To achieve the above objectives, the present invention provides a high-temperature and high-pressure flow detection method based on bidirectional probe through-beams, comprising:

[0006] The system receives a fluid detection command, determines the fluid channel to be detected based on the fluid detection command, and constructs a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, a pressure sensor, and a temperature sensor.

[0007] An ultrasonic emission test was conducted using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, in which each sensor data set corresponds one-to-one with an ultrasonic sensor group.

[0008] Based on data sets from multiple sensors, the direction of the target fluid in the fluid channel to be detected is determined.

[0009] Using the pressure and temperature sensors in the sensor detection unit, environmental parameters of the fluid channel to be detected are measured to obtain real-time ambient temperature and real-time ambient pressure.

[0010] Acquire a training data set, wherein the training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity, wherein the training sound velocity is the sound velocity of ultrasound in the fluid under the training temperature and training pressure.

[0011] A high-dimensional feature expansion is performed on the training data set to obtain a training feature data set, wherein the training feature data set includes multiple training feature data sets, and the training feature data sets include: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity, and the high-dimensional feature expansion is a Taylor expansion.

[0012] The pre-acquired neural network model is trained using the training feature data set to obtain the sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure and the sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid flow velocity.

[0013] High-temperature and high-pressure flow detection is performed based on the direction and velocity of the target fluid using a bidirectional probe.

[0014] Optionally, the ultrasonic emission test is performed using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, including:

[0015] The ultrasonic sensor groups are extracted sequentially from the plurality of ultrasonic sensor groups. Each ultrasonic sensor group includes two ultrasonic sensors. The two ultrasonic sensors in the same ultrasonic sensor group are installed on both sides of the fluid channel to be detected, and the line connecting the two ultrasonic sensors has an angle of less than 90 degrees with the radial direction of the fluid channel to be detected.

[0016] An ultrasonic emission experiment was conducted using the ultrasonic sensor array to obtain a sensor data set.

[0017] By aggregating the sensor data sets corresponding to each ultrasonic sensor group in multiple ultrasonic sensor groups, multiple sensor data sets are obtained.

[0018] Optionally, the step of performing an ultrasonic emission test based on the ultrasonic sensor group to obtain a sensor data set includes:

[0019] According to the preset positive flow direction, one ultrasonic sensor in the ultrasonic sensor group is set as the transmitting sensor and the other ultrasonic sensor is set as the receiving sensor, wherein the direction in which the transmitting sensor emits ultrasonic waves to the receiving sensor is the positive flow direction.

[0020] Based on the preset number of transmissions and the preset transmission frequency, the transmitting sensor transmits ultrasonic waves to the receiving sensor, and records the ultrasonic transmission time group and ultrasonic reception time group in the ultrasonic transmission step, and calculates the propagation time difference group between the ultrasonic transmission time group and the ultrasonic reception time group.

[0021] The last transmission in the ultrasonic transmission step is identified, and the signal amplitude and signal-to-noise ratio of the ultrasonic signal received by the receiving sensor are detected in the last transmission.

[0022] By pairing the propagation time difference group, signal amplitude, and signal-to-noise ratio, a forward propagation data group is obtained;

[0023] The transmitting and receiving sensors are interchanged, and based on the interchanged transmitting and receiving sensors, the step of using the transmitting sensor to transmit ultrasonic waves to the receiving sensor is returned until a forward propagation data set is obtained again, and the forward propagation data set obtained after the interchange is recorded as the reverse propagation data set.

[0024] The forward propagation data set and the reverse propagation data set are paired to obtain the sensor data set.

[0025] Optionally, determining the direction of the target fluid in the fluid channel to be detected based on multiple sensor data sets includes:

[0026] Perform the following operations for each of the multiple sensor data sets:

[0027] Extract the forward propagation time difference group of the forward propagation data group in the sensor data set, and the reverse propagation time difference group of the reverse propagation data group in the sensor data set, respectively;

[0028] Based on the forward propagation time difference group and the reverse propagation time difference group, calculate the bidirectional time difference group, where the bidirectional time difference group includes multiple bidirectional time differences, and the bidirectional time difference is the difference between the forward propagation time difference and the corresponding reverse propagation time difference in the reverse propagation time difference group.

[0029] Calculate the two-way standard deviation and the two-way mean deviation of the two-way time difference group;

[0030] Calculate the data confidence level based on the two-way standard deviation, the forward propagation data set, and the backward propagation data set;

[0031] The bidirectional time mean difference and data confidence scores are summarized to obtain multiple bidirectional time mean differences and multiple data confidence scores. Based on the multiple bidirectional time mean differences and multiple data confidence scores, the direction of the target fluid is determined.

[0032] Optionally, calculating the data confidence level based on the bidirectional standard deviation, the forward propagation data set, and the backward propagation data set includes:

[0033] The forward signal amplitude and forward signal-to-noise ratio are extracted from the forward propagation data set, and the reverse signal amplitude and reverse signal-to-noise ratio are extracted from the reverse propagation data set.

[0034] Identify the maximum signal amplitude and maximum signal-to-noise ratio in multiple sensor data sets;

[0035] Calculate the confidence level of the data using the following formula:

[0036] ,

[0037] in, Indicates the confidence level of the data. This represents the average value between the forward signal-to-noise ratio and the reverse signal-to-noise ratio. Indicates the maximum signal-to-noise ratio. This represents the average value between the amplitude of the positive signal and the amplitude of the negative signal. Indicates the maximum signal amplitude. This represents the two-way standard deviation.

[0038] Optionally, determining the target fluid direction based on multiple bidirectional time average differences and multiple data confidence levels includes:

[0039] Based on multiple bidirectional time-mean differences and multiple data confidence levels, the confidence time difference is obtained using a preset weighted average formula, wherein the weighted average formula is expressed as:

[0040] ,

[0041] in, Indicates the confidence time difference. This indicates the number of two-way time mean differences among multiple two-way time mean differences, or the number of data confidence scores among multiple data confidence scores. This represents the first of multiple data confidence levels. Data confidence level, Represents the average difference of multiple bidirectional times. The average time difference in both directions;

[0042] Determine whether the confidence time difference is greater than the preset standard time difference;

[0043] If the confidence time difference is greater than the standard time difference, the target fluid direction is recorded as the preset reverse flow direction;

[0044] If the confidence time difference is not greater than the standard time difference, then the target fluid direction is recorded as the positive flow direction.

[0045] Optionally, the step of performing high-dimensional feature expansion on the training data set to obtain a training feature data set includes:

[0046] Temperature and pressure variables are defined, and a sound velocity linkage influence function is constructed based on these variables. The sound velocity linkage influence function is expressed as follows:

[0047] ,

[0048] in, This represents the influence function of sound speed linkage. Represents the natural constant. This indicates the preset temperature coefficient. Represents temperature variable. This indicates the preset pressure coefficient. Indicates the stress variable;

[0049] According to the preset number of expansions, the sound speed linkage influence function is subjected to Taylor expansion to obtain a high-dimensional feature variable set, wherein the high-dimensional feature variable set includes a temperature feature variable set and a pressure feature variable set, and the order of the Taylor expansion is the same as the number of expansions.

[0050] Training data is extracted sequentially from the training data set, and the training temperature and training pressure in the training data are substituted into the high-dimensional feature variable set to obtain the high-dimensional training feature set. The high-dimensional training feature set and the training sound velocity are paired to obtain the training feature data set. The high-dimensional training feature set includes: a high-dimensional temperature feature set and a high-dimensional pressure feature set.

[0051] The training feature data sets are aggregated to obtain a training feature data set, where each training feature data set corresponds one-to-one with a training data set.

[0052] Optionally, the step of performing flow velocity compensation analysis on the fluid channel to be detected based on real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model to obtain the target fluid flow velocity includes:

[0053] The ultrasonic sensor groups are extracted sequentially from multiple ultrasonic sensor groups, and the receiving frequency group of the ultrasonic sensor group is identified.

[0054] The mean frequency offset is calculated based on the receiving frequency group and the transmitting frequency, wherein the mean frequency offset is the average value of the difference between each receiving frequency and the transmitting frequency in the receiving frequency group;

[0055] Based on the frequency offset mean, real-time ambient temperature, real-time ambient pressure and sound velocity compensation model, flow velocity compensation calculation is performed to obtain the compensation fluid flow velocity.

[0056] The compensating fluid velocities are summarized to obtain multiple compensating fluid velocities. Based on the multiple compensating fluid velocities and the multiple data confidence levels, a weighted average is performed to obtain the target fluid velocity.

[0057] Optionally, the step of performing flow velocity compensation calculations based on the mean frequency offset, real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model to obtain the compensation fluid velocity includes:

[0058] Substituting the real-time ambient temperature and real-time ambient pressure into the sound speed compensation model, the compensated sound speed is obtained, wherein the compensated sound speed is the output value of the sound speed compensation model.

[0059] The radial angle between the line connecting the two ultrasonic sensors in the ultrasonic sensor group and the radial direction of the fluid channel to be detected was determined.

[0060] Based on the average frequency offset, transmission frequency, compensated sound velocity, and radial angle, the compensated flow velocity is calculated using the following formula:

[0061] ,

[0062] in, Indicates the compensation flow rate. Indicates the frequency offset mean. Indicates the speed of sound compensation. Indicates the transmission frequency. Represents the cosine function. Indicates the radial angle.

[0063] To achieve the above objectives, the present invention also provides a high-temperature and high-pressure flow detection system based on bidirectional probe through-beams, comprising:

[0064] The detection unit construction module is used to receive fluid detection commands, determine the fluid channel to be detected based on the fluid detection commands, and construct a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, pressure sensors, and temperature sensors.

[0065] The fluid direction detection module is used to conduct ultrasonic emission tests using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets. Each sensor data set corresponds one-to-one with an ultrasonic sensor group. Based on the multiple sensor data sets, the direction of the target fluid in the fluid channel to be detected is determined.

[0066] The training data acquisition module is used to measure environmental parameters of the fluid channel to be detected using the pressure sensor and temperature sensor in the sensor detection unit, to obtain real-time environmental temperature and real-time environmental pressure, and to acquire a training data set. The training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity. The training sound velocity is the sound velocity of ultrasonic waves in the fluid under the training temperature and training pressure.

[0067] The fluid velocity calculation module is used to perform high-dimensional feature expansion on the training data set to obtain a training feature data set. The training feature data set includes multiple training feature data sets, including: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity. The high-dimensional feature expansion is a Taylor expansion. The pre-acquired neural network model is trained using the training feature data set to obtain a sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid velocity.

[0068] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0069] Memory, storing at least one instruction;

[0070] The processor executes the instructions stored in the memory to implement the high-temperature and high-pressure flow detection method based on bidirectional probes as described above.

[0071] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the above-described high-temperature and high-pressure flow detection method based on bidirectional probe beams.

[0072] To address the problems described in the background section, this invention first constructs a sensor detection unit comprising an ultrasonic sensor array, a pressure sensor, and a temperature sensor. This provides the hardware foundation for subsequent multi-parameter measurement and comprehensive analysis, ensuring the comprehensiveness and accuracy of data acquisition. Next, a through-and-through emission test is conducted using the ultrasonic sensor array within the sensor detection unit. This step acquires bidirectional data on sound wave propagation in the fluid, thus providing a basis for subsequent fluid direction determination. Then, by analyzing the sensor data set, the fluid flow direction can be accurately determined. Furthermore, the introduction of numerical confidence level in this step further improves the accuracy of flow direction detection. This is achieved by real-time measurement of the ambient temperature in the fluid channel. Temperature and pressure can capture the dynamic changes of fluids under high temperature and high pressure conditions. These environmental parameters are important bases for sound velocity calculation, providing fundamental data for subsequent sound velocity compensation models and ensuring the accuracy of sound velocity calculations. Furthermore, high-dimensional feature extraction of the training data through Taylor expansion captures the nonlinear relationship between environmental parameters and sound velocity, thereby enhancing the adaptability of the sound velocity compensation model to complex environmental conditions and improving its accuracy. Finally, the trained sound velocity compensation model is used to compensate for real-time measured environmental parameters, thus correcting errors in sound velocity calculation. This step significantly improves the accuracy of flow velocity calculation, especially under complex conditions such as high temperature and high pressure. Therefore, this invention can improve the accuracy and reliability of detecting flow direction and flow velocity under high temperature and high pressure environments. Attached Figure Description

[0073] Figure 1 This is a schematic flowchart of a high-temperature and high-pressure flow detection method based on bidirectional probes provided in an embodiment of the present invention.

[0074] Figure 2 This is a functional block diagram of a high-temperature and high-pressure flow detection system based on bidirectional probes provided in an embodiment of the present invention;

[0075] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the high-temperature and high-pressure flow detection method based on bidirectional probes, according to an embodiment of the present invention.

[0076] Explanation of reference numerals in the attached figures:

[0077] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0078] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0079] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0080] This application provides a method for detecting high-temperature and high-pressure flow based on bidirectional probes. The executing entity of this method includes, but is not limited to, at least one electronic device configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or server device, and the software may be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0081] Reference Figure 1 The diagram shown is a schematic flowchart of a high-temperature and high-pressure flow detection method based on a bidirectional probe according to an embodiment of the present invention. In this embodiment, the high-temperature and high-pressure flow detection method based on a bidirectional probe includes:

[0082] S1. Receive a fluid detection command, determine the fluid channel to be detected based on the fluid detection command, and construct a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, pressure sensors, and temperature sensors.

[0083] Understandably, the fluid detection command refers to a manually initiated command to detect fluid in a specific fluid channel, where detection refers to detecting the flow direction and velocity of the fluid. The fluid channel to be detected refers to the specific fluid channel specified in the fluid detection command. The sensor detection unit refers to a detection device containing multiple sensors. The ultrasonic sensor group consists of two ultrasonic sensors, each capable of emitting and receiving ultrasonic waves. Ultrasonic sensors within the same group can receive ultrasonic waves emitted by another sensor within the same group. The pressure sensor and temperature sensor refer to sensors used to detect pressure and temperature, respectively. The pressure sensor and temperature sensor detect the pressure and temperature of the fluid in the fluid channel to be detected. They can be installed in the middle or at the inlet / outlet of the fluid channel; the specific installation location can be determined by professionals and is not specifically limited here.

[0084] S2. Perform ultrasonic emission tests using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, wherein each sensor data set corresponds one-to-one with an ultrasonic sensor group.

[0085] It is clear that the sensor data set refers to the collection of test data acquired by an ultrasonic sensor group in the sensor detection unit during an ultrasonic emission test. Each ultrasonic sensor in the sensor detection unit corresponds to one sensor data set.

[0086] In detail, the ultrasonic emission test is performed using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, including:

[0087] The ultrasonic sensor groups are extracted sequentially from the plurality of ultrasonic sensor groups. Each ultrasonic sensor group includes two ultrasonic sensors. The two ultrasonic sensors in the same ultrasonic sensor group are installed on both sides of the fluid channel to be detected, and the line connecting the two ultrasonic sensors has an angle of less than 90 degrees with the radial direction of the fluid channel to be detected.

[0088] An ultrasonic emission experiment was conducted using the ultrasonic sensor array to obtain a sensor data set.

[0089] By aggregating the sensor data sets corresponding to each ultrasonic sensor group in multiple ultrasonic sensor groups, multiple sensor data sets are obtained.

[0090] It should be explained that there are two ultrasonic sensors in the ultrasonic sensor group. These two ultrasonic sensors can emit and receive ultrasonic waves from each other, and the line connecting them has a specific angle with the radial direction of the fluid channel to be detected. This angle is an acute angle, and its specific size is set manually.

[0091] In detail, the ultrasonic emission test based on the ultrasonic sensor group to obtain the sensor data set includes:

[0092] According to the preset positive flow direction, one ultrasonic sensor in the ultrasonic sensor group is set as the transmitting sensor and the other ultrasonic sensor is set as the receiving sensor, wherein the direction in which the transmitting sensor emits ultrasonic waves to the receiving sensor is the positive flow direction.

[0093] Based on the preset number of transmissions and the preset transmission frequency, the transmitting sensor transmits ultrasonic waves to the receiving sensor, and records the ultrasonic transmission time group and ultrasonic reception time group in the ultrasonic transmission step, and calculates the propagation time difference group between the ultrasonic transmission time group and the ultrasonic reception time group.

[0094] The last transmission in the ultrasonic transmission step is identified, and the signal amplitude and signal-to-noise ratio of the ultrasonic signal received by the receiving sensor are detected in the last transmission.

[0095] By pairing the propagation time difference group, signal amplitude, and signal-to-noise ratio, a forward propagation data group is obtained;

[0096] The transmitting and receiving sensors are interchanged, and based on the interchanged transmitting and receiving sensors, the step of using the transmitting sensor to transmit ultrasonic waves to the receiving sensor is returned until a forward propagation data set is obtained again, and the forward propagation data set obtained after the interchange is recorded as the reverse propagation data set.

[0097] The forward propagation data set and the reverse propagation data set are paired to obtain the sensor data set.

[0098] Understandably, the positive flow direction refers to the manually set positive direction of fluid flow in the fluid channel to be detected. Optionally, the direction in which the transmitting sensor emits ultrasonic waves towards the receiving sensor is recorded as the positive flow direction. The transmitting sensor and receiving sensor refer to ultrasonic sensors that emit and receive ultrasonic waves, respectively. The number of emissions and emission frequency refer to the manually set number of times the transmitting sensor emits ultrasonic waves and the frequency of the ultrasonic waves at each emission. The ultrasonic emission time group includes multiple ultrasonic emission times, where the ultrasonic emission time refers to the time when the transmitting sensor emits ultrasonic waves, and the ultrasonic receiving time refers to the time when the receiving sensor receives ultrasonic waves. To ensure that the ultrasonic waves received by the receiving sensor come from the same group of transmitting sensors, the frequency of the received ultrasonic waves should be the aforementioned preset emission frequency. Pairing refers to placing different types of data into the same array. Interchange refers to using the receiving sensor and the transmitting sensor as the transmitting sensor and the receiving sensor, respectively. The propagation time difference refers to the difference between the ultrasonic emission time and the corresponding ultrasonic receiving time.

[0099] S3. Based on the data set of multiple sensors, determine the direction of the target fluid in the fluid channel to be detected.

[0100] Understandably, the target fluid direction refers to the flow direction of the fluid in the fluid channel to be detected. The target fluid direction includes two possibilities: the forward flow direction and the reverse flow direction.

[0101] Specifically, determining the direction of the target fluid in the fluid channel to be detected based on multiple sensor data sets includes:

[0102] Perform the following operations for each of the multiple sensor data sets:

[0103] Extract the forward propagation time difference group of the forward propagation data group in the sensor data set, and the reverse propagation time difference group of the reverse propagation data group in the sensor data set, respectively;

[0104] Based on the forward propagation time difference group and the reverse propagation time difference group, calculate the bidirectional time difference group, where the bidirectional time difference group includes multiple bidirectional time differences, and the bidirectional time difference is the difference between the forward propagation time difference and the corresponding reverse propagation time difference in the reverse propagation time difference group.

[0105] Calculate the two-way standard deviation and the two-way mean deviation of the two-way time difference group;

[0106] Calculate the data confidence level based on the two-way standard deviation, the forward propagation data set, and the backward propagation data set;

[0107] The bidirectional time mean difference and data confidence scores are summarized to obtain multiple bidirectional time mean differences and multiple data confidence scores. Based on the multiple bidirectional time mean differences and multiple data confidence scores, the direction of the target fluid is determined.

[0108] It is clear that the forward propagation time difference group refers to the propagation time difference group within the forward propagation data group, and the reverse propagation time difference group refers to the propagation time difference group within the reverse propagation data group. The bidirectional standard deviation and bidirectional mean time difference refer to the standard deviation and mean value of each bidirectional time difference in the bidirectional time difference group, respectively. The data confidence score is a numerical value representing the reliability of the sensor data set. The higher the reliability of the sensor data set, the larger the confidence score value. Since each sensor data set corresponds to an ultrasonic sensor group, and in actual operation, the ultrasonic sensor group may experience some deviation from the actual data due to environmental noise interference, hardware aging, calibration errors, and mutual interference between sensors, the confidence score needs to be calculated to measure the reliability of this data. This confidence score is then used to assign different weights to the sensor data sets acquired by different ultrasonic sensor groups when calculating the target flow direction, thereby improving the accuracy and reliability of the overall calculation results.

[0109] In detail, the calculation of data confidence based on the bidirectional standard deviation, the forward propagation data set, and the backward propagation data set includes:

[0110] The forward signal amplitude and forward signal-to-noise ratio are extracted from the forward propagation data set, and the reverse signal amplitude and reverse signal-to-noise ratio are extracted from the reverse propagation data set.

[0111] Identify the maximum signal amplitude and maximum signal-to-noise ratio in multiple sensor data sets;

[0112] Calculate the confidence level of the data using the following formula:

[0113] ,

[0114] in, Indicates the confidence level of the data. This represents the average value between the forward signal-to-noise ratio and the reverse signal-to-noise ratio. Indicates the maximum signal-to-noise ratio. This represents the average value between the amplitude of the positive signal and the amplitude of the negative signal. Indicates the maximum signal amplitude. This represents the two-way standard deviation.

[0115] It should be explained that the forward signal amplitude and forward signal-to-noise ratio (SNR) refer to the signal amplitude and SNR in the forward propagation data set, respectively, and the reverse signal amplitude and reverse SNR refer to the signal amplitude and SNR in the reverse propagation data set, respectively. The maximum signal amplitude and maximum SNR refer to the signal amplitude and SNR that appear most frequently in multiple sensor data sets, respectively. In the formula for calculating data confidence, the average value between the forward and reverse SNR is normalized using the maximum SNR, and the average value between the forward and reverse signal amplitudes is normalized using the maximum signal amplitude. The two-way standard deviation is also used to comprehensively evaluate data confidence. The purpose of this formula is to quantify data quality, thereby avoiding interference from low SNR, low amplitude, or highly fluctuating data in direction determination.

[0116] For example, a certain , , , , Then the data confidence level is: .

[0117] Specifically, determining the target fluid direction based on multiple bidirectional time average differences and multiple data confidence levels includes:

[0118] Based on multiple bidirectional time-mean differences and multiple data confidence levels, the confidence time difference is obtained using a preset weighted average formula, wherein the weighted average formula is expressed as:

[0119] ,

[0120] in, Indicates the confidence time difference. This indicates the number of two-way time mean differences among multiple two-way time mean differences, or the number of data confidence scores among multiple data confidence scores. This represents the first of multiple data confidence levels. Data confidence level, Represents the average difference of multiple bidirectional times. The average time difference in both directions;

[0121] Determine whether the confidence time difference is greater than the preset standard time difference;

[0122] If the confidence time difference is greater than the standard time difference, the target fluid direction is recorded as the preset reverse flow direction;

[0123] If the confidence time difference is not greater than the standard time difference, then the target fluid direction is recorded as the positive flow direction.

[0124] Understandably, the standard time difference refers to an artificially set constant, which measures the difference in the time it takes for ultrasound to propagate in the same ultrasonic sensor array under the forward and reverse flow directions. The reverse flow direction refers to the direction completely opposite to the forward flow direction. Because the fluid flow direction is affected by the ultrasound propagation direction: when the flow direction and the ultrasound propagation direction are the same, the fluid flow will result in a shorter ultrasound propagation time; when they are opposite, the fluid flow will inhibit the propagation of ultrasound, thus resulting in a longer ultrasound propagation time. The aforementioned confidence time difference can be understood as the difference between the propagation time of ultrasound in the forward direction and the propagation time in the reverse direction. When the confidence time difference is greater than the standard time difference, it means that the propagation time in the forward direction is greater than the propagation time in the reverse direction. That is, the flow direction of the fluid in the fluid channel to be detected should suppress the propagation of ultrasound in the forward direction and promote the propagation of ultrasound in the reverse direction. This results in the propagation time of ultrasound in the forward direction being longer than the propagation time in the reverse direction. Therefore, the direction of the target fluid is the reverse flow direction. When the confidence time difference is not greater than the standard time difference, based on the above logical relationship, it can be concluded that the direction of the target fluid is the forward flow direction.

[0125] S4. Using the pressure sensor and temperature sensor in the sensor detection unit, measure the environmental parameters of the fluid channel to be detected to obtain the real-time ambient temperature and real-time ambient pressure.

[0126] Understandably, the real-time ambient temperature and real-time ambient pressure refer to the temperature and pressure of the fluid in the fluid channel to be detected, respectively.

[0127] S5. Obtain a training data set, wherein the training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity, wherein the training sound velocity is the sound velocity of ultrasound in the fluid under the training temperature and training pressure.

[0128] It should be explained that, under high temperature and high pressure conditions, the speed of sound is significantly affected by the nonlinear effects of temperature and pressure, which traditional mathematical models cannot accurately describe. Since the speed of sound directly affects the accuracy of subsequent calculations of the target fluid velocity, a neural network model needs to be introduced. Through the neural network model, the influence relationship between temperature and pressure on the speed of sound in the environment of the fluid channel to be detected can be learned. The training data set refers to the training data used to train the neural network model.

[0129] Furthermore, the training data set is acquired as follows: First, a reference temperature and reference pressure are set, and the reference sound velocity in the fluid channel to be tested is measured at the reference temperature and reference pressure. During the measurement of the reference sound velocity, the fluid in the fluid channel to be tested should be kept stationary, and the measurement is performed using an ultrasonic sensor. Then, the temperature and pressure in the fluid channel to be tested are changed. The change can be performed by modifying the temperature and pressure according to a preset adjustment interval, recording the changed pressure and temperature, calculating the pressure difference between the changed pressure and the reference pressure, and the temperature difference between the changed temperature and the reference temperature, and measuring the sound velocity again to obtain the changed sound velocity. The difference in sound velocity between the changed sound velocity and the reference sound velocity is calculated. The temperature difference, pressure difference, and sound velocity difference are summarized as training data. The above steps are repeated to obtain the training data set.

[0130] S6. Perform high-dimensional feature expansion on the training data set to obtain a training feature data set, wherein the training feature data set includes multiple training feature data sets, and the training feature data sets include: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity, and the high-dimensional feature expansion is a Taylor expansion.

[0131] It needs to be explained that, since the data used as input in the training data set has a low dimension, with only three dimensions: temperature, pressure, and sound speed, in order to further enhance the expressive power of the model, it is necessary to perform high-dimensional feature expansion on the training data set. Here, high-dimensional feature expansion refers to expanding low-dimensional data into data with higher dimensions. Specifically, the following steps are taken: first, construct the influence function between temperature and pressure on sound speed; then, perform Taylor expansion on this function to obtain multiple expansion formulas; and use these multiple expansion formulas as the expanded training data.

[0132] Furthermore, Taylor expansion extends the one-dimensional variables of temperature and pressure into higher-order polynomial features, which can capture the nonlinear relationship between sound speed and temperature and pressure. If only the original data is used, the neural network model may not be able to recognize higher-order coupling effects.

[0133] Specifically, the high-dimensional feature expansion performed on the training data set to obtain a training feature data set includes:

[0134] Temperature and pressure variables are defined, and a sound velocity linkage influence function is constructed based on these variables. The sound velocity linkage influence function is expressed as follows:

[0135] ,

[0136] in, This represents the influence function of sound speed linkage. Represents the natural constant. This indicates the preset temperature coefficient. Represents temperature variable. This indicates the preset pressure coefficient. Indicates the stress variable;

[0137] According to the preset number of expansions, the sound speed linkage influence function is subjected to Taylor expansion to obtain a high-dimensional feature variable set, wherein the high-dimensional feature variable set includes a temperature feature variable set and a pressure feature variable set, and the order of the Taylor expansion is the same as the number of expansions.

[0138] Training data is extracted sequentially from the training data set, and the training temperature and training pressure in the training data are substituted into the high-dimensional feature variable set to obtain the high-dimensional training feature set. The high-dimensional training feature set and the training sound velocity are paired to obtain the training feature data set. The high-dimensional training feature set includes: a high-dimensional temperature feature set and a high-dimensional pressure feature set.

[0139] The training feature data sets are aggregated to obtain a training feature data set, where each training feature data set corresponds one-to-one with a training data set.

[0140] Understandably, the sonic velocity linkage effect function refers to a function that represents the relationship between the effects of changing temperature difference and changing pressure difference on sonic velocity. Since the effects of temperature and pressure on sonic velocity are not independent, this sonic velocity linkage effect function describes the synergistic effect of the two in an exponential form. If only temperature or pressure is modeled separately, the interaction between temperature and pressure may be ignored, such as the amplification effect of temperature on sonic velocity under high pressure.

[0141] Furthermore, the temperature coefficient and pressure coefficient refer to artificially set weighting coefficients representing temperature and pressure, respectively. Optionally, the temperature coefficient and pressure coefficient are set to 0.4 and 0.6, respectively. The expansion quantity refers to the artificially set order of the Taylor expansion, wherein the sound speed linkage influence function can be... The expansion is performed on the high-dimensional feature variables, which refer to the terms with variables obtained after expanding the sound speed linkage influence function. Each high-dimensional feature variable has a unique order. Specifically, the temperature feature variable refers to a high-dimensional feature variable with temperature as its variable, and the pressure feature variable refers to a high-dimensional feature variable with pressure as its variable. The high-dimensional training features refer to the high-dimensional feature variables obtained after substituting training temperature and training pressure.

[0142] S7. Train the pre-acquired neural network model using the training feature data set to obtain the sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure and the sound velocity compensation model, perform flow velocity compensation analysis on the fluid channel to be detected to obtain the target fluid flow velocity.

[0143] It should be explained that the number of neurons in the input layer of the neural network model is the same as the number of training feature data in the training feature data set, and the number of neurons in the output layer of the neural network model is 1, representing the speed of sound. The speed of sound compensation model refers to the trained neural network model. Since the data on speed of sound in the training feature data set are all varying speed of sound differences, the speed of sound obtained in the output layer of the speed of sound compensation model is also a speed of sound difference. This speed of sound difference needs to be added to the reference speed of sound to obtain the specific speed of sound output by this speed of sound compensation model. The target fluid velocity is the velocity of the fluid in the fluid channel to be detected. The velocity compensation analysis refers to calculating the target fluid velocity using the speed of sound obtained from the speed of sound compensation model. Since the propagation speed of ultrasound in fluid is affected by environmental parameters, directly using the reference speed of sound to calculate the fluid velocity will introduce errors. This velocity compensation analysis, combined with real-time temperature, real-time pressure, and the speed of sound compensation model, can achieve the purpose of dynamically correcting the velocity, thereby improving the accuracy of the measurement results.

[0144] In detail, the flow velocity compensation analysis of the fluid channel to be detected, based on real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model, is performed to obtain the target fluid flow velocity, including:

[0145] The ultrasonic sensor groups are extracted sequentially from multiple ultrasonic sensor groups, and the receiving frequency group of the ultrasonic sensor group is identified.

[0146] The mean frequency offset is calculated based on the receiving frequency group and the transmitting frequency, wherein the mean frequency offset is the average value of the difference between each receiving frequency and the transmitting frequency in the receiving frequency group;

[0147] Based on the frequency offset mean, real-time ambient temperature, real-time ambient pressure and sound velocity compensation model, flow velocity compensation calculation is performed to obtain the compensation fluid flow velocity.

[0148] The compensating fluid velocities are summarized to obtain multiple compensating fluid velocities. Based on the multiple compensating fluid velocities and the multiple data confidence levels, a weighted average is performed to obtain the target fluid velocity.

[0149] Understandably, the receiving frequency refers to the frequency of the ultrasonic waves received by the receiving sensor in the ultrasonic sensor group when it receives the ultrasonic waves. The weighted average formula involved in the step of performing a weighted average based on multiple compensated fluid flow velocities and multiple data confidence levels is the same as the weighted average formula involved in calculating the confidence time difference, and will not be repeated here.

[0150] In detail, the flow velocity compensation calculation based on the frequency offset mean, real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model to obtain the compensation fluid flow velocity includes:

[0151] Substituting the real-time ambient temperature and real-time ambient pressure into the sound speed compensation model, the compensated sound speed is obtained, wherein the compensated sound speed is the output value of the sound speed compensation model.

[0152] The radial angle between the line connecting the two ultrasonic sensors in the ultrasonic sensor group and the radial direction of the fluid channel to be detected was determined.

[0153] Based on the average frequency offset, transmission frequency, compensated sound velocity, and radial angle, the compensated flow velocity is calculated using the following formula:

[0154] ,

[0155] in, Indicates the compensation flow rate. Indicates the frequency offset mean. Indicates the speed of sound compensation. Indicates the transmission frequency. Represents the cosine function. Indicates the radial angle.

[0156] Understandably, the radial angle refers to the angle between the line connecting two ultrasonic sensors in the ultrasonic sensor group and the radial direction of the fluid channel to be detected.

[0157] S8. Based on the target fluid direction and target fluid velocity, complete the high temperature and high pressure flow detection based on bidirectional probe.

[0158] It is clear that once the direction and velocity of the target fluid are measured, the high-temperature and high-pressure flow detection based on bidirectional probe is completed.

[0159] To address the problems described in the background section, this invention first constructs a sensor detection unit comprising an ultrasonic sensor array, a pressure sensor, and a temperature sensor. This provides the hardware foundation for subsequent multi-parameter measurement and comprehensive analysis, ensuring the comprehensiveness and accuracy of data acquisition. Next, a through-and-through emission test is conducted using the ultrasonic sensor array within the sensor detection unit. This step acquires bidirectional data on sound wave propagation in the fluid, thus providing a basis for subsequent fluid direction determination. Then, by analyzing the sensor data set, the fluid flow direction can be accurately determined. Furthermore, the introduction of numerical confidence level in this step further improves the accuracy of flow direction detection. This is achieved by real-time measurement of the ambient temperature in the fluid channel. Temperature and pressure can capture the dynamic changes of fluids under high temperature and high pressure conditions. These environmental parameters are important bases for sound velocity calculation, providing fundamental data for subsequent sound velocity compensation models and ensuring the accuracy of sound velocity calculations. Furthermore, high-dimensional feature extraction of the training data through Taylor expansion captures the nonlinear relationship between environmental parameters and sound velocity, thereby enhancing the adaptability of the sound velocity compensation model to complex environmental conditions and improving its accuracy. Finally, the trained sound velocity compensation model is used to compensate for real-time measured environmental parameters, thus correcting errors in sound velocity calculation. This step significantly improves the accuracy of flow velocity calculation, especially under complex conditions such as high temperature and high pressure. Therefore, this invention can improve the accuracy and reliability of detecting flow direction and flow velocity under high temperature and high pressure environments.

[0160] like Figure 2 The diagram shown is a functional block diagram of a high-temperature and high-pressure flow detection system based on bidirectional probes provided in an embodiment of the present invention.

[0161] The high-temperature and high-pressure flow detection system 100 based on bidirectional probes described in this invention can be installed in an electronic device. Depending on the functions implemented, the high-temperature and high-pressure flow detection system 100 may include a detection unit construction module 101, a fluid direction detection module 102, a training data acquisition module 103, and a fluid velocity calculation module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0162] The detection unit construction module 101 is used to receive fluid detection instructions, determine the fluid channel to be detected based on the fluid detection instructions, and construct a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, pressure sensors, and temperature sensors.

[0163] The fluid direction detection module 102 is used to perform ultrasonic emission tests using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, wherein each sensor data set corresponds one-to-one with an ultrasonic sensor group, and the direction of the target fluid in the fluid channel to be detected is determined based on the multiple sensor data sets.

[0164] The training data acquisition module 103 is used to measure environmental parameters of the fluid channel to be detected using the pressure sensor and temperature sensor in the sensor detection unit, to obtain real-time environmental temperature and real-time environmental pressure, and to acquire a training data set. The training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity. The training sound velocity is the sound velocity of ultrasonic waves in the fluid under the training temperature and training pressure.

[0165] The fluid velocity calculation module 104 is used to perform high-dimensional feature expansion on the training data set to obtain a training feature data set. The training feature data set includes multiple training feature data sets, including a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity. The high-dimensional feature expansion is a Taylor expansion. The training feature data set is used to train a pre-acquired neural network model to obtain a sound velocity compensation model. Based on real-time ambient temperature, real-time ambient pressure, and the sound velocity compensation model, velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid velocity. Specifically, in this embodiment of the invention, the modules in the high-temperature and high-pressure flow detection system 100 based on bidirectional probes are used in the same manner as described above. Figure 1 The method described herein uses the same technical means as the high-temperature and high-pressure flow detection method based on bidirectional probes and can produce the same technical effect, so it will not be repeated here.

[0166] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing a high-temperature and high-pressure flow detection method based on bidirectional probes, according to an embodiment of the present invention.

[0167] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a program for a high-temperature and high-pressure flow detection method based on bidirectional probes.

[0168] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a high-temperature, high-pressure flow detection method program based on bidirectional probe beams, but also to temporarily store data that has been output or will be output.

[0169] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a high-temperature, high-pressure flow detection method program based on bidirectional probe beams) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0170] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0171] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0172] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0173] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0174] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0175] The program for a high-temperature, high-pressure flow detection method based on bidirectional probe beams, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0176] The system receives a fluid detection command, determines the fluid channel to be detected based on the fluid detection command, and constructs a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, a pressure sensor, and a temperature sensor.

[0177] An ultrasonic emission test was conducted using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, in which each sensor data set corresponds one-to-one with an ultrasonic sensor group.

[0178] Based on data sets from multiple sensors, the direction of the target fluid in the fluid channel to be detected is determined.

[0179] Using the pressure and temperature sensors in the sensor detection unit, environmental parameters of the fluid channel to be detected are measured to obtain real-time ambient temperature and real-time ambient pressure.

[0180] Acquire a training data set, wherein the training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity, wherein the training sound velocity is the sound velocity of ultrasound in the fluid under the training temperature and training pressure.

[0181] A high-dimensional feature expansion is performed on the training data set to obtain a training feature data set, wherein the training feature data set includes multiple training feature data sets, and the training feature data sets include: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity, and the high-dimensional feature expansion is a Taylor expansion.

[0182] The pre-acquired neural network model is trained using the training feature data set to obtain the sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure and the sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid flow velocity.

[0183] High-temperature and high-pressure flow detection is performed based on the direction and velocity of the target fluid using a bidirectional probe.

[0184] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0185] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0186] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0187] The system receives a fluid detection command, determines the fluid channel to be detected based on the fluid detection command, and constructs a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, a pressure sensor, and a temperature sensor.

[0188] An ultrasonic emission test was conducted using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, in which each sensor data set corresponds one-to-one with an ultrasonic sensor group.

[0189] Based on data sets from multiple sensors, the direction of the target fluid in the fluid channel to be detected is determined.

[0190] Using the pressure and temperature sensors in the sensor detection unit, environmental parameters of the fluid channel to be detected are measured to obtain real-time ambient temperature and real-time ambient pressure.

[0191] Acquire a training data set, wherein the training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity, wherein the training sound velocity is the sound velocity of ultrasound in the fluid under the training temperature and training pressure.

[0192] A high-dimensional feature expansion is performed on the training data set to obtain a training feature data set, wherein the training feature data set includes multiple training feature data sets, and the training feature data sets include: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity, and the high-dimensional feature expansion is a Taylor expansion.

[0193] The pre-acquired neural network model is trained using the training feature data set to obtain the sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure and the sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid flow velocity.

[0194] High-temperature and high-pressure flow detection is performed based on the direction and velocity of the target fluid using a bidirectional probe.

[0195] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0196] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] Furthermore, the functional modules in the various embodiments of the present invention 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. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0198] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A high-temperature and high-pressure flow detection method based on bidirectional probe through-beams, characterized in that, The method includes: The system receives a fluid detection command, determines the fluid channel to be detected based on the fluid detection command, and constructs a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, a pressure sensor, and a temperature sensor. An ultrasonic emission test was conducted using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, in which each sensor data set corresponds one-to-one with an ultrasonic sensor group. Based on data sets from multiple sensors, the direction of the target fluid in the fluid channel to be detected is determined. Using the pressure and temperature sensors in the sensor detection unit, environmental parameters of the fluid channel to be detected are measured to obtain real-time ambient temperature and real-time ambient pressure. Acquire a training data set, wherein the training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity, wherein the training sound velocity is the sound velocity of ultrasound in the fluid under the training temperature and training pressure. A high-dimensional feature expansion is performed on the training data set to obtain a training feature data set, wherein the training feature data set includes multiple training feature data sets, and the training feature data sets include: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity, and the high-dimensional feature expansion is a Taylor expansion. The pre-acquired neural network model is trained using the training feature data set to obtain the sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure and the sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid flow velocity. High-temperature and high-pressure flow detection is performed based on the direction and velocity of the target fluid using a bidirectional probe.

2. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 1, characterized in that, The ultrasonic emission test is performed using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets, including: The ultrasonic sensor groups are extracted sequentially from the plurality of ultrasonic sensor groups. Each ultrasonic sensor group includes two ultrasonic sensors. The two ultrasonic sensors in the same ultrasonic sensor group are installed on both sides of the fluid channel to be detected, and the line connecting the two ultrasonic sensors has an angle of less than 90 degrees with the radial direction of the fluid channel to be detected. An ultrasonic emission experiment was conducted using the ultrasonic sensor array to obtain a sensor data set. By aggregating the sensor data sets corresponding to each ultrasonic sensor group in multiple ultrasonic sensor groups, multiple sensor data sets are obtained.

3. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 2, characterized in that, The ultrasonic emission test based on the ultrasonic sensor group yields a sensor data set, including: According to the preset positive flow direction, one ultrasonic sensor in the ultrasonic sensor group is set as the transmitting sensor and the other ultrasonic sensor is set as the receiving sensor, wherein the direction in which the transmitting sensor emits ultrasonic waves to the receiving sensor is the positive flow direction. Based on the preset number of transmissions and the preset transmission frequency, the transmitting sensor transmits ultrasonic waves to the receiving sensor, and records the ultrasonic transmission time group and ultrasonic reception time group in the ultrasonic transmission step, and calculates the propagation time difference group between the ultrasonic transmission time group and the ultrasonic reception time group. The last transmission in the ultrasonic transmission step is identified, and the signal amplitude and signal-to-noise ratio of the ultrasonic signal received by the receiving sensor are detected in the last transmission. By pairing the propagation time difference group, signal amplitude, and signal-to-noise ratio, a forward propagation data group is obtained; The transmitting and receiving sensors are interchanged, and based on the interchanged transmitting and receiving sensors, the step of using the transmitting sensor to transmit ultrasonic waves to the receiving sensor is returned until a forward propagation data set is obtained again, and the forward propagation data set obtained after the interchange is recorded as the reverse propagation data set. The forward propagation data set and the reverse propagation data set are paired to obtain the sensor data set.

4. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 3, characterized in that, The step of determining the direction of the target fluid in the fluid channel to be detected based on multiple sensor data sets includes: Perform the following operations for each of the multiple sensor data sets: Extract the forward propagation time difference group of the forward propagation data group in the sensor data set, and the reverse propagation time difference group of the reverse propagation data group in the sensor data set, respectively; Based on the forward propagation time difference group and the reverse propagation time difference group, calculate the bidirectional time difference group, where the bidirectional time difference group includes multiple bidirectional time differences, and the bidirectional time difference is the difference between the forward propagation time difference and the corresponding reverse propagation time difference in the reverse propagation time difference group. Calculate the two-way standard deviation and the two-way mean deviation of the two-way time difference group; Calculate the data confidence level based on the two-way standard deviation, the forward propagation data set, and the backward propagation data set; The bidirectional time mean difference and data confidence scores are summarized to obtain multiple bidirectional time mean differences and multiple data confidence scores. Based on the multiple bidirectional time mean differences and multiple data confidence scores, the direction of the target fluid is determined.

5. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 4, characterized in that, The calculation of data confidence based on the bidirectional standard deviation, the forward propagation data set, and the backward propagation data set includes: The forward signal amplitude and forward signal-to-noise ratio are extracted from the forward propagation data set, and the reverse signal amplitude and reverse signal-to-noise ratio are extracted from the reverse propagation data set. Identify the maximum signal amplitude and maximum signal-to-noise ratio in multiple sensor data sets; Calculate the confidence level of the data using the following formula: ， in, Indicates the confidence level of the data. This represents the average value between the forward signal-to-noise ratio and the reverse signal-to-noise ratio. Indicates the maximum signal-to-noise ratio. This represents the average value between the amplitude of the positive signal and the amplitude of the negative signal. Indicates the maximum signal amplitude. This represents the two-way standard deviation.

6. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 5, characterized in that, The determination of the target fluid direction based on multiple bidirectional time average differences and multiple data confidence levels includes: Based on multiple bidirectional time-mean differences and multiple data confidence levels, the confidence time difference is obtained using a preset weighted average formula, wherein the weighted average formula is expressed as: ， in, Indicates the confidence time difference. This indicates the number of two-way time mean differences among multiple two-way time mean differences, or the number of data confidence scores among multiple data confidence scores. This represents the first of multiple data confidence levels. Data confidence level, Represents the average difference of multiple bidirectional times. The average time difference in both directions; Determine whether the confidence time difference is greater than the preset standard time difference; If the confidence time difference is greater than the standard time difference, the target fluid direction is recorded as the preset reverse flow direction; If the confidence time difference is not greater than the standard time difference, then the target fluid direction is recorded as the positive flow direction.

7. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beams as described in claim 6, characterized in that, The high-dimensional feature expansion of the training data set yields a training feature data set, including: Temperature and pressure variables are defined, and a sound velocity linkage influence function is constructed based on these variables. The sound velocity linkage influence function is expressed as follows: ， in, This represents the influence function of sound speed linkage. Represents the natural constant. This indicates the preset temperature coefficient. Represents temperature variable. This indicates the preset pressure coefficient. Indicates a pressure variable; According to the preset number of expansions, the sound speed linkage influence function is subjected to Taylor expansion to obtain a high-dimensional feature variable set, wherein the high-dimensional feature variable set includes a temperature feature variable set and a pressure feature variable set, and the order of the Taylor expansion is the same as the number of expansions. Training data is extracted sequentially from the training data set, and the training temperature and training pressure in the training data are substituted into the high-dimensional feature variable set to obtain the high-dimensional training feature set. The high-dimensional training feature set and the training sound velocity are paired to obtain the training feature data set. The high-dimensional training feature set includes: a high-dimensional temperature feature set and a high-dimensional pressure feature set. The training feature data sets are aggregated to obtain a training feature data set, where each training feature data set corresponds one-to-one with a training data set.

8. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beam as described in claim 7, characterized in that, The flow velocity compensation analysis of the fluid channel under test, based on the real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model, is used to obtain the target fluid flow velocity, including: The ultrasonic sensor groups are extracted sequentially from multiple ultrasonic sensor groups, and the receiving frequency group of the ultrasonic sensor group is identified. The mean frequency offset is calculated based on the receiving frequency group and the transmitting frequency, wherein the mean frequency offset is the average value of the difference between each receiving frequency and the transmitting frequency in the receiving frequency group; Based on the frequency offset mean, real-time ambient temperature, real-time ambient pressure and sound velocity compensation model, flow velocity compensation calculation is performed to obtain the compensation fluid flow velocity. The compensating fluid velocities are summarized to obtain multiple compensating fluid velocities. Based on the multiple compensating fluid velocities and the multiple data confidence levels, a weighted average is performed to obtain the target fluid velocity.

9. The high-temperature and high-pressure flow detection method based on bidirectional probe through-beam as described in claim 8, characterized in that, The flow velocity compensation calculation based on the frequency offset mean, real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model is performed to obtain the compensated fluid flow velocity, including: Substituting the real-time ambient temperature and real-time ambient pressure into the sound speed compensation model, the compensated sound speed is obtained, wherein the compensated sound speed is the output value of the sound speed compensation model. The radial angle between the line connecting the two ultrasonic sensors in the ultrasonic sensor group and the radial direction of the fluid channel to be detected was determined. Based on the average frequency offset, transmission frequency, compensated sound velocity, and radial angle, the compensated flow velocity is calculated using the following formula: ， in, Indicates the compensation flow rate. Indicates the frequency offset from the mean. Indicates compensation for the speed of sound. Indicates the transmission frequency. Represents the cosine function. Indicates the radial angle.

10. A high-temperature and high-pressure flow detection system based on bidirectional probe through-beams, characterized in that, The system includes: The detection unit construction module is used to receive fluid detection commands, determine the fluid channel to be detected based on the fluid detection commands, and construct a sensor detection unit in the fluid channel to be detected. The sensor detection unit includes: multiple ultrasonic sensor groups, pressure sensors, and temperature sensors. The fluid direction detection module is used to conduct ultrasonic emission tests using multiple ultrasonic sensor groups in the sensor detection unit to obtain multiple sensor data sets. Each sensor data set corresponds one-to-one with an ultrasonic sensor group. Based on the multiple sensor data sets, the direction of the target fluid in the fluid channel to be detected is determined. The training data acquisition module is used to measure environmental parameters of the fluid channel to be detected using the pressure sensor and temperature sensor in the sensor detection unit, to obtain real-time environmental temperature and real-time environmental pressure, and to acquire a training data set. The training data set includes multiple training data, and the training data includes: training temperature, training pressure and training sound velocity. The training sound velocity is the sound velocity of ultrasonic waves in the fluid under the training temperature and training pressure. The fluid velocity calculation module is used to perform high-dimensional feature expansion on the training data set to obtain a training feature data set. The training feature data set includes multiple training feature data sets, including: a high-dimensional temperature feature set, a high-dimensional pressure feature set, and a training sound velocity. The high-dimensional feature expansion is a Taylor expansion. The pre-acquired neural network model is trained using the training feature data set to obtain a sound velocity compensation model. Based on the real-time ambient temperature, real-time ambient pressure, and sound velocity compensation model, the flow velocity compensation analysis is performed on the fluid channel to be detected to obtain the target fluid velocity.

Images