Remote maintenance and diagnosis system for pipeline type ultrasonic flowmeter

Abstract

The invention relates to the technical field of flowmeter monitoring and maintenance, and discloses a pipeline type ultrasonic flowmeter remote maintenance and diagnosis system, which comprises a data acquisition module used for acquiring equipment operation data and baseline data; the coupling and sound velocity analysis module is used for generating a coupling coefficient and a sound velocity deviation based on the corresponding relationship between the equipment operation data and the baseline data; the working condition diagnosis module is used for generating a path consistency index and flow state similarity based on the equipment operation data and the baseline data; the health index calculation module is used for generating a health index based on the coupling coefficient, the sound velocity deviation, the path consistency index and the flow state similarity weighting, and correcting the weights of the coupling coefficient, the sound velocity deviation, the path consistency index and the flow state similarity in the health index; and the decision execution module is used for generating a maintenance instruction based on the health index. According to the invention, intelligence and precision of remote maintenance and diagnosis of the pipeline type ultrasonic flowmeter are realized.

Description

Technical Field

[0001] This invention belongs to the field of flow meter monitoring and maintenance technology, specifically relating to a remote maintenance and diagnostic system for pipeline ultrasonic flow meters. Background Technology

[0002] As a core device for industrial fluid metering, pipeline ultrasonic flow meters are widely used in petroleum, chemical, and water industries. Their long-term reliability and metering accuracy directly impact production efficiency and safety. However, existing technologies still suffer from the following problems: 1. Traditional ultrasonic flow meters rely on single parameters for fault diagnosis, lacking a comprehensive assessment of multiple dimensions such as coupling performance, flow regime changes, and equipment aging, leading to a high rate of missed early faults. For example, progressive faults such as aging coupling agent or loose probes are difficult to identify using a single indicator, often causing sudden shutdowns. 2. Existing systems lack adaptability to environmental changes and equipment lifecycles. Drastic temperature changes can cause deviations in sound velocity calculations, but traditional algorithms do not dynamically adjust diagnostic parameter weights, potentially misjudging equipment status. For aging equipment that has been operating for a long time, there is a lack of specific monitoring mechanisms for the degradation of coupling components, making preventative maintenance impossible. 3. The lack of remote operation and maintenance capabilities results in delayed on-site fault response. Traditional flow meters rely on manual inspections to detect anomalies, failing to generate maintenance commands and trigger actuators in real time, leading to long fault handling cycles, especially in high-risk or remote scenarios, potentially triggering cascading safety risks. Summary of the Invention

[0003] This invention provides a remote maintenance and diagnostic system for pipeline ultrasonic flow meters, which solves the technical problems of lack of multi-dimensional status assessment, insufficient adaptability to environment and equipment life cycle, and delayed remote operation and maintenance response in related technologies.

[0004] This invention provides a remote maintenance and diagnostic system for pipeline ultrasonic flow meters, comprising:

[0005] The data acquisition module is used to collect equipment operation data and baseline data;

[0006] The equipment operation data includes: echo amplitude, downstream propagation time, upstream propagation time and signal-to-noise ratio for each sound wave propagation path, as well as equipment operation time, ambient temperature and multidimensional flow characteristics data. The baseline data includes: baseline echo amplitude, baseline downstream propagation time and baseline upstream propagation time for each sound wave propagation path, as well as baseline flow characteristics data.

[0007] The coupling and sound velocity analysis module is used to generate coupling coefficients and sound velocity deviations based on the correspondence between equipment operating data and baseline data.

[0008] The operational condition diagnostic module is used to generate path consistency index and flow similarity based on equipment operation data and baseline data through multi-stage discrimination.

[0009] The health index calculation module is used to generate a health index based on the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity, and to correct the weights of the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index according to the changes in equipment operating time and ambient temperature.

[0010] The decision execution module is used to generate maintenance instructions based on health indices and send the maintenance instructions to the pipeline ultrasonic flow meter.

[0011] Furthermore, multidimensional flow characteristic data refers to data extracted from the fluid echo signal in the pipeline based on the edge artificial intelligence chip, including: amplitude spectrum peaks, echo signal variance, turbulence intensity, and autocorrelation characteristics; baseline flow characteristic data includes: baseline amplitude spectrum peaks, baseline echo signal variance, baseline turbulence intensity, and baseline autocorrelation characteristics.

[0012] Furthermore, the steps for generating coupling coefficients include:

[0013] S201, the echo amplitude of each sound wave propagation path is weighted according to the signal-to-noise ratio;

[0014] S202, select sound wave propagation paths with echo amplitude greater than the first preset threshold as valid paths;

[0015] S203 calculates the coupling coefficient by comparing the cumulative sum of the echo amplitudes of the effective path with the cumulative sum of the echo amplitudes of the baseline.

[0016] Furthermore, the steps for generating the sound speed deviation include:

[0017] S301, the theoretical speed of sound is calculated based on the linear compensation formula for the change of the speed of sound in air with temperature;

[0018] S302, the measured speed of sound is obtained by dividing twice the preset path length by the sum of the downstream propagation time and the upstream propagation time;

[0019] S303 calculates the absolute difference between the theoretical sound speed and the measured sound speed, and divides the absolute difference by the theoretical sound speed to obtain the sound speed deviation.

[0020] Furthermore, a path consistency index and flow regime similarity are generated through multi-stage discrimination, specifically including:

[0021] Phase 1: Path consistency determination based on propagation time stability, including:

[0022] The average propagation time is calculated based on the downstream and upstream propagation times of each sound wave propagation path. The baseline average propagation time is calculated based on the baseline downstream and upstream propagation times of each sound wave propagation path. The maximum absolute difference between the average propagation time and the baseline average propagation time is then compared with the mean of the baseline average propagation time to generate the path consistency index.

[0023] The second stage: determining flow stability based on changes in flow characteristics, including:

[0024] A flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the equipment operation data, and a baseline flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the baseline data;

[0025] Calculate the cosine similarity between the flow eigenvector and the baseline flow eigenvector, and inverse it as the flow similarity.

[0026] Furthermore, the weights of coupling coefficient, sound velocity deviation, path consistency index, and flow regime similarity in the health index are corrected based on changes in equipment operating time and ambient temperature, including:

[0027] When the device running time is less than the second preset threshold, the weights of coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index remain at the preset default weights.

[0028] When the equipment running time exceeds the second preset threshold, the weights of the coupling coefficient and path consistency index in the health index are linearly increased, while the weights of the sound velocity deviation and flow pattern similarity in the health index are correspondingly decreased.

[0029] When the change in ambient temperature exceeds the third preset threshold, the weight of sound velocity deviation in the health index is linearly increased, while the weights of coupling coefficient, path consistency index and flow pattern similarity are reduced accordingly.

[0030] Furthermore, when the coupling coefficient is lower than the fourth preset threshold, an early warning message for abnormal probe coupling is generated.

[0031] Furthermore, the maintenance instructions include: parameter adjustment instructions, probe locking instructions, manual inspection prompt instructions, system restart instructions, and emergency shutdown instructions. The maintenance instructions are generated based on the sub-interval to which the health index belongs.

[0032] The beneficial effects of this invention are as follows: This invention constructs a multi-dimensional evaluation system that includes coupling coefficient, sound velocity deviation, path consistency index, and flow pattern similarity by acquiring multi-path acoustic wave data and extracting features in real time from edge AI chips. It combines equipment operating time and ambient temperature to dynamically correct the weight of the health index, thereby achieving accurate characterization of the coupling performance, flow pattern stability, and equipment aging status of the ultrasonic flow meter. Through the health index interval management and gradient maintenance instruction generation mechanism, it links the local actuator and the remote operation and maintenance platform to form a closed loop of the entire process from anomaly warning, parameter adaptive adjustment to manual repair. Attached Figure Description

[0033] Figure 1 This is a schematic diagram of a remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to the present invention. Detailed Implementation

[0034] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and implement the subject matter described herein, and changes may be made to the function and arrangement of the elements discussed without departing from the scope of this specification. Various processes or components may be omitted, substituted, or added as needed in the examples. Furthermore, features described in some examples may be combined in other examples.

[0035] like Figure 1 As shown, a remote maintenance and diagnostic system for a pipeline ultrasonic flow meter includes:

[0036] Data acquisition module 101 is used to collect equipment operation data and baseline data;

[0037] The equipment operation data includes: echo amplitude, downstream propagation time, upstream propagation time and signal-to-noise ratio for each sound wave propagation path, as well as equipment operation time, ambient temperature and multidimensional flow characteristics data. The baseline data includes: baseline echo amplitude, baseline downstream propagation time and baseline upstream propagation time for each sound wave propagation path, as well as baseline flow characteristics data.

[0038] The coupling and sound velocity analysis module 102 is used to generate coupling coefficients and sound velocity deviations based on the correspondence between equipment operating data and baseline data.

[0039] The operating condition diagnosis module 103 is used to generate a path consistency index and flow similarity based on equipment operating data and baseline data through multi-stage discrimination.

[0040] The health index calculation module 104 is used to generate a health index based on the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity, and to correct the weights of the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index according to the changes in equipment operating time and ambient temperature.

[0041] The decision execution module 105 is used to generate maintenance instructions based on the health index and send the maintenance instructions to the pipeline ultrasonic flow meter.

[0042] In one embodiment of the present invention, the data acquisition module collects the echo amplitude, downstream propagation time, upstream propagation time, and signal-to-noise ratio of each sound wave propagation path in real time at a frequency of 100Hz. There are 8 sound wave propagation paths, and multi-path coverage is achieved by deploying array transducers. The ambient temperature and equipment operating time are updated every 5 seconds. The multidimensional flow characteristic data is extracted in real time by the edge AI chip through bandpass filtering and wavelet packet decomposition to extract the amplitude spectrum peaks, echo signal variance, turbulence intensity, and autocorrelation features, which are used to represent the real-time flow state of the fluid in the pipe.

[0043] The baseline echo amplitude, baseline downstream propagation time, and baseline upstream propagation time of the baseline data are collected within 30 seconds after the device is first powered on. At this time, the fluid in the pipe must be in a static or extremely low-speed state. The edge AI chip continuously samples the echo amplitude, downstream propagation time, and upstream propagation time of each sound wave propagation path 10 times and takes the average value to generate baseline data.

[0044] To ensure the comparability of data with different dimensions, the equipment operation data and baseline data were normalized using the min-max normalization method.

[0045] In one embodiment of the present invention, the multidimensional flow characteristic data refers to the data extracted from the fluid echo signal in the pipe based on the edge artificial intelligence chip, including: amplitude spectrum peak, echo signal variance, turbulence intensity and autocorrelation characteristics; the baseline flow characteristic data includes: baseline amplitude spectrum peak, baseline echo signal variance, baseline turbulence intensity and baseline autocorrelation characteristics.

[0046] Among them, the multidimensional flow regime characteristic data is a set of core parameters reflecting the real-time flow state of the fluid in the pipeline. The amplitude spectrum peak is obtained by extracting the peak frequency with the highest energy in the spectrum through fast Fourier transform of the echo signal, which is directly related to the distribution of bubbles and the scale of turbulent vortices in the fluid. The echo signal variance represents the degree of fluctuation of the echo signal. The larger the echo signal variance, the more unstable the fluid flow regime. The turbulence intensity is obtained by calculating the Doppler frequency shift broadening of the echo signal, which is used to quantify the intensity of the random motion of fluid micro-particles. Autocorrelation characteristics: by analyzing the correlation of the echo signal at different time delays, the time series characteristics of the fluid flow are extracted to identify the periodic changes of the flow regime. The baseline flow regime characteristic data is a reference dataset for comparison, reflecting the baseline flow regime characteristics when the equipment is operating normally. The baseline flow regime characteristic data is obtained by collecting echo signals for no less than 10 minutes through the edge AI chip.

[0047] In one embodiment of the present invention, the coupling coefficient is used to quantify the coupling quality of the sound wave propagation path of the device, and the specific steps include:

[0048] S201, the echo amplitude of each sound wave propagation path is weighted according to the signal-to-noise ratio; specifically, the weight of each echo amplitude is obtained by calculating the ratio of the signal-to-noise ratio of each sound wave propagation path to the sum of the signal-to-noise ratios of all sound wave propagation paths. Through the weighting mechanism, the sound wave propagation path with a high signal-to-noise ratio can obtain a higher weight, thus suppressing the influence of noise interference on the coupling coefficient.

[0049] S202, select sound wave propagation paths with echo amplitude greater than a first preset threshold as valid paths; wherein, the first preset threshold is preferably set to 40% of the baseline echo amplitude. This step can eliminate invalid paths with excessively low echo signals due to aging of the coupling agent, loosening of the probe, etc., and ensure the reliability of the calculation.

[0050] S203, the coupling coefficient is calculated by comparing the cumulative sum of the echo amplitudes of the effective path with the cumulative sum of the echo amplitudes of the baseline; the formula for calculating the coupling coefficient is as follows: , Let k represent the coupling coefficient, k represent the index of the effective path, and S represent the set of effective paths. This represents the k-th valid path. This represents the baseline echo amplitude of the k-th valid path. The weight of the echo amplitude of the kth effective path is represented by the coupling coefficient. A coupling coefficient close to 1 indicates good coupling, while a coupling coefficient less than 1 indicates attenuation of echo energy and problems such as drying of the coupling agent or scaling on the inner wall of the pipe.

[0051] Through the above steps, the coupling coefficient can reflect the coupling status of the equipment's acoustic wave transmission link in real time, providing key parameters for the operating condition diagnosis module and health index calculation, and improving the early warning capability of pipeline ultrasonic flow meters for coupling-related faults, such as probe loosening and changes in medium characteristics.

[0052] In one embodiment of the present invention, the step of generating the sound speed deviation includes:

[0053] S301, the theoretical speed of sound is calculated based on the linear compensation formula for the change of sound speed in air with temperature; whereby the linear compensation formula is: , Represents the theoretical speed of sound. Indicates ambient temperature;

[0054] S302, the measured speed of sound is obtained by dividing twice the preset path length by the sum of the downstream propagation time and the upstream propagation time;

[0055] S303, calculate the absolute difference between the theoretical and measured sound speeds, and divide the absolute difference by the theoretical sound speed to obtain the sound speed deviation; the formula for calculating the sound speed deviation is: ,in, This represents the sound speed deviation, used to quantify the difference between the theoretical and measured sound speeds. L represents the preset path length, i.e., the fixed distance between transducers. and These represent the downstream propagation time and the upstream propagation time, respectively.

[0056] In one embodiment of the present invention, the path consistency index and flow similarity are generated through multi-stage discrimination, specifically including:

[0057] Phase 1: Path consistency determination based on propagation time stability, including:

[0058] The average propagation time is calculated based on the downstream and upstream propagation times of each sound wave propagation path. The baseline average propagation time is calculated based on the baseline downstream and upstream propagation times of each sound wave propagation path. The maximum absolute difference between the average propagation time and the baseline average propagation time is then ratioed to the mean of the baseline average propagation time to generate the path consistency index. The formula for calculating the path consistency index is as follows: ;

[0059] Wherein, PSI represents the path consistency index. and Let these represent the downstream propagation time and the upstream propagation time of the i-th sound wave propagation path, respectively. and The baseline downstream propagation time and the baseline upstream propagation time of the i-th sound wave propagation path are respectively represented, where i represents the index of the sound wave propagation path, n represents the number of sound wave propagation paths (preferably set to 8), and max represents the maximum value operation, that is, taking the maximum difference between the absolute difference between the average propagation time of each sound wave propagation path and the average propagation time of the baseline. PSI is used to reflect the dispersion of multi-path propagation time. The larger the PSI value, the more significant the difference in propagation time between paths, which may indicate abnormalities such as uneven flow velocity distribution and scaling on the inner wall of the pipe.

[0060] The second stage: determining flow stability based on changes in flow characteristics, including:

[0061] A flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the equipment operation data, and a baseline flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the baseline data;

[0062] Calculate the cosine similarity between the flow eigenvector and the baseline flow eigenvector, and inverse it as the flow similarity.

[0063] The closer the flow pattern similarity is to 0, the more similar the flow pattern is to the baseline. The greater the flow pattern similarity, the more significant the flow pattern change, such as an increase in bubbles or an increase in turbulence intensity.

[0064] In this embodiment, the first stage quickly filters out obvious abnormal paths by measuring the difference in propagation time, providing direction for the flow regime analysis in the second stage. The second stage accurately identifies the anomaly type by measuring the pattern differences in flow regime characteristics, avoiding misjudgment based on a single parameter. For example, changes in propagation time caused by temperature fluctuations can be distinguished by flow regime characteristics.

[0065] In one embodiment of the present invention, the weights of coupling coefficient, sound velocity deviation, path consistency index, and flow regime similarity in the health index are corrected based on changes in equipment operating time and ambient temperature, including:

[0066] When the device running time is less than the second preset threshold, the weights of coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index remain at the preset default weights.

[0067] When the equipment operating time exceeds the second preset threshold, the weights of the coupling coefficient and path consistency index in the health index are linearly increased, while the weights of sound velocity deviation and flow pattern similarity in the health index are correspondingly decreased. It should be noted that the longer the equipment operating time, the higher the risk of aging of coupling components such as probes and coupling agents, and the greater the probability that the path consistency index will be affected by loose installation. Therefore, the weights of the coupling coefficient and path consistency index in the health index are increased, while the weights of sound velocity deviation and flow pattern similarity, which are less affected by aging, are decreased.

[0068] When the change in ambient temperature exceeds the third preset threshold, the weight of sound velocity deviation in the health index is linearly increased, while the weights of coupling coefficient, path consistency index and flow pattern similarity are reduced accordingly. It should be noted that when the temperature changes drastically, the sound velocity is significantly affected by the thermal expansion of the medium. Therefore, the weight of sound velocity deviation needs to be increased to enhance the temperature compensation effect, while the weights of other parameters are reduced to avoid misjudgment caused by temperature interference.

[0069] Through the aforementioned dynamic weight correction mechanism, the health index calculation can adapt to the degree of equipment aging and environmental changes, realizing full-stage diagnostic capabilities from early fault equalization monitoring to mid-term aging precise positioning, and then to extreme environment-specific enhancement, thereby improving the long-term operational reliability of pipeline ultrasonic flow meters.

[0070] In one embodiment of the present invention, when the coupling coefficient is lower than a fourth preset threshold, the decision execution module generates a probe coupling anomaly warning message, preferably set to 0.85. The coupling coefficient reflects the acoustic wave transmission efficiency at the interface between the transducer and the pipeline medium. When it is lower than the fourth preset threshold, it may be caused by reasons such as coupling agent failure, loose probe installation, or medium scaling. At this time, the decision execution module displays a red warning icon and flashes it through the local interactive interface, and triggers an SMS notification to the maintenance personnel. This mechanism can provide early warning in the early stage of coupling performance degradation, accurately locate the anomaly point by combining multi-path data, and improve fault response efficiency and system operational reliability through automatic repair and manual maintenance linkage.

[0071] In one embodiment of the present invention, the decision execution module is used to generate maintenance instructions based on a health index and issue them to the pipeline ultrasonic flow meter. The maintenance instructions are generated according to the gradient of the health index interval, specifically including:

[0072] When the health index is between 90 and 100, the device is determined to be in a safe range. The decision execution module automatically generates parameter adjustment instructions and adjusts the weight of the sound speed deviation based on the real-time collected environmental data.

[0073] When the health index is between 80 and 90, the device is determined to be in the attention zone. If the path consistency index is detected to be greater than 0.08 and the coupling coefficient is less than 0.95 for more than 2 hours, the probe locking command is triggered, and the pre-tightening force is applied to the probe array through the stepper motor.

[0074] When the health index is between 65 and 80, the equipment is determined to be in the warning range. If the health index is below 80 for 12 consecutive hours and the sound velocity deviation is greater than 3%, or the flow pattern similarity is greater than 0.3, the decision execution module generates a manual inspection prompt instruction and pushes a work order containing details of abnormal parameters to the operation and maintenance personnel, recommending to check the probe coupling surface, cable joints, etc.

[0075] When the health index is between 50 and 65, the equipment is determined to be in the fault range. If the path consistency index is greater than 0.15, the decision execution module executes a three-level restart strategy, first a soft restart and then a hard restart, while switching to the backup channel and generating a repair work order to push to the operation and maintenance terminal.

[0076] When the health index is between 0 and 50, the equipment is determined to be in the failure range. The decision execution module immediately issues an emergency shutdown command to cut off the power supply, triggers the bypass valve to switch, and generates a fault diagnosis report containing multi-dimensional abnormal data to help quickly locate the fault point.

[0077] It should be noted that the interval and threshold sizes are set for ease of comparison. The size of the threshold depends on the amount of sample data and the base number set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless calculations, and the formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0078] The embodiments of the present invention have been described above, but the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms based on the guidance of the present embodiments, all of which are within the protection scope of the present embodiments.

Claims

1. A remote maintenance and diagnostic system for a pipeline ultrasonic flow meter, characterized in that, include: The data acquisition module is used to collect equipment operation data and baseline data; The equipment operation data includes: echo amplitude, downstream propagation time, upstream propagation time and signal-to-noise ratio for each sound wave propagation path, as well as equipment operation time, ambient temperature and multidimensional flow characteristics data. The baseline data includes: baseline echo amplitude, baseline downstream propagation time and baseline upstream propagation time for each sound wave propagation path, as well as baseline flow characteristics data. The coupling and sound velocity analysis module is used to generate coupling coefficients and sound velocity deviations based on the correspondence between equipment operating data and baseline data. The operational condition diagnostic module is used to generate path consistency index and flow similarity based on equipment operation data and baseline data through multi-stage discrimination. The health index calculation module is used to generate a health index based on the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity, and to correct the weights of the coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index according to the changes in equipment operating time and ambient temperature. The decision execution module is used to generate maintenance instructions based on health indices and send the maintenance instructions to the pipeline ultrasonic flow meter.

2. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, Multidimensional flow characteristic data refers to data extracted from the echo signal of fluid in the pipeline based on edge artificial intelligence chip, including: amplitude spectrum peaks, echo signal variance, turbulence intensity and autocorrelation characteristics; baseline flow characteristic data includes: baseline amplitude spectrum peaks, baseline echo signal variance, baseline turbulence intensity and baseline autocorrelation characteristics.

3. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, The steps for generating coupling coefficients include: S201, the echo amplitude of each sound wave propagation path is weighted according to the signal-to-noise ratio; S202, select sound wave propagation paths with echo amplitude greater than the first preset threshold as valid paths; S203 calculates the coupling coefficient by comparing the cumulative sum of the echo amplitudes of the effective path with the cumulative sum of the echo amplitudes of the baseline.

4. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, The steps to generate sound speed deviation include: S301, the theoretical speed of sound is calculated based on the linear compensation formula for the change of the speed of sound in air with temperature; S302, the measured speed of sound is obtained by dividing twice the preset path length by the sum of the downstream propagation time and the upstream propagation time; S303 calculates the absolute difference between the theoretical sound speed and the measured sound speed, and divides the absolute difference by the theoretical sound speed to obtain the sound speed deviation.

5. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, The path consistency index and flow similarity are generated through multi-stage discrimination, specifically including: Phase 1: Path consistency determination based on propagation time stability, including: The average propagation time is calculated based on the downstream and upstream propagation times of each sound wave propagation path. The baseline average propagation time is calculated based on the baseline downstream and upstream propagation times of each sound wave propagation path. The maximum absolute difference between the average propagation time and the baseline average propagation time is then compared with the mean of the baseline average propagation time to generate the path consistency index. The second stage: determining flow stability based on changes in flow characteristics, including: A flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the equipment operation data, and a baseline flow pattern feature vector is constructed based on the multidimensional flow pattern feature data in the baseline data; Calculate the cosine similarity between the flow eigenvector and the baseline flow eigenvector, and inverse it as the flow similarity.

6. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, The weights of coupling coefficient, sound velocity deviation, path consistency index, and flow regime similarity in the health index are adjusted based on changes in equipment operating time and ambient temperature, including: When the device running time is less than the second preset threshold, the weights of coupling coefficient, sound velocity deviation, path consistency index and flow pattern similarity in the health index remain at the preset default weights. When the equipment running time exceeds the second preset threshold, the weights of the coupling coefficient and path consistency index in the health index are linearly increased, while the weights of the sound velocity deviation and flow pattern similarity in the health index are correspondingly decreased. When the change in ambient temperature exceeds the third preset threshold, the weight of sound velocity deviation in the health index is linearly increased, while the weights of coupling coefficient, path consistency index and flow pattern similarity are reduced accordingly.

7. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, When the coupling coefficient is lower than the fourth preset threshold, an early warning message for abnormal probe coupling is generated.

8. The remote maintenance and diagnostic system for a pipeline ultrasonic flow meter according to claim 1, characterized in that, The maintenance instructions include: parameter adjustment instructions, probe locking instructions, manual inspection prompt instructions, system restart instructions, and emergency shutdown instructions. The maintenance instructions are generated based on the sub-interval to which the health index belongs.

Images