Intelligent pipeline wall thickness monitoring system, method, device, medium and product

Abstract

This invention relates to the field of pipe wall monitoring technology, and discloses an intelligent pipe wall thickness monitoring system, method, device, medium, and product. The system includes: a data acquisition unit configured to acquire electrical level data to obtain a first dataset; a second dataset acquired by acquiring electrical level data from each Hall sensor; a judgment unit configured to compare the electrical level data corresponding to each sensor array in the second dataset with the electrical level data corresponding to each sensor array in the first dataset, and determine whether corrosion exists in the monitored pipe based on the comparison result; a processing unit configured to adjust the acquisition time interval according to an adjustment coefficient; and an adjustment unit configured to determine whether to adjust the adjustment coefficient of the acquisition time interval. This invention solves the problem of large errors caused by reliance on manual labor, improves the efficiency and accuracy of pipe monitoring, and enhances its adaptability and intelligence.

Description

Technical Field

[0001] This invention relates to the field of pipe wall monitoring technology, and more specifically, to an intelligent pipe wall thickness monitoring system, method, equipment, medium, and product. Background Technology

[0002] In modern industry, pipeline systems are widely used in sectors such as oil, natural gas, chemicals, and water treatment. Over time, pipelines are affected by corrosion, wear, and other external factors, causing their wall thickness to gradually decrease, potentially leading to safety hazards such as leaks and explosions. Therefore, real-time monitoring of pipeline wall thickness has become crucial.

[0003] However, traditional monitoring methods often rely on manual inspections and periodic testing, which have some obvious shortcomings. For example, relying on manual testing not only increases labor costs, but may also lead to deviations in test results due to human factors, thereby affecting the assessment of pipeline health.

[0004] Therefore, how to solve the problem of large errors in traditional detection methods is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In view of this, the present invention proposes an intelligent pipeline wall thickness monitoring system, method, equipment, medium and product, aiming to solve the problem of large errors caused by the high degree of reliance on manual labor in current pipeline monitoring technology.

[0006] In a first aspect, the present invention proposes an intelligent pipeline wall thickness monitoring system, comprising:

[0007] A sensor array and a monitoring module, wherein the monitoring module is connected to the sensor array;

[0008] The sensor array is provided in multiple ways, and each sensor array is arranged around the pipe to be monitored. Each sensor array includes multiple Hall sensors.

[0009] The monitoring module includes a data acquisition unit, a judgment unit, a processing unit, and an adjustment unit;

[0010] The acquisition unit is configured to acquire the level data of each Hall sensor in all the sensor arrays to obtain a first dataset; after an acquisition time interval, the level data of each Hall sensor is acquired again to obtain a second dataset; the acquisition time interval is determined by the acquisition unit based on the operating data of the pipeline to be monitored;

[0011] The judgment unit is configured to compare the level data corresponding to each sensor array in the second dataset with the level data corresponding to each sensor array in the first dataset, and determine whether the pipeline to be monitored is corroded based on the comparison result;

[0012] The processing unit is configured to, when the judgment unit determines that the pipeline to be monitored is corroded, determine the corrosion area based on the level change, determine the adjustment coefficient of the acquisition time interval based on the corrosion rate, and adjust the acquisition time interval based on the adjustment coefficient; the level change refers to the level data that changes in the first dataset and the second dataset.

[0013] The adjustment unit is configured to collect the corrosion area and the real-time flow velocity of the pipeline to be monitored from the processing unit, establish a feature set based on the corrosion area and the real-time flow velocity, perform cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine a similar set, and determine whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the adjustment coefficient of the historical acquisition time interval in the similar set and the adjustment coefficient of the acquisition time interval.

[0014] In some embodiments, the acquisition unit determines the acquisition time interval based on the operating data of the pipeline to be monitored, satisfying the following formula:

[0015]

[0016] Where Tc represents the acquisition time interval, D represents the pipe diameter, ρ represents the fluid density in the pipe, Ac represents the pipe cross-sectional area, Fs represents the Hall sensor sensitivity, β represents the temperature influence coefficient, β ranges from 0.01 to 0.05, and Tavg represents the average temperature of the fluid in the pipe to be monitored.

[0017] In some embodiments, the determination unit determines whether the pipeline is corroded based on the comparison result, including:

[0018] When any of the level data in the second dataset changes, the judgment unit determines that the pipeline to be monitored is corroded;

[0019] When the level data in the second dataset is the same as that in the first dataset, the judgment unit determines that the pipeline to be monitored is not corroded.

[0020] In some embodiments, the processing unit determines the corrosion area based on level changes, including:

[0021] The processing unit determines the corrosion area based on the number of Hall sensors corresponding to the position of the change in the level data, and the corrosion area is directly proportional to the number of Hall sensors.

[0022] In some embodiments, the processing unit determines an adjustment coefficient for the acquisition time interval based on the corrosion rate, and adjusts the acquisition time interval according to the adjustment coefficient, including:

[0023] The processing unit determines the corrosion rate based on the corrosion area and the acquisition time interval, determines the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval to which the corrosion rate belongs, and adjusts the acquisition time interval based on the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval.

[0024] In some embodiments, the processing unit determines an adjustment coefficient for the sampling time interval corresponding to the corrosion rate range to which the corrosion rate belongs, and adjusts the sampling time interval based on the adjustment coefficient, including:

[0025] When the corrosion rate is less than or equal to the first preset corrosion rate, the processing unit determines that the corrosion rate belongs to the first corrosion rate range, determines the first preset adjustment coefficient corresponding to the first preset corrosion rate range, and adjusts the acquisition time interval based on the first preset adjustment coefficient.

[0026] When the corrosion rate is greater than the first preset corrosion rate and less than or equal to the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the second corrosion rate range, determines the second preset adjustment coefficient corresponding to the second corrosion rate range, and adjusts the acquisition time interval based on the second preset adjustment coefficient.

[0027] When the corrosion rate is greater than the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the third corrosion rate range, determines the third preset adjustment coefficient corresponding to the third corrosion rate range, and adjusts the acquisition time interval based on the third preset adjustment coefficient.

[0028] Wherein, the first corrosion rate is less than the second corrosion rate, the first preset adjustment coefficient is greater than the second preset adjustment coefficient, the second preset adjustment coefficient is greater than the third preset adjustment coefficient, and the third preset adjustment coefficient is greater than 0.

[0029] In some embodiments, the adjustment unit performs cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine a similar set, including:

[0030] S1: The adjustment unit initializes K centroids in the historical running data, and assigns the feature set to the nearest centroid to form K clusters;

[0031] S2: The adjustment unit recalculates the centroid of each cluster;

[0032] S3: The adjustment unit repeats S1 and S2 until the centroid no longer changes or the preset number of repetitions is completed;

[0033] S4: The adjustment unit constructs a similar set from the remaining historical running data in the cluster where the feature set is located;

[0034] The formula for calculating the centroid is as follows:

[0035]

[0036] Where Zk represents the centroid of the k-th cluster, |Ck| represents the number of data in the k-th cluster, and Ti represents the feature vector of the i-th data.

[0037] In some embodiments, the adjustment unit determines whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the adjustment coefficient of the historical acquisition time interval within the similar set and the adjustment coefficient of the acquisition time interval, including:

[0038] The adjustment unit extracts the adjustment coefficients of the historical collection time intervals from the similar set to form a historical adjustment group;

[0039] When there is data in the historical adjustment group that is greater than the adjustment coefficient of the collection time interval and at the same time there is data that is less than the adjustment coefficient of the collection time interval, the adjustment unit determines to correct the adjustment coefficient of the collection time interval.

[0040] When all data in the historical adjustment group are less than or equal to the adjustment coefficient of the acquisition time interval, or are greater than or equal to the adjustment coefficient of the acquisition time interval, the adjustment unit determines that the adjustment coefficient of the acquisition time interval should not be adjusted.

[0041] In some embodiments, when the adjustment unit determines to adjust the adjustment coefficient of the acquisition time interval,

[0042] The adjustment unit constructs a first correction set from the data in the historical adjustment group that are greater than the inter-collection interval by the adjustment coefficient.

[0043] The adjustment unit constructs a second correction set from the data in the historical adjustment group whose adjustment coefficients are less than the collection time interval;

[0044] The adjustment unit adjusts the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set.

[0045] In some embodiments, the adjustment unit corrects the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set, satisfying the following formula:

[0046]

[0047] Wherein, Kz is the adjustment coefficient of the corrected acquisition time interval, m is the number of adjustment coefficients of historical acquisition time intervals in the first correction set, Ki is the adjustment coefficient of the i-th historical acquisition time interval in the first correction set, K0 is the adjustment coefficient of the acquisition time interval, n is the number of adjustment coefficients of historical acquisition time intervals in the second correction set, and Kj is the adjustment coefficient of the j-th historical acquisition time interval in the second correction set.

[0048] Secondly, an intelligent pipeline wall thickness monitoring method is provided, comprising: collecting the level data of each Hall sensor in all sensor arrays to obtain a first dataset; after a collection time interval, collecting the level data of each Hall sensor again to obtain a second dataset; wherein the collection time interval is determined based on the operating data of the pipeline to be monitored;

[0049] The voltage level data corresponding to each sensor array in the second dataset is compared with the voltage level data corresponding to each sensor queue in the first dataset, and the presence of corrosion in the pipeline is determined based on the comparison results.

[0050] When corrosion is detected in the pipeline, the corrosion area is determined based on the level change, and the adjustment coefficient of the sampling time interval is determined based on the corrosion rate. The sampling time interval is then adjusted based on the adjustment coefficient.

[0051] The corrosion area and the real-time flow velocity of the pipeline to be monitored are collected. A feature set is established based on the corrosion area and the real-time flow velocity. The feature set is clustered with the historical operating data of the pipeline to be monitored to determine the similar set. The adjustment coefficient of the acquisition time interval is determined based on the relationship between the historical time interval adjustment coefficient and the acquisition time interval adjustment coefficient in the similar set.

[0052] Thirdly, an intelligent pipeline wall thickness monitoring device is provided, comprising:

[0053] The acquisition unit is used to acquire the level data of each Hall sensor in all sensor arrays to obtain a first dataset; after an acquisition time interval, the level data of each Hall sensor is acquired again to obtain a second dataset; the acquisition time interval is determined based on the operating data of the pipeline to be monitored.

[0054] The judgment unit is used to compare the level data corresponding to each sensor array in the second dataset with the level data corresponding to each sensor queue in the first dataset, and to determine whether the pipeline is corroded based on the comparison result.

[0055] The processing unit is used to determine the corrosion area based on the level change when it is determined that the pipeline is corroded, and to determine the adjustment coefficient of the sampling time interval based on the corrosion rate, and to adjust the sampling time interval based on the adjustment coefficient.

[0056] The adjustment unit is used to collect the corrosion area and the real-time flow velocity of the pipeline to be monitored, establish a feature set based on the corrosion area and the real-time flow velocity, perform cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine the similar set, and determine whether to correct the adjustment coefficient of the acquisition time interval based on the relationship between the historical time interval adjustment coefficient and the acquisition time interval adjustment coefficient in the similar set.

[0057] Fourthly, an intelligent pipeline wall thickness monitoring device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory via a bus; when the intelligent pipeline wall thickness monitoring device is running, the processor executes the computer execution instructions stored in the memory, so that the intelligent pipeline wall thickness monitoring device performs the intelligent pipeline wall thickness monitoring method described in the first aspect.

[0058] The intelligent pipeline wall thickness monitoring device can be a network device or a component of a network device, such as a chip system within the network device. This chip system supports the network device in implementing the functions involved in the first aspect and any possible implementation thereof, such as acquiring, determining, and transmitting the data and / or information involved in the aforementioned intelligent pipeline wall thickness monitoring method. The chip system includes a chip, but may also include other discrete devices or circuit structures.

[0059] Fifthly, a computer-readable storage medium is provided, comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the intelligent pipeline wall thickness monitoring method described in the first aspect.

[0060] In a sixth aspect, a computer program product is also provided, which includes computer instructions that, when executed on an intelligent pipeline wall thickness monitoring device, cause the intelligent pipeline wall thickness monitoring device to perform the intelligent pipeline wall thickness monitoring method as described in the first aspect above.

[0061] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the intelligent pipeline wall thickness monitoring device, or it may be packaged separately from the processor of the intelligent pipeline wall thickness monitoring device; this application does not limit this.

[0062] The descriptions of the second, third, fourth, fifth, and sixth aspects of this application can be referenced to the detailed description of the first aspect.

[0063] In the embodiments of this application, the name of the aforementioned intelligent pipeline wall thickness monitoring device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. For example, the receiving unit may also be called a receiving module, receiver, etc. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0064] Compared to existing technologies, this application utilizes a sensor array arranged around the pipeline to acquire voltage levels over different time periods, and determines the presence of corrosion by comparing these voltage levels. The monitoring module can also determine the corrosion area based on voltage level fluctuations obtained from the voltage level comparison, and adjust the acquisition time interval according to the corrosion rate. For example, the acquisition frequency can be reduced when corrosion is slow to lower energy consumption, while the acquisition frequency can be increased when corrosion is rapid, thus improving pipeline safety. Furthermore, the monitoring module can determine whether to adjust the acquisition time interval adjustment factor based on real-time flow velocity and corrosion area, making the set acquisition time interval more consistent with the current pipeline corrosion situation and better meeting user needs.

[0065] In summary, sensor arrays and monitoring modules can promptly confirm the presence of corrosion in pipelines. Compared to manual monitoring, this not only improves monitoring efficiency but also accuracy, enabling rapid identification of corrosion risks. Furthermore, by adjusting the acquisition interval and its adjustment coefficient, the monitoring frequency can be adjusted based on the actual operating conditions of the pipeline, thereby enhancing the flexibility and accuracy of pipeline monitoring. Attached Figure Description

[0066] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0067] Figure 1 This is a structural block diagram of the intelligent pipeline wall thickness monitoring system provided in an embodiment of the present invention;

[0068] Figure 2 A schematic diagram of the hardware structure of the intelligent pipeline wall thickness monitoring device provided in an embodiment of the present invention;

[0069] Figure 3 A flowchart of the intelligent pipeline wall thickness monitoring method provided in the embodiments of the present invention;

[0070] Figure 4 This is a schematic diagram of the intelligent pipeline wall thickness monitoring device provided in an embodiment of the present invention. Detailed Implementation

[0071] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0072] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0073] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0074] As described in the background section, manual inspection is not only inefficient but also prone to significant errors. Furthermore, under harsh environmental conditions, traditional monitoring equipment may fail or be damaged, affecting the continuity and accuracy of monitoring. Moreover, traditional monitoring methods typically only collect data at specific points in time, failing to provide dynamic feedback adjustments based on pipeline corrosion status, resulting in poor detection effectiveness due to the lack of a feedback adjustment mechanism.

[0075] To address this issue, this application provides an intelligent pipeline wall thickness monitoring system, comprising: a sensor array and a monitoring module. Multiple sensor arrays are arranged, each surrounding the pipeline to be monitored. Each sensor array includes multiple Hall effect sensors. The monitoring module includes a data acquisition unit, a judgment unit, a processing unit, and an adjustment unit. The data acquisition unit is configured to acquire the voltage level data of each Hall effect sensor in all sensor arrays to obtain a first dataset; after a data acquisition time interval, it acquires the voltage level data of each Hall effect sensor again to obtain a second dataset; the data acquisition time interval is determined by the data acquisition unit based on the operating data of the pipeline to be monitored. The judgment unit is configured to compare the second dataset with the first dataset to determine whether corrosion exists in the pipeline to be monitored.

[0076] The processing unit is configured to determine the corrosion area based on the level variation, determine the adjustment coefficient of the acquisition time interval based on the corrosion rate, and adjust the acquisition time interval based on the adjustment coefficient; the level variation refers to the level data that varies in the first dataset and the second dataset.

[0077] The adjustment unit is configured to collect the corrosion area and real-time flow velocity of the pipeline to be monitored from the processing unit. A feature set is established based on the corrosion area and real-time flow velocity. The feature set is then clustered with the historical operating data of the pipeline to be monitored to determine similar sets. Based on the relationship between the adjustment coefficient of the historical acquisition time interval and the adjustment coefficient of the acquisition time interval within the similar sets, it is determined whether to adjust the adjustment coefficient of the acquisition time interval.

[0078] As shown above, an array of sensors surrounding the pipeline under monitoring can acquire voltage levels over different time periods, and the presence of corrosion can be determined by comparing these voltage levels. The monitoring module can also determine the corrosion area based on voltage level fluctuations obtained from the voltage level comparison and adjust the sampling time interval according to the corrosion rate. For example, the sampling frequency can be reduced when corrosion is slow to lower energy consumption, while the sampling frequency can be increased when corrosion is rapid, thus improving pipeline safety. Furthermore, the monitoring module can determine whether to adjust the sampling time interval adjustment factor based on real-time flow velocity and corrosion area, making the set sampling time interval more consistent with the current pipeline corrosion situation and better meeting user needs.

[0079] In summary, sensor arrays and monitoring modules can promptly confirm the presence of corrosion in pipelines. Compared to manual monitoring, this not only improves monitoring efficiency but also accuracy, enabling rapid identification of corrosion risks. Furthermore, by adjusting the acquisition interval and its adjustment coefficient, the monitoring frequency can be adjusted based on the actual operating conditions of the pipeline, thereby enhancing the flexibility and accuracy of pipeline monitoring.

[0080] Furthermore, by comprehensively utilizing sensor arrays and monitoring modules, real-time and continuous monitoring of pipeline status is achieved. Automatic acquisition and comparison of Hall sensor level data allows for timely assessment of pipeline corrosion risks, reducing reliance on manual inspection and minimizing labor costs and human error. Simultaneously, dynamically adjusting the acquisition time interval based on pipeline operation data makes the monitoring process more flexible and efficient, enabling rapid response to corrosion conditions. Analysis of corrosion area and real-time flow velocity further optimizes the monitoring strategy, ensuring pipeline safety and reliability and effectively reducing potential safety hazards and economic losses. This application improves pipeline monitoring efficiency and accuracy, enhancing its adaptability and intelligence.

[0081] This application provides an intelligent pipeline wall thickness monitoring system, such as... Figure 1 As shown, the system includes a sensor array 101 and a monitoring module 102.

[0082] The sensor array 101 and the monitoring module 102 are communicatively connected. Multiple sensor arrays 101 are provided, each including multiple Hall effect sensors. The sensor arrays 101 surround the pipeline to be monitored. The monitoring module 102 includes a data acquisition unit, a judgment unit, a processing unit, and an adjustment unit.

[0083] Optionally, the sensor array 101 can be uniformly arranged on the outer or inner wall of the pipe to be monitored. A Hall sensor is an electronic component based on the Hall effect, which can convert magnetic signals into electrical signals; therefore, a Hall sensor can acquire level data.

[0084] Optionally, the Hall sensors in the sensor array 101 can be wirelessly connected to the monitoring module 102. The monitoring module 102 can send control commands to each sensor in the sensor array via wireless signals.

[0085] The acquisition unit is configured to acquire the level data of each Hall sensor in the entire sensor array to obtain the first dataset. After a time interval, the acquisition unit acquires the level data of each Hall sensor again to obtain the second dataset.

[0086] The data acquisition time interval is determined by the acquisition unit based on the operating data of the pipeline to be monitored.

[0087] Specifically, multiple Hall sensors are evenly arranged in a sensor array around the pipe to be monitored. Each sensor can independently acquire information about the surrounding magnetic field. The sensor array periodically acquires Hall voltage signals caused by the fluid inside the pipe and converts these signals into level data. During the data acquisition process, a first dataset is formed. After a set acquisition time interval, the sensor array acquires Hall voltage signals again, generating a second dataset.

[0088] It should be noted that in natural gas or oil pipelines, fluid flow is often associated with changes in magnetic fields. For example, the magnetic field generated by the fluid itself within the pipeline causes magnets to move or alter the magnetic field distribution as the fluid flows, thus inducing changes in the magnetic field around the Hall sensor. The Hall sensor can detect these magnetic field changes and convert them into electrical level data (such as high and low voltage levels). By monitoring these changes in electrical level data, the operating status of the pipeline under monitoring, such as flow rate and speed, can be indirectly obtained. Therefore, the electrical level data in the first dataset can represent the operating status of the pipeline under monitoring during the first acquisition period, while the electrical level data in the second dataset can represent the operating status during the second acquisition period. Furthermore, differences in pipeline wall thickness can also lead to different magnetic fields generated when fluid flows through, resulting in different acquired electrical level data. The judgment unit is configured to compare the electrical level data corresponding to each sensor array in the second dataset with the electrical level data corresponding to each sensor array in the first dataset, and determine whether corrosion exists in the pipeline under monitoring based on the comparison results.

[0089] Specifically, by comparing these two datasets, the changes in Hall voltage (i.e., level data) are determined. A change in the level data indicates corrosion in the pipeline, leading to variations in pipe wall thickness. When a ferromagnetic pipe with the same nominal wall thickness enters the detection zone, a large number of flux lines will concentrate within the pipe wall. The uniform magnetic field on the pipe surface passes perpendicularly through the sensor, forming an initial level at its output. When a thinner section of the pipe wall enters the monitoring area, an inner wall thickness loss zone creates a magnetic field increment on the pipe surface. The judgment unit in the monitoring module compares these two datasets to determine whether corrosion has occurred in the pipeline.

[0090] In one possible implementation, since slight variations in the voltage levels are normal, corrosion is determined to exist in the pipeline if the change in voltage levels in the first and second datasets exceeds a threshold; otherwise, no corrosion is determined. The processing unit is configured to, when the judgment unit determines corrosion in the pipeline to be monitored, determine the corrosion area based on the voltage level variation, determine an adjustment coefficient for the acquisition time interval based on the corrosion rate, and adjust the acquisition time interval according to the adjustment coefficient.

[0091] Among them, the level variation refers to the level data that changes in the first dataset and the second dataset.

[0092] Specifically, when determining whether a pipeline under monitoring is corroded, the processing unit can determine the corrosion area of ​​the pipeline based on the changing voltage levels in two datasets. After the data acquisition time interval, if the area of ​​corrosion in the pipeline under monitoring is larger (or the corrosion is deeper), there will be more changing voltage levels. In this case, the processing unit can determine the corrosion area of ​​the pipeline under monitoring based on the magnitude of the voltage level changes.

[0093] Furthermore, since the corrosion area is the increase in corrosion area of ​​the monitored pipeline during the sampling time interval, the ratio of the corrosion area to the sampling time interval can be determined as the corrosion rate. The processing unit can adjust the sampling time interval based on the corrosion rate and the adjustment coefficient. For example, the sampling frequency can be reduced when corrosion is slow to lower the equipment's energy consumption, while the sampling frequency can be increased when the corrosion rate is fast, thereby improving pipeline safety monitoring.

[0094] In one possible implementation, a corrosion warning can be issued when the corrosion area exceeds a corrosion area threshold, thereby prompting staff to take action on the pipeline under monitoring.

[0095] The adjustment unit is configured to collect the corrosion area and real-time flow velocity of the pipeline to be monitored from the processing unit. A feature set is established based on the corrosion area and real-time flow velocity. The feature set is then clustered with the historical operating data of the pipeline to be monitored to determine similar sets. The adjustment coefficient of the acquisition time interval is determined based on the relationship between the adjustment coefficient of the historical acquisition time interval and the adjustment coefficient of the acquisition time interval within the similar sets.

[0096] Specifically, the processing unit can calculate the corrosion area based on changes in the level data and adjust the acquisition time interval through corrosion rate analysis to more effectively respond to changes in the pipeline's condition. The adjustment unit, on the other hand, can use historical data for cluster analysis to determine whether the acquisition time interval needs to be corrected, thus achieving a dynamic feedback mechanism. This allows the acquisition time interval to better adapt to the current corrosion conditions, ensuring the timeliness and accuracy of data acquisition.

[0097] In one possible implementation, since the real-time flow velocity of the monitored pipeline has a significant impact on the corrosion rate, a feature set can be established based on the corrosion area and the real-time flow velocity. Then, historical operational data can be used to perform cluster analysis with the feature set, grouping the data according to the similarity between samples. For example, this can help identify real-time flow velocities with similar corrosion rates. If the adjustment factor for the historical acquisition time interval in similar sets differs significantly from the current setting, then the adjustment factor for the current acquisition time interval should be adjusted. For example, if historical data shows that more frequent data acquisition is needed during periods of high corrosion risk, while the current acquisition frequency is low, then the acquisition frequency should be increased to ensure timely capture of corrosion changes.

[0098] Understandably, by integrating real-time data acquisition and dynamic feedback mechanisms, comprehensive and continuous monitoring of pipeline conditions is achieved. This enables rapid identification of corrosion risks and intelligent adjustment of monitoring frequency based on actual pipeline operating conditions, improving the flexibility and accuracy of monitoring. Through in-depth analysis of corrosion area and real-time flow velocity, the system can take effective measures before potential risks emerge, reducing safety hazards and economic losses.

[0099] In some embodiments of this application, the acquisition unit determines the acquisition time interval based on the operating data of the pipeline to be monitored, satisfying the following formula:

[0100]

[0101] Where Tc represents the acquisition time interval, D represents the pipe diameter, ρ represents the fluid density in the pipe, Ac represents the pipe cross-sectional area, Fs represents the Hall sensor sensitivity, β represents the temperature influence coefficient, β ranges from 0.01 to 0.05, and Tavg represents the average temperature of the fluid in the pipe to be monitored.

[0102] Specifically, pipe diameter and cross-sectional area directly affect flow velocity, which in turn interacts with the fluid's physical properties (such as density), influencing changes in corrosion rate. The sensitivity of the Hall sensor determines its ability to capture these changes, while the temperature influence coefficient considers the dynamic changes in the corrosion process caused by environmental factors. By combining these factors, a reasonable data acquisition interval can be determined, allowing for the appropriate adjustment of the data acquisition frequency to adapt to the actual conditions of the pipeline under different operating conditions. For example, different fluids have different corrosive abilities, thus requiring different acquisition intervals. Similarly, different temperatures correspond to different corrosion rates, also requiring different acquisition intervals at different temperatures.

[0103] Understandably, by incorporating multiple parameters into the calculation of the acquisition time interval, dynamic adaptive monitoring of the pipeline condition is achieved. Compared with traditional fixed-time interval acquisition methods, this approach can more effectively respond to changes in fluid and environmental conditions within the pipeline, ensuring timely capture of data changes in the early stages of corrosion. This not only improves the flexibility and accuracy of monitoring but also reduces potential safety hazards.

[0104] In some embodiments of this application, the determination unit determines whether the pipeline is corroded based on the comparison results, including: when any level data in the second dataset changes, the determination unit determines that the pipeline to be monitored is corroded. When all level data in the second dataset are the same as those in the first dataset, the determination unit determines that the pipeline to be monitored is not corroded.

[0105] In some embodiments of this application, the processing unit determines the corrosion area based on the level change, including: the processing unit determines the corrosion area based on the number of Hall sensors corresponding to the position of the level data change, and the corrosion area is proportional to the number of Hall sensors.

[0106] Specifically, when the sensor array determines the corrosion area based on voltage level changes, it can identify the Hall sensor corresponding to the changed voltage level by comparing the first and second datasets. The location of this Hall sensor indicates the location of the voltage level change, i.e., the location of corrosion. Then, the corrosion area can be determined based on the location of corrosion and the number of Hall sensors, pinpointing the exact location of corrosion. This allows for timely intervention by personnel in cases of large corrosion areas, preventing potential safety hazards.

[0107] In some embodiments of this application, the processing unit determines an adjustment coefficient for the sampling time interval based on the corrosion rate, and adjusts the sampling time interval based on the adjustment coefficient. This includes: the processing unit determines the corrosion rate based on the corrosion area and the sampling time interval, determines the adjustment coefficient for the sampling time interval corresponding to the corrosion rate interval to which the corrosion rate belongs, and adjusts the sampling time interval based on the adjustment coefficient for the sampling time interval corresponding to the corrosion rate interval.

[0108] In one possible implementation, when the corrosion rate is less than or equal to a first preset corrosion rate, the processing unit determines that the corrosion rate belongs to the first corrosion rate range, determines the first preset adjustment coefficient corresponding to the first preset corrosion rate range, and adjusts the acquisition time interval based on the first preset adjustment coefficient.

[0109] When the corrosion rate is greater than the first preset corrosion rate and less than or equal to the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the second corrosion rate range, determines the second preset adjustment coefficient corresponding to the second corrosion rate range, and adjusts the acquisition time interval based on the second preset adjustment coefficient.

[0110] When the corrosion rate is greater than the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the third corrosion rate range, determines the third preset adjustment coefficient corresponding to the third corrosion rate range, and adjusts the acquisition time interval based on the third preset adjustment coefficient.

[0111] Among them, the first corrosion rate is less than the second corrosion rate, the first preset adjustment coefficient is greater than the second preset adjustment coefficient, the second preset adjustment coefficient is greater than the third preset adjustment coefficient, and the third preset adjustment coefficient is greater than 0.

[0112] Optionally, the first preset corrosion rate, the second preset corrosion rate, the first preset adjustment coefficient, the second preset adjustment coefficient, and the third preset adjustment coefficient are all pre-set. Furthermore, these values ​​can be determined based on historical operating data of the pipeline to be monitored, thus ensuring that these preset data better reflect the pipeline's operating conditions.

[0113] Specifically, the processing unit can compare the corrosion rate with a first preset corrosion rate and a second preset corrosion rate, respectively. Based on the comparison results, it determines the adjustment coefficient of the acquisition time interval (e.g., the first preset adjustment coefficient, the second preset adjustment coefficient, and the third preset adjustment coefficient), and adjusts the acquisition time interval accordingly. For example, if the corrosion rate is high, the current acquisition time interval may be too long, posing a safety hazard. Therefore, the adjustment coefficient of the acquisition time interval corresponding to the current corrosion rate can be determined, and the acquisition time interval can be adjusted to shorten the acquisition time interval, increase the acquisition frequency, and reduce the risk of accidents. Understandably, the judgment unit determines whether corrosion exists in the pipeline by comparing the level data in the first and second datasets. If any level data in the second dataset changes, it is determined that corrosion exists in the pipeline; otherwise, it is considered that there is no corrosion. The processing unit determines the corrosion area based on the number of Hall sensors corresponding to the level changes, and the two are directly proportional. That is, the more sensors whose data changes, the larger the corrosion area. The processing unit compares the actual corrosion rate with multiple sets of preset corrosion rates to determine the corresponding adjustment coefficient of the acquisition time interval. Depending on the different corrosion rate ranges, the adjustment coefficient of the acquisition time interval is a different preset value to ensure timely response to corrosion progress.

[0114] Understandably, real-time comparison of electrical levels allows for rapid response to changes in pipeline conditions. Data-driven judgment methods reduce manual intervention and improve accuracy and real-time performance. The corrosion area is proportional to the number of sensors, ensuring a more comprehensive reflection of the actual corrosion situation. By setting adjustment coefficients for different corrosion rates and data acquisition intervals, the system can adapt to the actual conditions of the pipeline, ensuring effective monitoring under various corrosion conditions.

[0115] In some embodiments of this application, the adjustment unit performs cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine the similar set, including:

[0116] S1: The adjustment unit initializes K centroids in the historical running data, assigns the feature set to the nearest centroid, and forms K clusters.

[0117] S2: Adjust the unit to recalculate the centroid of each cluster.

[0118] S3: Adjust the unit to repeat S1 and S2 until the centroid no longer changes or the preset number of repetitions is completed.

[0119] S4: The adjustment unit constructs a similar set from the remaining historical running data in the cluster where the feature set is located.

[0120] The formula for calculating the centroid is as follows:

[0121]

[0122] Where Zk represents the centroid of the k-th cluster, |Ck| represents the number of data in the k-th cluster, and Ti represents the feature vector of the i-th data.

[0123] Specifically, historical operational data includes a set of historical features collected during historical monitoring, along with adjustment coefficients for the corresponding historical collection time intervals. This historical data is a database that gradually accumulates over time as the intelligent pipeline wall thickness monitoring system is used to quickly assess and correct the reasonableness of the time interval adjustment coefficients. K-means clustering, an unsupervised learning method, identifies the natural structure between data points by partitioning them. Continuous adjustment of the centroids ensures the accuracy of clustering, while the distribution of data points concentrates similar features, facilitating further analysis. The feature vector of each data set represents multidimensional data describing its operational state. By calculating the centroids, typical features of similar operational states can be extracted, providing strong support for pipeline monitoring.

[0124] Understandably, cluster analysis allows adjustment units to effectively identify similar pipeline states in historical operational data, forming accurate clusters. This enables the system to not only dynamically adapt to current monitoring needs but also to conduct more precise risk assessments and decisions based on historical data. In-depth analysis of pipeline operational status enables more efficient resource allocation and safety management.

[0125] In some embodiments of this application, the adjustment unit determines whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the adjustment coefficient of the historical acquisition time interval in the similar set and the adjustment coefficient of the acquisition time interval, including: the adjustment unit extracts the adjustment coefficient of the historical acquisition time interval in the similar set to form a historical adjustment group.

[0126] When there are data points in the historical adjustment group that are greater than the adjustment coefficient of the acquisition time interval and simultaneously there are data points that are less than the adjustment coefficient of the acquisition time interval, the adjustment unit determines to adjust the adjustment coefficient of the acquisition time interval. When all data points in the historical adjustment group are less than or equal to the adjustment coefficient of the acquisition time interval, or all data points are greater than or equal to the adjustment coefficient of the acquisition time interval, the adjustment unit determines not to adjust the adjustment coefficient of the acquisition time interval.

[0127] Specifically, when there are adjustment coefficients in the historical adjustment group that are both greater than and less than the current acquisition time interval, it indicates that there are different corrosion rates or environmental changes in the historical data. In this case, it may be necessary to reassess the current acquisition frequency to ensure that rapidly changing situations can be captured, while avoiding excessive acquisition that would waste resources. When all data in the historical adjustment group are less than or equal to, or all are greater than or equal to, the adjustment coefficient of the current acquisition time interval, it indicates that the historical acquisition frequency has been relatively stable, and the corrosion rate or other influencing factors have not fluctuated significantly within a certain range. In this case, the current acquisition frequency can be considered reasonable and no correction is needed.

[0128] Understandably, the adjustment unit extracts historical time interval adjustment coefficients from similar sets, forming a dataset called a "historical adjustment group." This data represents historical adjustments under similar conditions. When the historical adjustment group contains data both greater than and less than the current time interval adjustment coefficient, the adjustment unit determines that the current time interval adjustment coefficient needs to be corrected. This judgment indicates different historical adjustment experiences, suggesting that a reassessment may be necessary. If all data in the historical adjustment group are less than or equal to the current time interval adjustment coefficient, or all are greater than or equal to the coefficient, the adjustment unit determines that no correction is needed. This means the current settings may still be applicable and do not require change. Through the analysis of historical data, the adjustment unit can make more reasonable decisions based on past performance. The composition and conditional judgment of the historical adjustment group provide the system with a data-driven decision-making basis, helping to reduce interference from subjective human factors. By observing the distribution of data in the historical adjustment group, the suitability of the current time interval adjustment coefficient can be determined, thereby enabling a more flexible monitoring strategy.

[0129] Understandably, by introducing comparative analysis of historical time interval adjustment coefficients, the adjustment unit can achieve more intelligent adaptive adjustments. This not only improves the flexibility of monitoring but also ensures the effectiveness of adjustment measures, thereby enabling a faster and more accurate response to potential risks in the face of complex and changing pipeline operating environments, and ensuring the safe and stable operation of the pipeline.

[0130] In some embodiments of this application, when the adjustment unit determines that the adjustment coefficient of the acquisition time interval needs to be corrected, the adjustment unit constructs a first correction set from the data in the historical adjustment group that have an adjustment coefficient greater than the acquisition time interval. The adjustment unit constructs a second correction set from the data in the historical adjustment group that have an adjustment coefficient less than the acquisition time interval.

[0131] The adjustment coefficients for the acquisition time interval are corrected based on the first and second correction sets.

[0132] The adjustment unit corrects the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set, satisfying the following formula:

[0133]

[0134] Wherein, Kz is the adjustment coefficient of the corrected acquisition time interval, m is the number of adjustment coefficients of historical acquisition time intervals in the first correction set, Ki is the adjustment coefficient of the i-th historical acquisition time interval in the first correction set, K0 is the adjustment coefficient of the acquisition time interval, n is the number of adjustment coefficients of historical acquisition time intervals in the second correction set, and Kj is the adjustment coefficient of the j-th historical acquisition time interval in the second correction set.

[0135] Specifically, when adjustment coefficients greater than and less than the current acquisition time interval exist simultaneously in the historical adjustment group, it indicates that the corrosion rate or environmental conditions have fluctuated significantly in the past. Therefore, it is necessary to adjust the adjustment coefficients in a timely manner to ensure that the acquisition frequency is suitable for the current changing scenario and to improve the system's adaptability and flexibility. The adjustment unit needs to correct the adjustment coefficients of the acquisition time interval. This dynamic adjustment strategy helps optimize monitoring results and reduce risks.

[0136] Understandably, the adjustment unit constructs a first correction set from all data in the historical adjustment group that are greater than the current time interval adjustment coefficient. This data reflects adjustment experience under similar conditions. Similarly, the adjustment unit constructs a second correction set from all data in the historical adjustment group that are less than the current time interval adjustment coefficient, reflecting adjustment data that may be more suitable for current conditions. Adjustments are made based on the data in the first and second correction sets. By calculating based on these two sets of data, a new time interval adjustment coefficient is derived, thereby optimizing the monitoring strategy. By calculating the new coefficient, the system quickly adapts to changing pipeline conditions, ensuring that the data acquisition frequency matches actual needs. An adaptive monitoring mechanism is formed based on learning from historical data. By dividing historical adjustment data into two categories, the adjustment unit can make targeted adjustments, ensuring that the time interval adjustment coefficient is more consistent with the current pipeline operating status. This improves the scientific rigor and flexibility of monitoring, enabling rapid response to changes in the pipeline's internal and external environment, thereby effectively reducing potential safety risks.

[0137] The above embodiments, through the comprehensive use of sensor arrays and monitoring modules, achieve real-time and continuous monitoring of pipeline status. Automatic acquisition and comparison of Hall sensor level data promptly determines the presence of corrosion risks, reducing reliance on manual inspection and minimizing labor costs and human error. Simultaneously, dynamically adjusting the acquisition time interval based on pipeline operation data makes the monitoring process more flexible and efficient, enabling rapid response to corrosion conditions. Analysis of corrosion area and real-time flow velocity further optimizes the monitoring strategy, ensuring pipeline safety and reliability and effectively reducing potential safety hazards and economic losses. This application improves pipeline monitoring efficiency and accuracy, enhancing its adaptability and intelligence.

[0138] The basic hardware structure of monitoring module 102 includes Figure 2 The components included in the intelligent pipeline wall thickness monitoring device shown below. Figure 2 Taking the intelligent pipeline wall thickness monitoring device shown as an example, the hardware structure of the monitoring module 102 is introduced.

[0139] like Figure 2The diagram shown is a hardware structure schematic of an intelligent pipeline wall thickness monitoring device provided in an embodiment of this application. The intelligent pipeline wall thickness monitoring device includes a processor 21, a memory 22, a communication interface 23, and a bus 24. The processor 21, memory 22, and communication interface 23 are connected via the bus 24.

[0140] Processor 21 is the control center of the intelligent pipeline wall thickness monitoring device. It can be a single processor or a collective term for multiple processing elements. For example, processor 21 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0141] As one embodiment, processor 21 may include one or more CPUs, for example Figure 2 CPU 0 and CPU 1 are shown in the diagram.

[0142] The memory 22 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0143] In one possible implementation, the memory 22 can exist independently of the processor 21. The memory 22 can be connected to the processor 21 via a bus 24 and is used to store instructions or program code. When the processor 21 calls and executes the instructions or program code stored in the memory 22, it can implement the intelligent pipeline wall thickness monitoring method provided in the following embodiments of this application.

[0144] In this embodiment, the software programs stored in the memory 22 differ for the monitoring module 102, resulting in different functions implemented by the monitoring module 102. The functions performed by each device will be described in conjunction with the following flowchart.

[0145] In another possible implementation, the memory 22 can also be integrated with the processor 21.

[0146] Communication interface 23 is used for connecting the intelligent pipeline wall thickness monitoring device with other devices via a communication network, such as Ethernet, wireless access network, or wireless local area network (WLAN). Communication interface 23 may include a receiving unit for receiving data and a sending unit for sending data.

[0147] Bus 24 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0148] It should be pointed out that, Figure 2 The structure shown does not constitute a limitation on intelligent pipeline wall thickness monitoring devices, except Figure 2 In addition to the components shown, the intelligent pipe wall thickness monitoring device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0149] The intelligent pipeline wall thickness monitoring method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0150] The intelligent pipe wall thickness monitoring method provided in this application embodiment is applied to... Figure 1 The monitoring module 102 in the intelligent pipeline wall thickness monitoring system shown. For example... Figure 3 As shown, this intelligent pipeline wall thickness monitoring method includes:

[0151] S301: Collect the level data of each Hall sensor in all sensor arrays to obtain the first dataset; after the acquisition time interval, collect the level data of each Hall sensor again to obtain the second dataset.

[0152] The data collection time interval is determined based on the operating data of the pipeline to be monitored.

[0153] S302: Compare the level data corresponding to each sensor array in the second dataset with the level data corresponding to each sensor queue in the first dataset, and determine whether there is corrosion in the pipeline based on the comparison results.

[0154] S303: When corrosion is determined in the pipeline, the corrosion area is determined based on the level change, and the adjustment coefficient of the sampling time interval is determined based on the corrosion rate. The sampling time interval is then adjusted based on the adjustment coefficient.

[0155] S304: Collect the corrosion area and the real-time flow velocity of the pipeline to be monitored. Establish a feature set based on the corrosion area and real-time flow velocity. Perform cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine the similar set. Determine whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the historical time interval adjustment coefficient and the acquisition time interval adjustment coefficient within the similar set.

[0156] Specifically, an array of sensors surrounding the pipeline under monitoring can acquire voltage levels over different time periods, and the presence of corrosion can be determined by comparing these voltage levels. The monitoring module can also determine the corrosion area based on voltage level fluctuations obtained from the voltage level comparison and adjust the sampling time interval according to the corrosion rate. For example, the sampling frequency can be reduced when corrosion is slow to lower energy consumption, while the sampling frequency can be increased when the corrosion rate is fast, thus improving pipeline safety. Furthermore, the monitoring module can determine whether to adjust the sampling time interval adjustment factor based on real-time flow velocity and corrosion area, making the set sampling time interval more consistent with the current pipeline corrosion situation and better meeting user needs.

[0157] Understandably, by comprehensively utilizing sensor arrays and monitoring modules, real-time and continuous monitoring of pipeline status is achieved. Automatic acquisition and comparison of Hall sensor level data allows for timely assessment of pipeline corrosion risks, reducing reliance on manual inspection and minimizing labor costs and human error. Simultaneously, dynamically adjusting the acquisition time interval based on pipeline operation data makes the monitoring process more flexible and efficient, enabling rapid response to corrosion conditions. Analysis of corrosion area and real-time flow velocity further optimizes the monitoring strategy, ensuring pipeline safety and reliability and effectively reducing potential safety hazards and economic losses. This application improves pipeline monitoring efficiency and accuracy, enhancing its adaptability and intelligence.

[0158] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0159] This application embodiment can divide the intelligent pipeline wall thickness monitoring device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0160] like Figure 4 The diagram shown is a structural schematic of an intelligent pipeline wall thickness monitoring device provided in an embodiment of this application. Figure 4 The intelligent pipeline wall thickness monitoring device shown includes: a data acquisition unit 401, a judgment unit 402, a processing unit 403, and an adjustment unit 404;

[0161] The acquisition unit 401 is used to acquire the level data of each Hall sensor in the sensor array to obtain a first dataset; after an acquisition time interval, it acquires the level data of each Hall sensor again to obtain a second dataset. The acquisition time interval is determined based on the operating data of the pipeline to be monitored.

[0162] The judgment unit 402 is used to compare the level data corresponding to each sensor array in the second dataset with the level data corresponding to each sensor queue in the first dataset, and to determine whether there is corrosion in the pipeline based on the comparison result.

[0163] The processing unit 403 is used to determine the corrosion area based on the level change when corrosion is detected in the pipeline, determine the adjustment coefficient of the acquisition time interval based on the corrosion rate, and adjust the acquisition time interval based on the adjustment coefficient.

[0164] The adjustment unit 404 is used to collect the corrosion area and the real-time flow velocity of the pipeline to be monitored. It establishes a feature set based on the corrosion area and the real-time flow velocity, performs cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine the similar set, and determines whether to correct the adjustment coefficient of the acquisition time interval based on the relationship between the historical time interval adjustment coefficient and the acquisition time interval adjustment coefficient in the similar set.

[0165] Optionally, the acquisition unit 401 is specifically used for:

[0166] The data collection time interval is determined based on the operating data of the pipeline to be monitored, satisfying the following formula:

[0167]

[0168] Where Tc represents the acquisition time interval, D represents the pipe diameter, ρ represents the fluid density in the pipe, Ac represents the pipe cross-sectional area, Fs represents the Hall sensor sensitivity, β represents the temperature influence coefficient, β ranges from 0.01 to 0.05, and Tavg represents the average temperature of the fluid in the pipe to be monitored.

[0169] Optionally, the judgment unit 402 is specifically used for:

[0170] When any level data in the second dataset changes, the judgment unit determines that the pipeline to be monitored is corroded;

[0171] When the level data in the second dataset is the same as that in the first dataset, the judgment unit determines that there is no corrosion in the pipeline to be monitored.

[0172] Optionally, the processing unit 403 is specifically used for:

[0173] The corrosion area is determined by the number of Hall sensors corresponding to the position of the change in the level data, and the corrosion area is directly proportional to the number of Hall sensors.

[0174] Optionally, the processing unit 403 is specifically used for:

[0175] The processing unit determines the corrosion rate based on the corrosion area and the acquisition time interval, determines the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval to which the corrosion rate belongs, and adjusts the acquisition time interval based on the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval.

[0176] Optionally, the processing unit 403 is specifically used for:

[0177] When the corrosion rate is less than or equal to the first preset corrosion rate, the processing unit determines that the corrosion rate belongs to the first corrosion rate range, determines the first preset adjustment coefficient corresponding to the first preset corrosion rate range, and adjusts the acquisition time interval based on the first preset adjustment coefficient.

[0178] When the corrosion rate is greater than the first preset corrosion rate and less than or equal to the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the second corrosion rate range, determines the second preset adjustment coefficient corresponding to the second corrosion rate range, and adjusts the acquisition time interval based on the second preset adjustment coefficient.

[0179] When the corrosion rate is greater than the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the third corrosion rate range, determines the third preset adjustment coefficient corresponding to the third corrosion rate range, and adjusts the acquisition time interval based on the third preset adjustment coefficient.

[0180] Among them, the first corrosion rate is less than the second corrosion rate, the first preset adjustment coefficient is greater than the second preset adjustment coefficient, the second preset adjustment coefficient is greater than the third preset adjustment coefficient, and the third preset adjustment coefficient is greater than 0.

[0181] Optionally, the adjusting unit 404 is specifically used for:

[0182] S1: The adjustment unit initializes K centroids in the historical running data, assigns feature sets to the nearest centroids, and forms K clusters;

[0183] S2: Adjust the unit to recalculate the centroid of each cluster;

[0184] S3: Adjust the unit to repeat S1 and S2 until the centroid no longer changes or the preset number of repetitions is completed;

[0185] S4: The adjustment unit constructs a similar set from the remaining historical running data in the cluster where the feature set is located;

[0186] The formula for calculating the centroid is as follows:

[0187]

[0188] Where Zk represents the centroid of the k-th cluster, |Ck| represents the number of data in the k-th cluster, and Ti represents the feature vector of the i-th data.

[0189] Optionally, the adjusting unit 404 is specifically used for:

[0190] The adjustment unit extracts the adjustment coefficients of historical collection time intervals from similar sets to form historical adjustment groups;

[0191] When there are data in the historical adjustment group that have an adjustment coefficient greater than the collection time interval and at the same time there are data that have an adjustment coefficient less than the collection time interval, the adjustment unit determines to correct the adjustment coefficient of the collection time interval.

[0192] When all data in the historical adjustment group are less than or equal to the adjustment coefficient of the acquisition time interval, or are greater than or equal to the adjustment coefficient of the acquisition time interval, the adjustment unit determines not to adjust the adjustment coefficient of the acquisition time interval.

[0193] Optionally, the adjusting unit 404 is specifically used for:

[0194] The adjustment unit constructs the first correction set from the historical adjustment group data that have an adjustment coefficient greater than the inter-collection interval;

[0195] The adjustment unit constructs a second correction set from the historical adjustment group containing adjustment coefficients that are less than the acquisition time interval;

[0196] The adjustment unit adjusts the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set.

[0197] Optionally, the adjusting unit 404 is specifically used for:

[0198] The adjustment coefficients for the acquisition time interval are corrected based on the first and second correction sets, satisfying the following formula:

[0199]

[0200] Wherein, Kz is the adjustment coefficient of the corrected acquisition time interval, m is the number of adjustment coefficients of historical acquisition time intervals in the first correction set, Ki is the adjustment coefficient of the i-th historical acquisition time interval in the first correction set, K0 is the adjustment coefficient of the acquisition time interval, n is the number of adjustment coefficients of historical acquisition time intervals in the second correction set, and Kj is the adjustment coefficient of the j-th historical acquisition time interval in the second correction set.

[0201] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0202] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0203] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0204] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An intelligent pipeline wall thickness monitoring system, characterized in that, include: A sensor array and a monitoring module, wherein the monitoring module is connected to the sensor array; The sensor array is provided in multiple ways, and each sensor array is arranged around the pipe to be monitored. Each sensor array includes multiple Hall sensors. The monitoring module includes a data acquisition unit, a judgment unit, a processing unit, and an adjustment unit; The acquisition unit is configured to acquire the level data of each Hall sensor in all the sensor arrays to obtain a first dataset; after an acquisition time interval, the level data of each Hall sensor is acquired again to obtain a second dataset; the acquisition time interval is determined by the acquisition unit based on the operating data of the pipeline to be monitored; The judgment unit is configured to compare the level data corresponding to each sensor array in the second dataset with the level data corresponding to each sensor array in the first dataset, and determine whether the pipeline to be monitored is corroded based on the comparison result; The processing unit is configured to, when the judgment unit determines that the pipeline to be monitored is corroded, determine the corrosion area based on the level change, determine the adjustment coefficient of the acquisition time interval based on the corrosion rate, and adjust the acquisition time interval based on the adjustment coefficient; the level change refers to the level data that changes in the first dataset and the second dataset. The adjustment unit is configured to collect the corrosion area and the real-time flow rate of the pipeline to be monitored from the processing unit, establish a feature set based on the corrosion area and the real-time flow rate, perform cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine a similar set, and determine whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the adjustment coefficient of the historical acquisition time interval and the adjustment coefficient of the acquisition time interval within the similar set. The adjustment unit performs cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine similar sets, including: S1: The adjustment unit initializes K centroids in the historical running data, and assigns the feature set to the nearest centroid to form K clusters; S2: The adjustment unit recalculates the centroid of each cluster; S3: The adjustment unit repeats S1 and S2 until the centroid no longer changes or the preset number of repetitions is completed; S4: The adjustment unit constructs a similar set from the remaining historical running data in the cluster where the feature set is located; The formula for calculating the centroid is as follows: Where Zk represents the centroid of the k-th cluster, Let represent the number of data in the k-th cluster, and Ti represent the feature vector of the i-th data.

2. The intelligent pipeline wall thickness monitoring system according to claim 1, characterized in that, The acquisition unit determines the acquisition time interval based on the operating data of the pipeline to be monitored, satisfying the following formula: Where Tc represents the data acquisition time interval, and D represents the pipe diameter. The value represents the fluid density inside the pipe, Ac represents the cross-sectional area of ​​the pipe, and Fs represents the sensitivity of the Hall sensor. This represents the temperature influence coefficient, with β ranging from 0.01 to 0.

05. This indicates the average temperature of the fluid inside the pipeline to be monitored.

3. The intelligent pipeline wall thickness monitoring system according to claim 1, characterized in that, The judgment unit determines whether the pipeline is corroded based on the comparison results, including: When any of the level data in the second dataset changes, the judgment unit determines that the pipeline to be monitored is corroded; When the level data in the second dataset is the same as that in the first dataset, the judgment unit determines that the pipeline to be monitored is not corroded.

4. The intelligent pipeline wall thickness monitoring system according to claim 1, characterized in that, The processing unit determines the corrosion area based on level changes, including: The processing unit determines the corrosion area based on the number of Hall sensors corresponding to the position of the change in the level data, and the corrosion area is directly proportional to the number of Hall sensors.

5. The intelligent pipeline wall thickness monitoring system according to claim 4, characterized in that, The processing unit determines an adjustment coefficient for the acquisition time interval based on the corrosion rate, and adjusts the acquisition time interval according to the adjustment coefficient, including: The processing unit determines the corrosion rate based on the corrosion area and the acquisition time interval, determines the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval to which the corrosion rate belongs, and adjusts the acquisition time interval based on the adjustment coefficient of the acquisition time interval corresponding to the corrosion rate interval.

6. The intelligent pipeline wall thickness monitoring system according to claim 5, characterized in that, The processing unit determines an adjustment coefficient for the sampling time interval corresponding to the corrosion rate range to which the corrosion rate belongs, and adjusts the sampling time interval based on the adjustment coefficient, including: When the corrosion rate is less than or equal to the first preset corrosion rate, the processing unit determines that the corrosion rate belongs to the first corrosion rate range, determines the first preset adjustment coefficient corresponding to the first preset corrosion rate range, and adjusts the acquisition time interval based on the first preset adjustment coefficient. When the corrosion rate is greater than the first preset corrosion rate and less than or equal to the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the second corrosion rate range, determines the second preset adjustment coefficient corresponding to the second corrosion rate range, and adjusts the acquisition time interval based on the second preset adjustment coefficient. When the corrosion rate is greater than the second preset corrosion rate, the processing unit determines that the corrosion rate belongs to the third corrosion rate range, determines the third preset adjustment coefficient corresponding to the third corrosion rate range, and adjusts the acquisition time interval based on the third preset adjustment coefficient. Wherein, the first corrosion rate is less than the second corrosion rate, the first preset adjustment coefficient is greater than the second preset adjustment coefficient, the second preset adjustment coefficient is greater than the third preset adjustment coefficient, and the third preset adjustment coefficient is greater than 0.

7. The intelligent pipeline wall thickness monitoring system according to claim 1, characterized in that, The adjustment unit determines whether to adjust the adjustment coefficient of the acquisition time interval based on the relationship between the adjustment coefficient of the historical acquisition time interval within the similar set and the adjustment coefficient of the acquisition time interval, including: The adjustment unit extracts the adjustment coefficients of the historical collection time intervals from the similar set to form a historical adjustment group; When there is data in the historical adjustment group that is greater than the adjustment coefficient of the collection time interval and at the same time there is data that is less than the adjustment coefficient of the collection time interval, the adjustment unit determines to correct the adjustment coefficient of the collection time interval. When all data in the historical adjustment group are less than or equal to the adjustment coefficient of the acquisition time interval, or are greater than or equal to the adjustment coefficient of the acquisition time interval, the adjustment unit determines that the adjustment coefficient of the acquisition time interval should not be adjusted.

8. The intelligent pipeline wall thickness monitoring system according to claim 7, characterized in that, When the adjustment unit determines to adjust the adjustment coefficient of the acquisition time interval, The adjustment unit constructs a first correction set from the historical adjustment group containing data with adjustment coefficients greater than the collection time interval. The adjustment unit constructs a second correction set from the data in the historical adjustment group whose adjustment coefficients are less than the collection time interval; The adjustment unit adjusts the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set.

9. The intelligent pipeline wall thickness monitoring system according to claim 8, characterized in that, The adjustment unit adjusts the adjustment coefficient of the acquisition time interval according to the first correction set and the second correction set, satisfying the following formula: ； in, Let m be the adjustment factor for the corrected acquisition time interval, m be the number of adjustment factors for historical acquisition time intervals in the first correction set, Ki be the adjustment factor for the i-th historical acquisition time interval in the first correction set, K0 be the adjustment factor for the acquisition time interval, n be the number of adjustment factors for historical acquisition time intervals in the second correction set, and Kj be the adjustment factor for the j-th historical acquisition time interval in the second correction set.

10. An intelligent pipeline wall thickness monitoring method, applied to the intelligent pipeline wall thickness monitoring system as described in any one of claims 1-9, characterized in that, include: Collect the level data of each Hall sensor in all sensor arrays to obtain the first dataset; After the acquisition time interval, the level data of each Hall sensor is acquired again to obtain a second dataset; the acquisition time interval is determined based on the operating data of the pipeline to be monitored. The voltage level data corresponding to each sensor array in the second dataset is compared with the voltage level data corresponding to each sensor queue in the first dataset, and the presence of corrosion in the pipeline is determined based on the comparison results. When corrosion is detected in the pipeline, the corrosion area is determined based on the level change, and the adjustment coefficient of the sampling time interval is determined based on the corrosion rate. The sampling time interval is then adjusted based on the adjustment coefficient. The corrosion area and the real-time flow velocity of the pipeline to be monitored are collected. A feature set is established based on the corrosion area and the real-time flow velocity. The feature set is clustered with the historical operating data of the pipeline to be monitored to determine the similar set. The relationship between the historical time interval adjustment coefficient and the collection time interval adjustment coefficient in the similar set is used to determine whether the collection time interval adjustment coefficient should be corrected. The step of performing cluster analysis on the feature set and the historical operating data of the pipeline to be monitored to determine the similar set includes: S1: Initialize K centroids in the historical running data, and assign the feature set to the nearest centroid to form K clusters; S2: Recalculate the centroid of each cluster; S3: Repeat S1 and S2 until the centroid no longer changes or the preset number of repetitions is completed; S4: Construct a similar set from the remaining historical running data in the cluster where the feature set is located; The formula for calculating the centroid is as follows: Where Zk represents the centroid of the k-th cluster, Let represent the number of data in the k-th cluster, and Ti represent the feature vector of the i-th data.

11. An intelligent pipeline wall thickness monitoring device, characterized in that, include: A processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer-executable instructions, and when the device is running, the processor executes the computer-executable instructions stored in the memory to cause the device to perform the system of any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is capable of executing the system as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes: a computer program or instructions that, when run on a computer, cause the computer to perform the system as described in any one of claims 1 to 9.

Images